# Brief Documentation - Full Content > This file contains the complete plain-text content of all Brief documentation pages. > For AI agents that want to fetch all help content in a single request. > > Last updated: 2026-09-10 > Total pages: 45 --- # What is Brief URL: https://briefhq.ai/docs/what-is-brief/ Category: Getting Started Last Updated: 2026-07-05 Brief is a Navigator that aligns your team and agents from vision to impact at AI speed. It ensures every decision is informed, every builder is aligned, and no team ships blind. The Problem When you use AI coding agents like Cursor, Claude Code, or Windsurf, they're building blind. They don't know your customers, can't remember decisions you made last week, and have no visibility into your roadmap or strategic priorities. Brief solves this by navigating your team and agents to the context that matters. It builds your Product Graph from tools you already use (Linear, Notion, GitHub, meeting transcripts, analytics) and keeps everyone aligned. Who Brief is For Brief is built for teams whose AI is building blindly and need a Navigator from vision to impact. It shows up in a few common shapes: - The founder or CEO who became the accidental PM. You're setting direction, talking to customers, and steering the roadmap without a formal product function. Brief turns the context in your head into a Product Graph your whole team — and every AI agent — can build from. - The engineering leader whose agents build the wrong thing. Your team ships fast with AI, but velocity in the wrong direction is waste. Brief aligns every agent with your decisions, customers, and strategy so speed compounds instead of scatters. - The PM who now codes with AI. You can build what you spec — but your AI keeps suggesting approaches the team already rejected. Brief gives it your decision history and research signals so it proposes what actually fits. Brief fits technical founders from pre-seed through Series A, and it scales up: mid-market and enterprise product teams use Brief to keep larger organizations — and larger fleets of agents — aligned on the same context. How Brief Works Brief connects three critical pieces of your product development: Your Product Context Brief automatically collects data from tools you already use—Linear or Asana for work tracking, GitHub for your codebase, Notion or Google Drive for documentation, Fireflies, Fathom, or Granola for customer calls, and PostHog for analytics. See the full list in the Integrations Overview. Strategic Intelligence Brief analyzes and synthesizes this data to understand who your users are, what features you've built, what decisions you've made, your velocity, and what customers are saying. AI Coding Agents Brief navigates your AI coding tools (Cursor, Claude Code, Windsurf, VS Code) to the context they need through MCP. Every builder stays aligned. Key Capabilities Navigator for AI Agents Brief is built from the ground up to align your team and agents. It's not a dashboard you look at—it's context that navigates your AI tools to the right answers. Chat, Wherever You Work Ask Brief anything about your product from the surface you're already in: the web app, Slack DMs, Microsoft Teams, the mobile app, or the Chrome extension. Paste a screenshot, attach a doc, capture a decision, or create a ticket in Linear, Jira, or Asana — Brief answers from your Product Graph everywhere. Agents That Work For You Beyond chat, Brief runs an agents layer on top of your context. Build custom agents by chatting with the Agent Builder, get a Weekly Brief digest of what changed and what matters, and let Proactive Brief nudge you when a decision needs review or a signal surges. Start with the Agents Overview. Automatic Product Graph No manual data entry required. Brief builds your Product Graph from tools you already use, keeping everyone aligned automatically. Always Up-to-Date Brief's understanding grows over time as you connect more tools and as your product evolves. It continuously syncs to stay current. No Team Ships Blind Unlike code assistants that only understand syntax, Brief ensures every builder is aligned with your decisions, customers, and strategy. Why Use Brief? vs. Traditional PM Tools Linear, Jira, and Notion are where work happens. Brief is why work happens. Brief reads from those tools and creates an understanding layer on top that AI can query. Traditional tools store information; Brief synthesizes understanding. Traditional tools are for humans to read; Brief is for AI agents to query. vs. Using AI Coding Agents Alone Without Brief | With Brief AI is building blind | AI is aligned with your vision Context resets every session | Context persists and compounds AI suggests rejected approaches | AI knows what you've decided Decisions live in Slack threads | Decisions are in your Product Graph Example: Ask Cursor "What should we build next?" without Brief, and it'll give generic advice. Ask with Brief, and it gets navigated to your research signals, checks what's already built, reviews recent decisions, and gives you prioritized recommendations. Every builder aligned. Getting Started Ready to try Brief? Check out our Quick Start Guide to get set up in 5 minutes. Common Use Cases - Onboarding new engineers who need to be aligned from day one - Deciding what to build next based on research signals and velocity - Navigating to past decisions with searchable decision history - Keeping your entire team aligned from vision to impact How does Brief work with AI coding tools? Brief navigates AI coding tools like Cursor, Claude Code, Windsurf, and VS Code to your product context through MCP. When you're coding, Brief aligns your AI with your decisions, customers, and strategy. Every builder stays aligned without leaving their IDE. See MCP Setup to connect yours. What permissions does Brief need? Brief needs read permissions to extract context from your connected tools. You grant these automatically during OAuth flows. For MCP write features (like creating tasks), Brief also needs write permissions to specific integrations. How long does it take to set up Brief? You can set up Brief in about 5 minutes. Create your account, add company information, connect your first integration (recommended: Linear), and you're done. Brief starts syncing immediately and builds understanding in the background. --- # Quick Start Guide URL: https://briefhq.ai/docs/quick-start/ Category: Getting Started Last Updated: 2026-07-05 Get Brief up and running in just 5 minutes. This guide walks you through account setup, connecting your tools, and getting your team aligned. Before You Start Brief works best when you have at least one of these tools: - Linear, Jira, or Asana for work tracking - Notion, Confluence, or Google Drive for documentation - GitHub for codebase analysis You can start with just one and add more later—Brief builds your Product Graph as you connect more tools. Step 1: Create Your Account Go to app.briefhq.ai Sign up with Google, GitHub, or email Create your organization (each team gets an isolated workspace) Step 2: Add Company Information Brief starts with a short company step that collects: - Organization name - Website - Your title - Development team size Brief uses that to personalize the workspace and kick off downstream context extraction after onboarding. Step 3: Connect Your First Integration Start with the tool you use most: Linear (Recommended) Linear is great for first-time setup because it gives Brief: - Velocity data (how fast you ship) - What's being built right now - Your work pipeline Open Integrations in Brief Find Linear and click Connect Authorize Brief in the OAuth flow Choose the teams or scopes you want Brief to use Finish setup and let the initial sync start Other Integrations GitHub/GitLab — Shows what's actually built vs. what's planned Notion/Confluence/Google Drive/SharePoint — Extracts strategy and product docs Jira/Asana — Alternative work tracking tools Fireflies/Fathom/Granola/Plaud/Zoom/Gong — Captures customer research from calls PostHog/Mixpanel — Analytics for understanding user behavior Slack/Microsoft Teams — Chat with Brief where your team already talks See the full list in the Integrations Overview. Step 4: Review Extracted Context As Brief analyzes your connected tools, you'll see review modals when data is ready. Visit different sections to review and approve: - Product Context — Company info, goals, and competitive advantages - Features — Product capabilities Brief found - Personas — Customer segments Brief identified - Decisions — Important choices to log Approve or edit the extracted data. Brief won't overwrite your changes once you approve them. Step 5: Ask Your First Question Now try Brief chat. The empty state shows a small set of contextual presets based on your page, connected tools, and how long you've been using Brief. Common examples include: - 🔭 "I'm new to Brief, show me around" - 🚏 "What should we build next?" - 👤 "Who are we building for?" - 📏 "How do we know it's working?" - ⚖️ "What should we stop doing?" Try These Questions - "Do we already have authentication?" (checks your actual codebase) - "What did we decide about the pricing model?" (searches decision history) - "What are customers saying about onboarding?" (searches research signals) Step 6: Connect to Your AI Coding Tools (Optional) Want Brief to work with Cursor, Claude Code, VS Code, Claude Desktop, or Codex? Set up the Model Context Protocol: Open the Integrations page in Brief Launch the MCP setup flow and pick your AI tool's tab Follow the host-native install steps — every client opens a browser for OAuth on first tool call. No API key required. If your host surfaces Brief prompts, start with /brief-setup after connecting. Returning users on a new surface can use /brief-welcome-back; otherwise the MCP setup flow falls back to brief_get_onboarding_context and, for fresh coding repos, brief_ask(..., onboarding: true). See the Brief MCP Setup Guide for per-client instructions, or the Brief CLI Setup if you prefer shell-based access for your coding agent. Next Steps - Connect More Integrations — More tools = better understanding - Learn Key Concepts — Understand how Brief builds your Product Graph - Tips for Better Answers — Get better answers from Brief - Meet Brief Agents — Scheduled agents and digests built on your connected tools, plus billing details when you're ready to add your team Troubleshooting Integration won't connect Make sure you have admin access to the tool you're connecting. Brief needs read permissions to extract context. Data isn't syncing Initial sync takes 1-5 minutes depending on the tool and your workspace size. Check the Integrations page to see sync status. Answers seem incomplete Brief provides better answers as you connect more data sources. Start with Linear + GitHub, then add documentation and customer research tools for richer context. Need more help? Check our Troubleshooting Guide or contact support. --- # Key Concepts URL: https://briefhq.ai/docs/key-concepts/ Category: Getting Started Last Updated: 2026-07-05 Understanding these core concepts will help you get the most value from Brief—your Navigator from vision to impact. How Brief Builds Your Product Graph Brief builds your Product Graph automatically by connecting to your existing tools. It extracts and synthesizes: - Features — Your product capabilities and their status - Personas — Your customer segments and their needs - Decisions — Important choices with rationale - Goals — Your strategic objectives - Velocity — How fast you ship - Research Signals — What customers are saying The Process You provide company info during onboarding Brief syncs your tools (Linear, GitHub, Notion, etc.) Brief builds your Product Graph from decisions, customers, and strategy You review and approve what Brief found It updates continuously as new data arrives Brief keeps every builder aligned as you connect more tools and as your product evolves. Data Sources & Integrations Brief connects to your tools in two ways: One-Click OAuth Linear, GitHub, GitLab, Notion, Confluence, Jira, Asana, Fathom, Granola, Plaud, Zoom, Gong, Google Drive, SharePoint, HubSpot, Attio, Supabase, Miro, Slack, Microsoft Teams, Webex These use OAuth—you click "Connect," authorize Brief, choose what to share, and you're done. After authorization, many integrations include a scoping step where you select exactly what data Brief can access. - Sync time: 30 seconds to 5 minutes depending on workspace size - Update frequency: Continuous (webhooks + polling) API Key Setup Fireflies, PostHog, Mixpanel, Stripe, LangFuse, Arize, Lightfield These require you to create an API key and paste it into Brief. PostgreSQL uses a similar guided setup where you enter database connection details. - Why API keys? These tools don't offer OAuth for their APIs - Security: Brief stores your keys encrypted Team vs. Personal Connections Some integrations are team connections—an admin connects once and the whole workspace is covered (for example Fireflies, Gong, Stripe, HubSpot, Supabase). Others are personal connections—each user authorizes their own account, so Brief only sees what that user can see (for example Linear, GitHub, Notion, Slack). Communication Tools Slack, Microsoft Teams, Webex Brief lives where your team talks. In Slack you can DM Brief directly for full chat—streaming answers, decision capture, and file understanding—or use the /decide command to log decisions from any conversation. Microsoft Teams is a full chat surface too, and Webex spaces feed team context into your Product Graph. Current State vs Product Understanding Brief distinguishes between what's actually built and what's planned or understood: Current State (Ground Truth) What's actually in your codebase right now—analyzed from GitHub. This is reality. Use Current State when: - "Do we have authentication?" - "What's our tech stack?" - "Is feature X already built?" Product Understanding (Synthesized) Your company context, velocity, personas, and goals—synthesized from all your tools. This is strategic intelligence. Use Product Understanding when: - "Who are our users?" - "What should we build next?" - "Why did we decide X?" Documents & Decisions Documents General product documents you create in Brief—specs, strategy docs, planning docs. These live in your Brief workspace and are searchable via chat. Decisions A special type of document that records important choices with: - What was decided - Why that choice was made - When and by whom Decisions are immutable—they can be archived but never deleted. This creates an audit trail of your product evolution. Logging Decisions From Slack: From Chat: From the Web UI: Navigate to Documents → New Decision When an AI later asks "Why did we choose React?", Brief can surface the original decision with full context. Model Context Protocol (MCP) MCP is how Brief navigates AI coding agents like Cursor, Claude Code, Windsurf, and VS Code to the context they need. What Brief Provides via MCP When you ask your AI coding agent a question, Brief navigates it to: - Your Product Graph (personas, features, goals) - Decision history ("Why did we do X?") - Current State ("Do we already have Y?") - Create new documents with your approval How It Works You install Brief's MCP server in your AI tool You authenticate via OAuth Brief navigates your AI to the right context Every builder stays aligned, session after session Preset Prompts Brief's chat suggests contextual presets—starter prompts chosen for you based on the page you're on, which tools you've connected, and how long you've been using Brief. Common examples include: - 🔭 "I'm new to Brief" — Guided tour - 🚏 "What should we build next?" — Evidence-backed priorities - 👤 "Who are we building for?" — ICP with data - 📏 "How do we know it's working?" — Measurement plan The presets you see change as your workspace grows, so they always query the data sources you actually have. Brief Agents Beyond chat, Brief runs agents—scheduled workers that turn your connected tools into recurring insight. You can create custom agents by chatting with the Agent Builder, run them on a weekly cadence with results delivered in-app and to Slack, and get org-wide digests like the Weekly Brief. Brief also proactively nudges you with review invitations and reminders when something needs your attention. Learn more in the Agents Overview. Next Steps Now that you understand the key concepts: - Connect More Tools — More sources = better understanding - Learn What to Ask — Get better answers from Brief - Set Up MCP — Connect to your coding tools --- # What is MCP (Model Context Protocol)? URL: https://briefhq.ai/docs/what-is-mcp/ Category: Getting Started Last Updated: 2026-01-07 Model Context Protocol (MCP) is an open standard developed by Anthropic that allows AI assistants to securely connect to external data sources and tools. It's the technology that lets Brief navigate your AI coding assistant to your product context. MCP in Plain English Think of MCP like a USB port for AI assistants. Just as USB lets you plug any device into your computer, MCP lets AI tools plug into any compatible data source. Before MCP | With MCP AI only knows what's in its training data | AI can access live data from your tools Context limited to current conversation | Context includes your docs, decisions, codebase Every AI tool builds custom integrations | One standard works across all AI tools Why MCP Matters for Development Teams Your AI Stops Building Blind Without MCP, Cursor or Claude only knows what you paste into the chat. With MCP, Brief navigates your AI to: - What decisions you've made and why - Who your customers are - What's already built in your codebase - What your team is working on right now Every Session Aligned MCP connections are persistent. Brief keeps your Product Graph current, so every AI session starts aligned—not blind. One Integration, Many AI Tools Brief's MCP server works with Cursor, Claude Code, Claude Desktop, Windsurf, VS Code, and any MCP-compatible tool. Connect once, every builder aligned. How does MCP work? AI Assistant sends a query via MCP (e.g., "What did we decide about authentication?") MCP Server (Brief) receives the query and searches your data Response flows back to the AI assistant with relevant context AI Assistant uses that context to give you better answers MCP vs. Traditional Integrations Aspect | Traditional API | MCP Who builds it | Each AI tool builds their own | One standard, many tools Security | Varies by implementation | OAuth-based, standardized Context quality | Often limited | Rich, structured context Setup effort | Different for each tool | One setup works everywhere Getting Started with MCP Ready to give your AI coding assistant access to Brief? Set up Brief MCP — Connect Brief to Cursor, Claude, or your preferred tool Quick Start Guide — Get Brief configured with your product context What is Brief? — Learn more about what Brief provides via MCP Further Reading - Anthropic's MCP Announcement — The official introduction to MCP - MCP Specification — Technical documentation for developers - Brief MCP Setup Guide — Step-by-step connection instructions --- # What is Product Context? URL: https://briefhq.ai/docs/what-is-product-context/ Category: Getting Started Last Updated: 2026-01-07 Product context is the business knowledge that AI coding agents need to build the right thing—not just syntactically correct code. Without it, your AI is building blind. Why Product Context Matters AI coding assistants like Cursor, Claude Code, and Windsurf are brilliant at how to build things. But they're building blind: - Who you're building for (your customers, their pain points) - What you've already decided (and why you decided it) - Where you're headed (your strategy, goals, roadmap) - What constraints exist (technical debt, team capacity, dependencies) Without this context, your team is not aligned. Brief navigates your agents to the answers they need. What is the product context gap? AI coding assistants know programming languages, frameworks, and code syntax, but they don't know your ICP and customer segments, past architectural decisions, why features were rejected, team velocity and capacity, or what's already built elsewhere in your codebase. What AI Knows | What AI Needs to Know Programming languages | Your ICP and customer segments Frameworks and libraries | Past architectural decisions Code syntax and patterns | Why features were rejected Documentation (if you paste it) | Team velocity and capacity Current file contents | What's already built elsewhere This gap is why AI coding assistants often suggest features that already exist, miss critical business requirements, or build things that don't serve your strategy. What are the types of product context? Customer Context Who are you building for? What are their pain points? What do they care about? Examples: - User personas and their needs - Customer feedback themes - Support ticket patterns - User research insights Decision Context What have you decided, and why? What did you reject? Examples: - "We chose Postgres over MongoDB because of relational data needs" - "We rejected real-time collaboration—not core to our ICP" - "We're using Clerk for auth to avoid building it ourselves" Strategic Context Where is the product headed? What are your goals? Examples: - 6-month vision and OKRs - Competitive positioning - Key metrics and targets - Roadmap priorities Technical Context What constraints and patterns exist in your codebase? Examples: - Tech stack and frameworks - Architectural patterns - Technical debt areas - Performance requirements Velocity Context How fast can your team actually ship? Examples: - Release frequency - Cycle time metrics - Team capacity - Current work in progress How does Brief provide product context? Brief builds your Product Graph automatically from tools you already use. It extracts work pipeline and velocity from Linear or Jira, your actual built features and tech stack from GitHub, strategy and decisions from Notion or Google Docs, discussions and decisions from Slack, customer research from Fireflies, Fathom, or Granola, and user behavior from PostHog. Tool | Context Extracted Linear/Jira | Work pipeline, velocity, priorities GitHub | What's actually built, tech stack Notion/Docs | Strategy, decisions, specs Slack | Discussions, decisions, context Fireflies/Fathom/Granola | Customer research, feedback PostHog | User behavior, feature adoption Brief then navigates AI coding assistants to this context via MCP (Model Context Protocol). Every builder stays aligned. How is product context different from code context? Code context is what the code does (function signatures, file contents, syntax, dependencies), while product context is why the code exists (business requirements, customer needs, strategic alignment, decision rationale). Code Context | Product Context What the code does | Why the code exists Function signatures | Business requirements File contents | Customer needs Syntax errors | Strategic alignment Dependencies | Decision rationale Both are essential. Code context helps AI write correct code. Product context helps AI write the right code. Real-World Example Without Product Context: > You: "Add a feature for team collaboration" > > AI: "I'll add real-time collaborative editing, presence indicators, and a commenting system..." With Product Context (via Brief): > You: "Add a feature for team collaboration" > > AI (navigated by Brief): "I see we decided against real-time collaboration in Decision #42 because it's not core to our solo-founder ICP. Our personas are primarily individual users. Did you want to revisit that decision, or focus on async collaboration instead?" Getting Started Want to give your AI coding assistant product context? What is Brief? — Learn how Brief captures and provides product context Quick Start Guide — Set up Brief in 5 minutes Connect Your Tools — Start building your product context automatically --- # Brief on Mobile URL: https://briefhq.ai/docs/mobile/ Category: Getting Started Last Updated: 2026-07-05 Brief on mobile puts your Navigator in your pocket — chat with Brief and talk through decisions from wherever you are. Availability Open Brief in your phone's browser and it switches to a mobile-friendly layout automatically — no install required, on iOS or Android. Sign in with the same account you use on the web. For a dedicated app with voice, join the iOS beta through TestFlight, Apple's beta testing program. Chat, wherever you are Mobile chat carries the same conversation as web: multi-turn context, contextual preset prompts, and the same tool calls Brief runs on your product graph and connected tools. Start a thread on your phone and pick it back up on desktop — conversation history is shared across surfaces. Voice In the TestFlight app, you can talk to Brief instead of typing. Ask a question out loud and Brief responds in a live conversation, with the same tool calls and reasoning happening underneath as in a typed chat — you just experience it as speech. Links open straight into chat When you tap a document or decision link — from Slack, email, or your weekly digest — it opens directly into a mobile-friendly chat view instead of a full editor. You can read the content and ask Brief about it right there. Your weekly digest works the same way: opening it from your inbox drops you into a chat about that digest, and that conversation stays in your history so you can find it again later. What's different from desktop A few things are still desktop-only while mobile is in beta: - Full document editing — mobile shows document content inside chat; editing happens on desktop. - Landscape layout — the TestFlight app is portrait-only for now. What's Next - Chat Overview — See what Brief Chat can do across every surface. - Quick Start Guide — Get Brief set up if you haven't already. - Using Brief Agents — Learn how Weekly Brief and other agents deliver into your chat history. --- # Fireflies Integration URL: https://briefhq.ai/docs/fireflies-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Fireflies provides high-quality customer research signals from call transcripts. It's one of the most valuable integrations for understanding what customers actually want. What data does Brief extract? - Meeting Transcripts — Full conversation content - Research Signals — Customer pain points and feature requests - Sentiment — How customers feel about topics - Business Impact — Mentions of ARR, deal size, urgency Why should I connect Fireflies to Brief? Customer Research Extract themes from sales calls, support calls, and user interviews without manual tagging. High-Quality Insights Call transcript data is treated as high-confidence evidence—Brief trusts what customers say directly. Persona Enrichment Customer quotes and pain points automatically flow into your personas. How do I set up this integration? Part 1: Get Your API Key Go to Fireflies Developer Settings Click "Generate API Key" (or copy your existing one) Copy the API key and save it somewhere temporarily Part 2: Configure the Webhook On the same Fireflies page, scroll to the "Webhook" section Check the box for "Transcription Completed" event Copy your Brief webhook URL from the Brief integrations page (format shown below) Paste the webhook URL into Fireflies' "Webhook url" field Click "Save" in Fireflies After saving, Fireflies will show you a webhook secret—copy it Webhook URL format: Part 3: Complete Setup in Brief Return to Brief's integrations page Paste your API key in the first field Paste your webhook secret in the second field Click "Save" Done! What happens after I connect? After connecting: Webhook verification — Brief confirms connection with Fireflies Backfill — Brief fetches recent transcripts via API Real-time sync — New transcripts arrive via webhook immediately after meetings Research extraction — AI agents analyze transcripts for themes Common Issues "Transcripts not syncing" Cause: Webhook not enabled or "Transcription Completed" event not checked Fix: Go back to Fireflies → Settings → Developer Ensure webhook URL is saved Ensure "Transcription Completed" checkbox is checked "Invalid signature" error Cause: Webhook secret mismatch Fix: Go to Fireflies → Settings → Developer Re-copy the webhook secret (the one shown after saving) Paste it exactly into Brief (no extra spaces) Click "Save" in Brief "No themes extracted" Cause: Transcripts don't have actual content Fix: Ensure meetings are being transcribed (not just recorded). Check Fireflies settings to enable transcription for all meetings. Tips for Best Results Meeting Naming Name your Fireflies meetings clearly: - ✅ "Customer Interview - Acme Corp" - ✅ "Support Call - Bug Report" - ❌ "Zoom Meeting" Transcript Quality - Speak clearly in meetings - Identify speakers if possible - Fireflies works better with structured conversations Signal Extraction Brief looks for: - Pain points ("frustrated with...", "wish we could...") - Feature requests ("would love to see...", "need support for...") - Business impact ("we'd buy if...", "worth $X to us...") What's Next? Now that Fireflies is connected: - Connect Granola — Another meeting tool option - Connect Fathom — Alternative meeting tool - Connect PostHog — Add analytics for full picture - View Integrations — See all available integrations --- # GitHub Integration URL: https://briefhq.ai/docs/github-integration/ Category: Connecting Your Tools Last Updated: 2026-02-21 Brief + GitHub gives your AI coding agents ground truth about your codebase. Instead of AI tools inventing features that already exist or duplicating work, they can query Brief to understand what's actually built—not what's planned or documented. Without GitHub | With GitHub Connected AI invents existing features | AI checks what's already built No tech stack awareness | AI knows your frameworks PRs disconnected from decisions | Code linked to product context GitHub is essential for Brief because it provides the "source of truth" about your product—what exists in code versus what exists only in documentation. What data does Brief extract from GitHub? - Pull Requests — Open, merged, and closed PRs - Commits — Commit messages and activity - Contributors — Team structure and who's building what - Code Patterns — Tech stack, frameworks, dependencies Why should I connect GitHub to Brief? Brief + GitHub gives your AI coding agents ground truth about your codebase, tech stack detection, and work cross-referencing. Current State (Ground Truth) Brief analyzes your codebase to know what features are actually built vs. what's just planned in Linear or documented in Notion. Tech Stack Detection Automatically identifies your frameworks, languages, and technical sophistication. Work Cross-Reference When you mention your Linear issue key in a PR title (for example ACME-123), Brief links that PR to the issue automatically. How do I set up the GitHub integration? Steps Go to Integrations in Brief Find GitHub and click Connect Authorize Brief in GitHub's OAuth flow Select Organization — Choose which GitHub org to connect Select Repositories — Pick which repos Brief should analyze, or click "Don't share" to skip. Choosing "Don't share" completes the connection but Brief won't have any repos to analyze—you can add repositories later and Brief will start syncing once you do. See What happens after I connect GitHub? for more. Click Complete Setup Done! Brief starts analyzing your code What happens after I connect GitHub? After connecting: Repository analysis — Brief scans your codebase structure PR/commit sync — Brief fetches recent activity Tech stack detection — Brief identifies frameworks and languages Webhook registration — Brief subscribes to push/PR events How do I connect multiple repos? Want to connect more than one repo? Go back to Integrations Click Manage next to GitHub Click Add Repository Select additional repos Common Issues Why can't I see my organization? You don't have admin access to the GitHub organization. Ask your GitHub org admin to grant you admin permissions, or have them connect GitHub to Brief. Why aren't any PRs syncing? Your selected repo may have no PR activity. Check that the correct repository was selected with recent PR activity. Why isn't cross-referencing working? Linear issue keys aren't in your PR titles. Include them in titles like: feat(ACME-123): Add authentication. Format: type(TICKET-ID): description What's Next? Now that GitHub is connected: - Connect Linear — Enable work cross-referencing - Connect Notion — Add strategy docs - View Integrations — See all available integrations --- # HubSpot Integration URL: https://briefhq.ai/docs/hubspot-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Brief + HubSpot gives your team visibility into your sales pipeline and customer relationships. Instead of context-switching between your CRM and product decisions, Brief understands who your customers are, what deals are in play, and how your pipeline looks. Without HubSpot | With HubSpot Connected Customer data lives in CRM only | AI sees your contacts and companies Pipeline invisible to product | AI knows your deals and stages Sales context missing from decisions | Decisions informed by CRM data What data does Brief access from HubSpot? - Contacts — Names, emails, phone numbers, and company associations - Companies — Company records with industry, size, and metadata - Deals — Deal pipeline, stages, amounts, and close dates - Owners — Who's responsible for contacts and deals Why should I connect HubSpot to Brief? Customer Context for Product Decisions When deciding what to build, Brief can reference who your customers actually are — their industries, sizes, and what they're paying for. Pipeline Visibility Brief can see your deals and pipeline stages, helping you understand which product features or improvements could impact revenue. Cross-Reference with Other Data Combined with integrations like Stripe (billing), Linear (engineering), and Slack (conversations), HubSpot CRM data gives Brief a complete picture of your business. How do I set up the HubSpot integration? Go to Integrations in Brief Find HubSpot and click Connect You'll be redirected to HubSpot to authorize Brief Review the permissions and click Connect app Done! Brief can now access your CRM data What can I ask Brief with HubSpot connected? Once connected, try asking Brief: - "Who are our biggest customers?" - "Show me our open deals" - "What companies are in our pipeline?" - "Search for contacts at [company name]" - "What does our deal pipeline look like?" Common Issues Why does the connection fail? Your HubSpot account may need to be allowlisted for Brief. Contact us at support@briefhq.ai and we'll add your account right away. Why can't Brief see my contacts? Make sure the HubSpot user who authorized Brief has access to the CRM objects you're asking about. HubSpot respects per-user permissions — if your user can't see certain contacts in HubSpot, Brief won't see them either. Why did it connect to the wrong HubSpot account? You authorized with the wrong HubSpot account. Disconnect in Brief, then reconnect while logged into the correct HubSpot account. What's Next? Now that HubSpot is connected: - Connect Stripe — Add revenue data alongside CRM - Connect Linear — Link customers to what you're building - View Integrations — See all available integrations --- # Integrations Overview URL: https://briefhq.ai/docs/integrations-overview/ Category: Connecting Your Tools Last Updated: 2026-07-05 Brief builds your Product Graph from tools you already use. No manual data entry required—Brief navigates your team and agents to the context that matters, keeping every builder aligned automatically. How Integrations Work When you connect a tool to Brief: Initial Sync — Brief fetches recent data (30 seconds to 5 minutes) Product Graph Build — Brief extracts decisions, customers, and strategy from your data Continuous Updates — Brief stays in sync automatically via webhooks or polling You Review — Approve or edit what Brief extracted. Every builder stays aligned. Connection Types Type | How It Works | Examples One-Click OAuth | Click "Connect" → Authorize → Done | Linear, GitHub, GitLab, Notion, Slack, Microsoft Teams, Webex, Jira, Asana, Confluence, Google Drive, SharePoint, Fathom, Granola, Plaud, Zoom, Gong, HubSpot, Attio, Supabase, Miro API Key Setup | Create API key → Paste into Brief → Save | Fireflies, PostHog, Mixpanel, LangFuse, Arize, Stripe, Lightfield Guided Setup | Enter connection details in a setup dialog | PostgreSQL OAuth is simpler (one click), but some tools only offer API keys. PostgreSQL uses a short setup dialog where you enter your database connection details. Team vs. Personal Connections Integrations connect in one of two ways: - Team connections — One org-wide connection covers everyone. Usually an admin connects once, and the whole workspace benefits. Examples: GitLab, Fireflies, Gong, PostHog, Mixpanel, LangFuse, Arize, Stripe, HubSpot, Attio, Lightfield, Supabase, PostgreSQL, Miro. - Personal connections — Each user authorizes their own account, so Brief only sees what that user can see. Examples: Linear, GitHub, Notion, Slack, Microsoft Teams, Webex, Fathom, Granola, Plaud, Zoom, Jira, Asana, Confluence, Google Drive, SharePoint. If a team integration is already connected, you won't be asked to connect it again. For personal integrations, each teammate connects their own account from the Integrations page. What Goes Into Your Product Graph Different integrations provide different types of context: Work Management Linear, Jira, Asana, Miro - What you're building (current work pipeline) - How fast you ship (velocity metrics) - What's shipped vs. planned - Planning and strategy signals from Miro boards Development GitHub, GitLab - Your tech stack - What's actually in your codebase - Team structure and who's building what GitLab support covers both GitLab.com and self-hosted GitLab instances. Documentation Notion, Confluence, Google Drive, SharePoint - Strategy documents and goals - Decision records - Product documentation Meetings & Customer Research Fireflies, Fathom, Granola, Plaud, Zoom, Gong, Webex Meetings - What customers are saying - Pain points and feature requests - Research themes from calls and sales conversations Communication Slack, Microsoft Teams, Webex Messaging - Chat with Brief where your team already works—Slack DMs and Microsoft Teams are full chat surfaces - Log decisions from conversations - Capture context where it happens CRM HubSpot, Attio, Lightfield - Contacts, companies, and deal pipeline - Sales context for product decisions - Customer relationships and ownership Billing & Revenue Stripe - Subscription and revenue data - Customer billing history - MRR and payment status Analytics PostHog, Mixpanel - Feature adoption - User behavior patterns - Which features are actually used LLM Observability LangFuse, Arize - Traces, requests, and sessions from your AI product - Prompt performance and token usage - Latency metrics and cost tracking Databases Supabase, PostgreSQL - Query your product database directly from chat - Run read-only SQL against a read replica or analytics database - Table-level access control — admins choose which tables are exposed Integration Categories Core Setup (Recommended First) Start with these for the best foundation: Linear or Jira — Work tracking GitHub or GitLab — Codebase analysis Notion, Confluence, or SharePoint — Documentation Add Research Tools Get higher quality insights: Fireflies, Fathom, Granola, Plaud, Zoom, or Gong — Customer research from meetings PostHog or Mixpanel — Analytics data Revenue & CRM Add business context: Stripe — Revenue and subscription data HubSpot, Attio, or Lightfield — CRM contacts, companies, and deals LLM Observability If you're building AI products: LangFuse or Arize — Track LLM performance, costs, and usage Databases Ask questions of your own data: Supabase or PostgreSQL — Read-only SQL from chat Communication Tools Bring Brief to where your team talks: Slack, Microsoft Teams, or Webex — Chat with Brief and log decisions from conversations How Long Does Setup Take? Integration | Setup Time | Initial Sync Linear | 1 minute | 30-60 seconds GitHub | 1 minute | 1-2 minutes GitLab | 1-2 minutes | 1-2 minutes Notion | 1 minute | 2-5 minutes Confluence | 1 minute | 2-5 minutes Google Drive | 1 minute | 2-5 minutes SharePoint | 1 minute | 2-5 minutes Jira | 1 minute | 1-2 minutes Asana | 1 minute | 1-2 minutes Miro | 1 minute | 1-2 minutes Fathom | 1 minute | 1-2 minutes Granola | 1 minute | 1-2 minutes Plaud | 1 minute | 1-2 minutes Zoom | 1 minute | Periodic sync Gong | 1-2 minutes | 1-2 minutes Fireflies | 3-5 minutes | 1-2 minutes PostHog | 2-3 minutes | 1-2 minutes Mixpanel | 2-3 minutes | 1-2 minutes LangFuse | 2-3 minutes | Instant Arize | 2-3 minutes | Instant Stripe | 2-3 minutes | Instant HubSpot | 1 minute | Instant Attio | 1 minute | Instant Lightfield | 1-2 minutes | Instant Supabase | 2-3 minutes | Instant PostgreSQL | 2-3 minutes | Instant Slack | 1-2 minutes | Instant Microsoft Teams | 1-2 minutes | Instant Webex | 1-2 minutes | Instant Next Steps Ready to connect your tools? Start with: - Linear Integration — Recommended first integration - GitHub Integration — Connect your codebase - All Integrations — See all available integrations Once connected, put your context to work: - Brief Agents — Scheduled agents that turn your connected tools into recurring insight - Account & Billing — Seats, invites, and plan management Need help? Check our Troubleshooting Guide. All Integrations Work Management - Linear — Issue tracking and sprints - Jira — Enterprise issue tracking - Asana — Task and project management - Miro — Boards for planning and strategy Development - GitHub — Code repos and issues - GitLab — GitLab.com and self-hosted repos Documentation - Notion — Docs and knowledge base - Confluence — Team documentation - Google Drive — Docs, Sheets, and Slides - SharePoint — Microsoft 365 documents Communication - Slack — Chat with Brief and capture decisions - Microsoft Teams — Chat with Brief in Teams - Webex — Messaging spaces and meetings Meetings & Customer Research - Fireflies — Meeting transcription - Fathom — AI meeting assistant - Granola — AI meeting notes - Plaud — AI voice recorder - Zoom — Meeting recordings and transcripts - Gong — Revenue intelligence from calls CRM - HubSpot — Contacts, companies, and deals - Attio — Modern startup CRM - Lightfield — AI-native CRM Billing & Revenue - Stripe — Subscriptions and payments Analytics - PostHog — Product analytics - Mixpanel — Product analytics and events LLM Observability - LangFuse — LLM traces and prompts - Arize — LLM observability with Arize AX or Phoenix Databases - Supabase — Postgres database queries - PostgreSQL — Read-only SQL from chat --- # Linear Integration URL: https://briefhq.ai/docs/linear-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Brief + Linear gives your AI coding agents real-time understanding of your work pipeline. Instead of AI tools guessing what to build next, they can query Brief to see what's in progress, what's blocked, and how fast your team ships. Without Linear | With Linear Connected AI guesses priorities | AI sees your actual backlog No velocity context | AI knows your shipping speed PRs merge with no ticket trail | PRs auto-link to Linear issues by ticket key Linear is one of the best first integrations for Brief—it takes about a minute to connect and immediately gives Brief understanding of what you're building, how fast you ship, and your work pipeline. What data does Brief extract from Linear? - Issues and Projects — What's backlogged, in progress, and shipped - Velocity Metrics — Release frequency, cycle time, throughput trends - Team Structure — Who's working on what - Labels and Priorities — How you organize work Why should I connect Linear to Brief? Brief + Linear gives your AI coding agents visibility into your work pipeline, velocity, and strategic decisions. Work Pipeline See what's being built right now vs. what's planned vs. what shipped. Velocity Understanding Brief calculates how fast your team ships based on issue completion patterns. Work Cross-Reference When your GitHub PR title includes a Linear issue key (for example ACME-123), Brief automatically links that PR to the issue—so shipped code and planned work stay connected without any manual tagging. How do I set up the Linear integration? Go to Integrations in Brief Find Linear and click Connect Authorize Brief in Linear's OAuth flow Select teams to share — Choose which Linear teams Brief should track, or click "Don't share" to skip Done! Brief starts syncing immediately What happens after I connect Linear? After connecting: Immediate sync — Brief fetches your recent issues Webhook registration — Brief subscribes to Linear updates Background analysis — Velocity agent calculates metrics You review — Approve extracted features and velocity data Common Issues Why aren't any issues syncing? Your Linear workspace may be empty, or the teams you shared don't have any issues yet. Create some issues or check that recent work exists. Why isn't the webhook working? Webhook failed to register during initial connection. Go to Linear → Settings → Webhooks and check if Brief webhook exists. If missing, disconnect and reconnect in Brief. Why did it connect to the wrong workspace? You authorized with the wrong Linear account. Disconnect in Brief, then reconnect with the correct Linear account. What's Next? Now that Linear is connected: - Connect GitHub — Cross-reference issues with PRs - Connect Notion — Add strategy docs - View Integrations — See all available integrations --- # Notion Integration URL: https://briefhq.ai/docs/notion-integration/ Category: Connecting Your Tools Last Updated: 2026-02-21 Notion provides Brief with strategic context, decision records, and product documentation. It's one of the best sources for understanding your product strategy and goals. What data does Brief extract? - Pages and Databases — All shared content - Product Documentation — Strategy docs, roadmaps, specs - Decision Records — ADRs and decision pages - Persona Documents — ICP docs and user research notes Why should I connect Notion to Brief? Strategic Context Extract goals, OKRs, competitive analysis, and product strategy directly from your Notion workspace. Decision Extraction Brief identifies and extracts decision records (ADRs) and important product decisions. Persona Discovery ICP documents and user research notes automatically enrich your personas. How do I set up this integration? Steps Go to Integrations in Brief Find Notion and click Connect Authorize Brief in Notion's OAuth flow Select pages to share — Notion asks you which pages/databases Brief can access Choose what to index — Brief shows a setup page where you pick which shared pages to actively index, or click "Don't share" to skip Done! Brief starts syncing Sharing Pages with Brief Notion requires you to explicitly share pages with integrations. Brief only sees what you share. How to Share Pages Open a Notion page you want Brief to access Click Share in the top right Click Invite and search for "Brief" Select the Brief integration Choose access level (usually "Can view") Click Invite Share Parent Pages When you share a parent page, all nested child pages are included automatically. Share your main workspace or project pages for comprehensive coverage. What happens after I connect? After connecting: Initial sync — Brief fetches all shared pages (2-5 minutes) Content analysis — Strategy agent extracts goals, decisions, personas Webhook registration — Brief subscribes to page updates Continuous sync — Updates automatically as you edit pages Common Issues Why does it say "No pages found"? Cause: No pages shared with Brief integration Fix: In Notion, go to a page you want to share Click Share → Invite → Search for "Brief" Add the Brief integration to that page Why is content missing? Cause: Page not shared with Brief Fix: Check page permissions. Brief only sees explicitly shared pages. Re-share pages or share parent pages to include children. Why is syncing slow? Cause: Large workspace with many pages Fix: Initial sync for large workspaces (100+ pages) can take 5+ minutes. This is normal. Subsequent updates are instant via webhooks. What's Next? Now that Notion is connected: - Connect Linear — Cross-reference work with strategy docs - Connect GitHub — Link decisions to code - View Integrations — See all available integrations --- # PostHog Integration URL: https://briefhq.ai/docs/posthog-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 PostHog provides Brief with the highest-quality data source: actual user behavior. Analytics data is treated as the most confident signal about your product and users. What data does Brief extract? - Event Data — User actions and behaviors - Feature Adoption — Which features are actually used - User Cohorts — Behavioral segments - Funnel Analysis — Conversion patterns Why should I connect PostHog to Brief? Persona Sizing Use actual usage data to size your persona segments. Analytics is the highest-confidence source Brief has for understanding your users. Feature Adoption Know which features are actually used vs. just built. Brief can tell you "Authentication is used by 95% of users" based on real data. High-Confidence Insights Analytics data is the gold standard. It's what users actually do, not what they say or what you plan. How do I set up this integration? Steps Part 1: Create API Key in PostHog Go to PostHog API Keys Click "Create API Key" Select the "MCP Server" scope preset Copy the API key Part 2: Connect in Brief Go to Integrations in Brief Find PostHog and click Connect Paste your API key in the first field Select your PostHog project from the dropdown Click Save Done! What happens after I connect? After connecting: Initial sync — Brief fetches recent event data (1-2 minutes) Persona sizing — Analytics data enriches persona understanding Feature adoption — Brief calculates which features are used Polling updates — Brief checks for new data periodically Common Issues Why does it say "Invalid API key"? Cause: API key doesn't have the right permissions Fix: Go back to PostHog → Settings → API Keys Ensure you selected the "MCP Server" scope when creating the key Create a new key if needed and update in Brief Why are no projects shown in the dropdown? Cause: API key doesn't have the right scope Fix: Recreate the API key in PostHog using the "MCP Server" scope preset Why aren't any events syncing? Cause: PostHog project has no events in the selected time range Fix: - Ensure PostHog is actually tracking events - Check that events exist in PostHog dashboard - Verify you selected the correct project What PostHog Data Powers Personas - Segment sizing: "SMB users: 60% of traffic" - Behavioral patterns: What features each persona uses - Confidence boost: Analytics data raises confidence in your persona definitions Features - Adoption rates: "OAuth: 95% of users" - Usage patterns: When and how features are used - Drop-off points: Where users abandon flows Product Understanding - Most used features - User journey patterns - Retention metrics What's Next? Now that PostHog is connected: - Connect Fireflies — Add customer research - Connect Granola — AI-powered meeting notes - Connect Linear — Cross-reference usage with work - View Integrations — See all available integrations --- # Slack Integration URL: https://briefhq.ai/docs/slack-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Slack is a full Brief chat surface. DM the Brief bot to ask anything you'd ask in the web app — backed by your connected tools, documents, and decisions — and capture decisions right in the channels where they happen. No context-switching required. What can I do with Brief in Slack? - Chat with Brief in DMs — The same AI agent that powers web chat, with streaming answers and full access to your product context - Capture decisions — Via the /decide command, the /propose command, or @Brief mentions in channels - Ask Brief in channels — Mention @Brief in any channel it's been invited to and it replies in-thread, using the thread as context - Share files — Drop images, PDFs, Word docs, and spreadsheets into a DM and Brief reads them - See your workspace at a glance — The bot's App Home tab shows recent decisions and documents Why should I connect Slack to Brief? Brief where your team already is Ask questions, check decisions, and search your product context without opening another tool. Answers stream into the DM as Brief works. Decision capture in context Log decisions right where the conversation happens. Brief captures who, when, and where automatically. Team adoption It's easier to get your team to type /decide in Slack than to remember to log decisions elsewhere. Teammates without Brief accounts can still ask @Brief questions in channels (read-only). How do I set up the Slack integration? From Brief Go to Integrations in Brief Find Slack and click Connect Select your Slack workspace and authorize the Brief bot Choose channels Brief learns from — Select the channels Brief can read for context (public channels are pre-selected). You can skip this step and adjust later. Choose channels to invite Brief to — Opt Brief into the channels where you want @Brief and /decide available. Brief categorizes channels by purpose in the background, so the most relevant ones — product and strategy discussions — surface first. Done — DM the Brief bot to start chatting From the Slack App Directory You can also install Brief directly from Slack's App Directory — no existing Brief account needed: Click Install on Brief's Slack App Directory listing Authorize the app in your Slack workspace If you don't have a Brief account yet, you'll be taken through a short sign-up that creates your Brief workspace and links it to Slack Brief sends you a welcome DM to get you started Chatting with Brief in DMs Open a DM with the Brief bot and ask anything — "what did we decide about auth?", "summarize this PRD", "what shipped this week?". Brief answers with the same agent and tools as web chat. What you'll see: - Streaming answers — Brief posts a thinking indicator immediately, then updates the message as the answer forms, including live status for any tools it's using - Collapsible reasoning — When Brief reasons through a problem, the finished answer shows a one-line summary ("Thought for 3s") with a See reasoning button to expand the full trace - Suggested actions — Follow-up buttons under answers when there's an obvious next step - Feedback and regenerate — Thumbs up/down and a regenerate button on every response, plus a View in Brief link to continue in the web app How conversations work: you have one continuous conversation with Brief per Slack workspace — context carries across messages until you reset it. If you send new messages while Brief is still answering, it queues them and addresses each in turn. DM slash commands Command | What it does /brief-new | Start a fresh conversation (clears context) /brief-clear | Same as /brief-new /brief-status | Show your session — message count and last activity /brief-model | View or change the AI model Brief uses in this workspace Brief uses the latest Claude models; /brief-model on its own shows the current model, and /brief-model switches it for your workspace. Sharing files in DMs Attach files to a DM and Brief reads them as part of your message: - Images and screenshots — Analyzed visually - PDFs — Text extracted, with OCR fallback for scanned documents - Word documents (.docx), spreadsheets (.xlsx, .xls), presentations (.pptx), text, CSV, and Markdown files — Content extracted Files up to 20MB are supported. If one file in a batch fails, Brief tells you and continues with the rest. Capturing decisions The /decide command Log a confirmed decision from any channel the bot is in: Slack shows a preview of your decision text with the channel and author attached. Click Confirm to log it to Brief, or Edit to adjust the wording first. The /propose command For questions that still need a decision, /propose creates a pending proposal your team can weigh in on: Using @Brief mentions Mention @Brief in a channel for conversational capture — or any other question: Brief reads the surrounding thread for context, proposes a structured decision, and shows a preview to confirm or edit. Mentions also work for plain questions — Brief answers in-thread. Teammates who aren't in Brief yet get read-only answers; logging decisions and other write actions require a Brief account. Decisions from DM chat When a DM conversation surfaces a decision, Brief proposes it with Confirm / Edit / Cancel buttons below its answer — no command needed. What Brief captures - Topic — What the decision is about (inferred or edited) - Decision — The choice made - Rationale — Why (from your message) - Author — Who logged it - Timestamp — When it was made - Channel — Where the conversation happened Tips for best results ✅ Clear and specific: ✅ Includes rationale: ❌ Too vague: Slack permissions Brief's Slack bot requests permissions to: - Read messages in channels it's a member of, and your DM history with the bot — for thread context and conversation continuity - Send and update messages — for streaming answers, previews, and confirmations - Provide slash commands — /decide, /propose, and the /brief-* commands - Read and upload files — to process attachments you share and send files back - Read your email address — to match your Slack account to your Brief account - Unfurl Brief links — to show previews when Brief URLs are shared - Add emoji reactions — for lightweight acknowledgments Brief does not read: - Private channels, unless you explicitly invite the bot - Group DMs - Your DMs with other people Common issues Why isn't the bot responding in a channel? The Brief bot isn't in the channel. Type /invite @Brief in the channel, then try again. Why does Brief ask me to connect my account? Your Slack account isn't matched to a Brief user. Brief matches accounts by email — click the Connect to Brief button in the bot's message, and make sure your Slack profile email matches the email you use for Brief. Why can't I see the /decide command? The slash commands didn't install properly. Go to Brief → Integrations, disconnect Slack, then reconnect and re-authorize. Why did it connect to the wrong workspace? Disconnect in Brief, then reconnect and select the correct Slack workspace during authorization. Brief says the conversation is getting long Long-running DM sessions eventually hit the context limit. Type /brief-new to start a fresh conversation — your decisions and documents in Brief are unaffected. What's Next? Now that Slack is connected: - Chat tips — Get better answers from Brief chat - Microsoft Teams integration — The same chat experience for Teams workspaces - Brief agents — Scheduled agents can deliver results straight to Slack - View integrations — See all available integrations --- # Stripe Integration URL: https://briefhq.ai/docs/stripe-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Brief + Stripe gives your team visibility into your revenue. Instead of switching between Stripe dashboards and product decisions, Brief understands your billing data and can factor revenue context into strategic recommendations. Without Stripe | With Stripe Connected Revenue is a separate dashboard | AI sees your MRR and subscriptions No billing context in decisions | Decisions informed by revenue data Manual revenue reporting | Ask Brief about customer revenue anytime What data does Brief access from Stripe? - Subscriptions — Active, canceled, and trialing subscriptions with plan details - Customers — Customer records with metadata and email - Invoices — Payment history, amounts, and status - Products & Prices — Your product catalog and pricing tiers Why should I connect Stripe to Brief? Revenue Context for Decisions When you're deciding what to build next, Brief can factor in which features drive revenue, which customers are churning, and where expansion revenue is coming from. Customer Intelligence Brief can cross-reference Stripe customers with data from other integrations (CRM, support) to build a fuller picture of your customer base. GTM Alignment Revenue data helps Brief understand your business model and make product recommendations that align with your growth goals. How do I set up the Stripe integration? Go to Integrations in Brief Find Stripe and click Connect You'll need a Stripe Restricted API Key with read-only access Creating a Restricted Key in Stripe Go to Stripe Dashboard → API Keys Click Create restricted key Give it a name like "Brief Read-Only" Grant Read access to: Customers, Subscriptions, Prices, Products, Invoices Click Create key and copy the key (starts with rk_live_... or rk_test_...) Paste the key into Brief Setting Up Webhooks (Optional) Webhooks give Brief real-time updates when subscriptions change: In Stripe Dashboard, go to Developers → Webhooks Click Add an endpoint Paste the webhook URL shown in Brief's setup flow Select these events: customer.subscription.created, customer.subscription.updated, customer.subscription.deleted, invoice.paid, invoice.payment_failed Save the endpoint, then reveal the signing secret Paste the signing secret into Brief before saving What can I ask Brief with Stripe connected? Once connected, try asking Brief: - "What's our current MRR?" - "Show me our active subscriptions" - "Which customers have upcoming invoices?" - "What does our subscription growth look like?" Common Issues Why does it say "invalid API key"? Make sure you're using a Restricted Key (starts with rk_), not a Secret Key. Also verify you're using the correct mode (test vs. live) for your environment. Why can't Brief see my subscriptions? Your restricted key may not have the right permissions. Go back to Stripe → API Keys and verify the key has Read access to Subscriptions, Customers, and Invoices. What's Next? Now that Stripe is connected: - Connect HubSpot — Add CRM context alongside revenue - Connect Linear — Link revenue to what you're building - View Integrations — See all available integrations --- # Supabase Integration URL: https://briefhq.ai/docs/supabase-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Supabase gives Brief direct access to your product data. Instead of manually pulling reports, ask your agent questions like "how many users signed up this week?" or "what's our most active feature?" and get answers backed by real data. What can Brief do with Supabase? - Query your data — Ask natural language questions, get SQL-backed answers - Explore schema — List tables, describe columns, understand your data model - Run analytics — Aggregations, counts, trends, and ad-hoc analysis - Table-level access control — Admins choose exactly which tables the agent can see Which database should I connect? We strongly recommend connecting a read replica or analytics database rather than your production instance. This is the same best practice used with BI tools like Metabase, Looker, or Mode. Benefits of using a read replica: - Zero risk to production — Even in a worst-case scenario, production data is unaffected - No performance impact — Queries don't compete with your application's traffic - Standard practice — Same setup you'd use for any analytics or BI tool If you don't have a read replica, Supabase makes it easy to create one from your project dashboard under Settings → Database → Read Replicas. How do I set up this integration? Steps Part 1: Connect your Supabase account Go to Settings → Integrations in Brief Find Supabase and click Connect You'll be redirected to Supabase to authorize Brief Review the permissions and click Authorize Part 2: Select your project After authorization, you'll see a list of your Supabase projects Select the project you want Brief to query (we recommend a read replica) Click Next: Choose Tables Part 3: Choose which tables to expose You'll see all tables in the selected project Uncheck any tables you don't want the agent to access Click Connect Done! Your agent can now query the selected tables. What permissions does Brief request? Brief uses Supabase's OAuth to authenticate. The authorization includes: Permission | What it does | Why Brief needs it Database Read | Read table schemas and column types | Lets the agent understand your data model Database Write | Execute SQL queries via the Management API | Required by Supabase for any SQL execution, even read-only queries Security model Brief applies three layers of protection: Statement validation — Queries are parsed and only SELECT, WITH (CTE), and EXPLAIN statements are allowed. INSERT, UPDATE, DELETE, and DROP are rejected before they reach your database. Read-only transactions — All queries execute inside a read-only Postgres transaction. Even if a write statement somehow passed validation, the database itself would reject it. Table allowlist — The agent can only query tables your admin explicitly approved during setup. Queries referencing other tables are blocked. How does it work in chat? Once connected, your agent can answer data questions directly: > You: How many users signed up this month? > > Agent: runs SELECT count(*) FROM public.users WHERE created_at >= '2026-03-01' > > You had 847 new signups this month, up 12% from February. The agent discovers your database through Brief's skill system — it won't see database tools until the conversation is relevant, keeping context focused. Managing connections Adding more projects Go to Settings → Integrations, find Supabase, and click Add Project to connect additional databases. Changing table access To modify which tables are accessible: Go to Settings → Integrations Find the Supabase project you want to modify Click the settings icon Update the table selection Save Disconnecting To remove a Supabase project: Go to Settings → Integrations Find the project and click Disconnect Common Issues "SQL execution requires additional permissions" Cause: Your Supabase connection was authorized without the database query scope. Fix: Disconnect and reconnect Supabase. The updated authorization flow will request the necessary permissions. Agent says "I can see tables but can't query data" Cause: Same as above — the agent can read schema (which needs fewer permissions) but can't execute queries. Fix: Reconnect Supabase from Settings → Integrations. "Access denied: table not in the allowed list" Cause: The table you're asking about wasn't selected during setup. Fix: Update the table allowlist in Settings → Integrations → your Supabase project. Queries are slow Cause: Complex queries on large tables, or querying a production database under load. Fix: - Use a read replica instead of production - Ask more specific questions (the agent will use LIMIT and targeted WHERE clauses) - Results are automatically truncated to prevent context overflow What's Next? Now that Supabase is connected: - Connect PostHog — Complement database data with event analytics - Connect Linear — Cross-reference user data with your roadmap - View Integrations — See all available integrations --- # Attio Integration URL: https://briefhq.ai/docs/attio-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Brief + Attio gives your team visibility into your modern CRM data. Attio is built for startups who want a flexible, relationship-first CRM. Connect it to Brief so your product decisions are informed by real customer context. Without Attio | With Attio Connected Customer relationships siloed in CRM | AI sees your people and companies Deal pipeline invisible to product | AI knows your opportunities and stages Sales context missing from decisions | Decisions informed by real customer data What data does Brief access from Attio? - People — Contact records with names, emails, and relationship history - Companies — Company records with industry, stage, and custom attributes - Deals — Your sales pipeline, stages, and deal values - Lists — Custom lists and segments you've created in Attio Why should I connect Attio to Brief? Relationship Context for Product Decisions When deciding what to build, Brief can reference your actual customer relationships — who they are, what stage they're at, and how you've engaged with them. Pipeline Visibility Brief can see your deals and pipeline stages, helping you understand which product features or improvements could impact revenue. Flexible Data Model Attio's custom objects and attributes are all accessible to Brief, so your unique CRM setup translates into rich product context. How do I set up the Attio integration? Go to Integrations in Brief Find Attio and click Connect You'll be redirected to Attio to authorize Brief Review the permissions and click Allow Done! Brief can now access your CRM data What can I ask Brief with Attio connected? Once connected, try asking Brief: - "Who are our key contacts?" - "Show me our open deals" - "What companies are we talking to?" - "Search for people at [company name]" - "What does our deal pipeline look like?" Common Issues Why does the connection fail? Make sure you're logged into the correct Attio workspace when authorizing. If you have multiple workspaces, you'll need to select the right one during the OAuth flow. Why can't Brief see certain records? Attio respects workspace permissions. If your Attio user can't access certain records, Brief won't see them either. Check your Attio permissions if data seems missing. Why did it connect to the wrong workspace? Disconnect in Brief, then reconnect while logged into the correct Attio workspace. What's Next? Now that Attio is connected: - Connect Stripe — Add revenue data alongside CRM - Connect Linear — Link customers to what you're building - View Integrations — See all available integrations --- # Confluence Integration URL: https://briefhq.ai/docs/confluence-integration/ Category: Connecting Your Tools Last Updated: 2026-02-21 Confluence provides Brief with strategic context and product documentation. For teams using Atlassian, it's the best source for understanding product strategy and decisions. What data does Brief extract from Confluence? - Pages and Spaces — All accessible content - Product Documentation — Strategy docs, roadmaps, requirements - Decision Records — ADRs and decision pages - Strategy Documents — Goals, OKRs, and competitive analysis Why should I connect Confluence to Brief? Strategic Context Extract goals, roadmaps, and product strategy from your Confluence workspace. Decision Extraction Brief automatically identifies ADRs (Architecture Decision Records) and important product decisions. Documentation Search Your Confluence content becomes searchable via Brief chat. How do I set up the Confluence integration? Steps Go to Integrations in Brief Find Confluence and click Connect Authorize Brief in Atlassian's OAuth flow Select Confluence site — Choose which site to connect (if you have multiple) Choose what to share — Select which spaces Brief should index, or click "Don't share" to skip Done! Brief starts syncing What if my workspace requires admin approval? Some Atlassian workspaces require admin approval for third-party apps. If Admin Approval Required You'll see a message during OAuth: "Admin approval required" Ask your Atlassian workspace admin to approve Brief Admin approves in: Atlassian Admin Console → App Management → Pending Requests Once approved, reconnect in Brief What Happens Next After connecting: Initial sync — Brief fetches recent pages (2-5 minutes) Content analysis — Strategy agent extracts goals and decisions Webhook registration — Brief subscribes to page updates Continuous sync — Updates automatically as pages are edited Does Confluence work better with Jira? Yes, Confluence and Jira are often used together. When you connect both: - Brief cross-references work items with strategy docs - Better understanding of "why" behind the work - Decisions linked to epics and tickets Common Issues Why does it say "Admin approval required"? Your Atlassian workspace requires admin approval for new apps. Ask your Atlassian admin to approve Brief in the admin console under App Management → Pending Requests. Why does it say "Token expired"? Atlassian OAuth tokens expire hourly but auto-refresh automatically. If issues persist after 5 minutes, disconnect and reconnect. Why did it connect to the wrong Confluence site? You connected to the wrong Atlassian site during OAuth. Disconnect in Brief, then reconnect and select the correct Confluence site. Why aren't any pages syncing? Your Confluence site may have no content or Brief may lack permissions. Check that Brief has read access to spaces in Confluence settings. How long does setup take? Initial setup takes about 1 minute for the OAuth flow and scoping step. The initial sync takes 2-5 minutes to fetch your pages and content. Updates happen in real-time via webhooks. How does Brief identify decisions? Brief automatically identifies ADRs (Architecture Decision Records) and important product decisions by analyzing page structure, titles, and content patterns. These become searchable via Brief chat. What's Next? Now that Confluence is connected: - Connect Jira — Cross-reference work with documentation - Connect GitHub — Link strategy to code - View Integrations — See all available integrations --- # Fathom Integration URL: https://briefhq.ai/docs/fathom-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Fathom provides high-quality customer research signals from meeting recordings, with AI-generated summaries that give Brief rich material to work from. What data does Brief extract? - Meeting Transcripts — Full conversation content - AI Summaries — Fathom's structured summaries - Action Items — Tasks identified during meetings - Research Signals — Customer pain points and feature requests Why should I connect Fathom to Brief? Customer Research Extract themes from sales calls, support calls, and user interviews automatically. High-Quality Summaries Fathom's AI summaries are already structured, making extraction more accurate. Simpler Setup Unlike Fireflies, Fathom uses simple OAuth—no webhook configuration needed. How do I set up this integration? Steps Go to Integrations in Brief Find Fathom and click Connect Authorize Brief in Fathom's OAuth flow Review privacy settings — Brief shows what data it will access and confirms raw transcripts stay private Personal plan: Click Connect to confirm, or "Don't analyze my calls" to skip Team plan: Select which teams' recordings Brief can access, then click Connect Done! Brief starts syncing No API keys or webhooks — just OAuth and a quick privacy confirmation. What happens after I connect? After connecting: Privacy confirmation — Brief shows what data will be shared and privacy guarantees Initial sync — Brief fetches recent recordings (1-2 minutes) Research extraction — AI agents analyze transcripts for themes Webhook registration — Brief subscribes to new recordings Continuous sync — New recordings arrive automatically Privacy Guarantees Fathom is a call recording integration, so Brief applies extra privacy protections: - Your transcripts stay private — Raw transcripts are only accessible to you - Aggregated insights for your team — Brief extracts themes, trends, and key quotes — never the full content - You control access — Disconnect or adjust permissions at any time Common Issues "No calls synced" Cause: Fathom hasn't recorded any meetings yet Fix: Ensure Fathom is recording meetings (not just scheduled). Check Fathom settings to enable recording for all meetings. "Missing transcripts" Cause: Fathom subscription doesn't include transcription Fix: Check your Fathom subscription plan. Some plans only record video without transcription. "No research signals extracted" Cause: Transcripts are too short or lack customer conversation Fix: Brief works best with customer-facing calls (sales, support, interviews). Internal team meetings may not generate research signals. Tips for Best Results Meeting Types That Work Best - ✅ Customer interviews - ✅ Sales discovery calls - ✅ Support calls - ✅ User research sessions - ❌ Internal team standups - ❌ Planning meetings Fathom Features Brief Uses - Transcripts — Full conversation content - Highlights — Important moments you marked - AI Summary — Fathom's structured summary - Participant Info — Who was in the meeting Fathom vs. Fireflies vs. Granola Feature | Fathom | Fireflies | Granola Setup | One-click OAuth | API key + webhook | One-click OAuth Setup time | 1 minute | 3-5 minutes | 1 minute Summaries | Excellent AI summaries | Good transcripts | AI-powered notes Team support | Team selector | N/A | Shared folder confirmation Research extraction | High quality | High quality | High quality All three provide high-quality research signals. Choose based on which tool you already use. What's Next? Now that Fathom is connected: - Connect Granola — Another meeting tool option - Connect Fireflies — Use multiple tools together - Connect PostHog — Add analytics for full picture - View Integrations — See all available integrations --- # GitLab Integration URL: https://briefhq.ai/docs/gitlab-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Brief reads merge requests and issues from your GitLab projects so agents and teammates can check what's actually shipped instead of guessing from Linear or docs. This page covers both GitLab.com and self-hosted GitLab servers — pick the section that matches your setup. What does Brief capture from GitLab? - Projects — the repos Brief has visibility into - Merge Requests — open, merged, and closed MRs - Issues — optional; a single toggle turns issue mining on or off across the projects you select - User info — who's authoring the work Brief has read-only access — it never opens, comments on, or merges anything in GitLab. Why connect GitLab to Brief? Ground truth for agents Agents checking "does this already exist" get a real answer from merge request activity instead of inventing duplicate work. One connection for the whole org GitLab is a team-level integration — an admin connects it once and every project you select is visible to the whole org. Teammates don't each need to authorize their own account. Works with your own GitLab server If your team runs GitLab on its own infrastructure rather than gitlab.com, Brief connects to that instance directly, including self-signed certificates. How do I set up the GitLab integration? GitLab.com Go to Integrations in Brief Find GitLab and click Connect Authorize Brief in GitLab's OAuth flow Select projects — pick which projects Brief should analyze, then toggle whether to include issue mining across the projects you selected Click Complete Setup Done! Brief starts syncing merge requests (and issues, if selected) Self-Hosted GitLab Go to Integrations in Brief Find GitLab (Self-Hosted) and click Connect Enter your instance URL — for example https://gitlab.example.com Choose how to authenticate. OAuth (recommended) — in your GitLab instance, add an application (Settings → Applications) with the read_api scope using the callback URL Brief shows you, then paste the Application ID and Secret into Brief and continue through the authorize flow. Access token — create a token with the read_api scope (Settings → Access Tokens) and paste it into Brief directly, no app registration needed. Select projects — pick which projects Brief should analyze, then toggle whether to include issue mining across the projects you selected Done! Brief starts syncing on a periodic schedule Common Issues "Can't see my projects after connecting" Cause: No projects were selected during setup, or the connected account lacks access. Fix: Go to Integrations → Manage next to GitLab and re-open project selection. Confirm the connecting account has at least read access to the projects you want. "Merge requests aren't updating in real time (self-hosted)" Cause: Self-hosted GitLab syncs periodically rather than via webhooks. Fix: This is expected — give it a sync cycle. If data is still stale after that, disconnect and reconnect to refresh the connection. "OAuth app fields are missing (self-hosted)" Cause: You're on the token path but tried to fill in Application ID/Secret, or vice versa. Fix: Use "Use an access token instead" or "Use OAuth instead" inside the connect dialog to switch modes — the fields shown depend on which path you're on. "Certificate error connecting to my instance" Cause: Your GitLab server uses a self-signed or internal CA certificate that Brief doesn't trust by default. Fix: Ask your Brief admin to get the certificate trusted at the org level, then retry the connection. What's Next? Now that GitLab is connected: - Connect Linear — cross-reference merge requests with issues - Connect GitHub — use both if your org spans providers - View Integrations — see all available integrations --- # Jira Integration URL: https://briefhq.ai/docs/jira-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Jira gives Brief understanding of your work pipeline and velocity. For teams using Atlassian, it's the primary source for understanding what you're building and how fast you ship. What data does Brief extract from Jira? - Issues and Epics — What's backlogged, in progress, and shipped - Sprints — Sprint planning and completion data - Velocity Metrics — Release frequency, cycle time, throughput - Project Structure — How you organize work Why should I connect Jira to Brief? Work Pipeline See what's being built right now vs. what's planned vs. what shipped. Velocity Understanding Brief calculates how fast your team ships based on sprint completion patterns. Jira + Confluence Combo When you connect both Jira and Confluence, Brief cross-references work items with strategy docs for complete context. How do I set up the Jira integration? Steps Go to Integrations in Brief Find Jira and click Connect Authorize Brief in Atlassian's OAuth flow Select Jira site — Choose which site to connect (if you have multiple) Choose projects to share — Select which Jira projects Brief should track, or click "Don't share" to skip Done! Brief starts syncing What if my workspace requires admin approval? Some Atlassian workspaces require admin approval for third-party apps. If Admin Approval Required You'll see a message during OAuth: "Admin approval required" Ask your Atlassian workspace admin to approve Brief Admin approves in: Atlassian Admin Console → App Management → Pending Requests Once approved, reconnect in Brief What Happens Next After connecting: Initial sync — Brief fetches recent issues and sprints (1-2 minutes) Velocity analysis — Velocity agent calculates metrics Webhook registration — Brief subscribes to issue updates Continuous sync — Updates automatically as issues change Common Issues Why does it say "Admin approval required"? Your Atlassian workspace requires admin approval for new apps. Ask your Atlassian admin to approve Brief in the admin console under App Management → Pending Requests. Why does it say "Token expired"? Atlassian OAuth tokens expire hourly but auto-refresh automatically. If issues persist after 5 minutes, disconnect and reconnect. Why did it connect to the wrong Jira site? You connected to the wrong Atlassian site during OAuth. Disconnect in Brief, then reconnect and select the correct Jira site. Why aren't any issues syncing? Your Jira site may be empty or Brief may lack permissions. Check that Brief has read access to projects in Jira settings. How long does setup take? Initial setup takes about 1 minute for the OAuth flow and scoping step. The initial sync takes 1-2 minutes to fetch your issues and sprints. Updates happen in real-time via webhooks. How does Brief calculate velocity? Brief analyzes your sprint completion patterns, issue lifecycle times, and throughput to calculate velocity metrics and understand your team's shipping capacity. Can I connect multiple Jira sites? Yes, select which site during OAuth. To connect a different site, disconnect the current one and reconnect with the new site. What's Next? Now that Jira is connected: - Connect Confluence — Cross-reference work with strategy docs - Connect GitHub — Link issues to PRs - View Integrations — See all available integrations --- # LangFuse Integration URL: https://briefhq.ai/docs/langfuse-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Brief + LangFuse gives your team visibility into how your AI product is performing. If you're building with LLMs, LangFuse tracks your traces, prompts, and costs. Connect it to Brief so your product decisions are informed by real usage data. Without LangFuse | With LangFuse Connected LLM performance data siloed | AI sees your traces and metrics Prompt effectiveness unknown | AI knows which prompts work Cost and latency invisible | Decisions informed by real data What data does Brief access from LangFuse? - Traces — End-to-end request traces through your LLM application - Observations — Individual LLM calls, spans, and events within traces - Metrics — Latency, token usage, costs, and custom scores - Prompts — Your prompt templates and their performance Why should I connect LangFuse to Brief? Understand Your AI Product's Performance When making product decisions about your AI features, Brief can reference actual performance data — which prompts work best, where latency spikes, and what's costing the most. Debug Issues Faster Brief can search your traces to help you understand failures, edge cases, and unexpected behavior in your LLM application. Optimize Prompts and Costs With visibility into token usage and costs, Brief can help you make informed decisions about prompt optimization and model selection. How do I set up the LangFuse integration? Go to Integrations in Brief Find LangFuse and click Connect Get your API keys from your LangFuse project settings (Settings → API Keys) Enter your Secret Key (starts with sk-lf-...) Enter your Public Key (starts with pk-lf-...) Optionally enter your Host if your project is on the US region Click Save What can I ask Brief with LangFuse connected? Once connected, try asking Brief: - "Show me recent traces with errors" - "What's our average latency for the chat endpoint?" - "Which prompts have the highest token usage?" - "Find traces where users complained about slow responses" - "What's our LLM cost trend this week?" Common Issues Why does the connection fail? Double-check that you've entered both the Secret Key and Public Key correctly. They're different keys — the Secret Key starts with sk-lf- and the Public Key starts with pk-lf-. Why can't Brief see my traces? Make sure the API keys you provided have access to the project you want to query. LangFuse supports multiple projects — ensure you're using keys from the right one. Why does it say my Host isn't recognized? Brief's LangFuse connection supports the two LangFuse Cloud hosts only — the default (cloud.langfuse.com) and the US region (us.cloud.langfuse.com). Self-hosted LangFuse instances aren't supported yet. What's Next? Now that LangFuse is connected: - Connect Arize — Alternative LLM observability - Connect PostHog — Add product analytics - View Integrations — See all available integrations --- # PostgreSQL Integration URL: https://briefhq.ai/docs/postgresql-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 PostgreSQL gives Brief direct, read-only access to a database you host yourself — RDS, Aurora, or a self-hosted instance. Enter connection details once, choose which tables the agent can see, and start asking questions in chat instead of writing SQL by hand. What can Brief do with PostgreSQL? - Query your data — Ask natural language questions, get SQL-backed answers - Explore schema — List tables and describe columns, grouped by schema - Run analytics — Aggregations, counts, trends, and ad-hoc analysis - Table-level access control — Admins choose exactly which tables the agent can query Which database should I connect? We strongly recommend a read replica or analytics database, not your primary production instance — the same practice you'd use with any BI tool. It removes any risk to production and keeps agent queries from competing with application traffic. Brief also needs a publicly reachable host. It connects over the Postgres wire protocol directly, so an address that only resolves inside your private network (a VPC-internal hostname, localhost, or an RFC1918 IP) will be refused. Use your database provider's public endpoint, or a bastion/proxy that exposes one. How do I set up this integration? Connecting PostgreSQL is admin-only — you need to be a workspace admin. Steps Part 1: Enter connection details Go to Settings → Integrations in Brief Find PostgreSQL and click Connect Fill in a connection name, host, port, database, username, and password Set SSL Mode to Verify Full — Brief requires verify-full and won't save a connection without it Click Test Connection & Continue Part 2: Choose which tables to expose Brief introspects the schema and shows every table it found Uncheck any tables you don't want the agent to access Click Connect Database — done, Brief can now query the selected tables If schema introspection returns nothing, Brief connects without restrictions rather than blocking you — you can still ask the agent to describe individual tables by name. Security model Brief applies several layers of protection to every query: Statement validation — only SELECT, WITH (CTE), and EXPLAIN are allowed; everything else is rejected before it reaches your database Read-only transactions — every query runs with default_transaction_read_only set, so even a write statement that slipped through validation would be rejected by Postgres itself Table allowlist — the agent can only see and query tables an admin explicitly selected during setup Function and keyword deny-list — file access, network-egress, and privilege functions (and statements like COPY, GRANT, VACUUM) are blocked, even inside a CTE Private-host blocking — connections to internal, loopback, or link-local addresses are refused Result limits — query results are capped and truncated so a large table can't flood the conversation Credentials are encrypted at rest, and every query opens a short-lived connection that closes immediately after. How does it work in chat? Once connected, your agent can answer data questions directly: > You: How many orders came in last week? > > Agent: runs a read-only SELECT count(*) against your orders table > > You had 312 orders last week, up from 275 the week before. The agent discovers your database through Brief's skill system — it won't see database tools until the conversation is relevant, keeping context focused. Brief also generates a starter skill describing how to use your connected database, which you can refine from Settings. Managing connections Changing table access There's no in-place editor for an existing connection's table selection today. To expose different tables, disconnect and reconnect — you'll get a fresh table selector during setup. Disconnecting Go to Settings → Integrations, find the connection, and click Disconnect. Brief immediately stops querying the database. Common Issues "Connection test failed" Cause: Brief couldn't reach the database with the credentials provided. Fix: Double-check host, port, database name, username, and password. Confirm the database accepts connections from outside your network. "Refused to connect: host is in a private/internal range" Cause: The host resolves to an internal, loopback, or link-local address. Fix: Point Brief at a publicly reachable endpoint — your provider's public host, not a VPC-internal one. "PostgreSQL connection requires ssl_mode=verify-full" Cause: The connection was saved without full SSL verification, or your database's SSL setup changed. Fix: Reconnect from Settings → Integrations and confirm your database supports verify-full SSL. "Access denied: table is not in the allowed list" Cause: The table you're asking about wasn't selected during setup. Fix: Disconnect and reconnect from Settings → Integrations, adding the table to your selection. Queries are slow or get truncated Cause: A complex query on a large table, or a result set past the row/size limit. Fix: Ask more specific questions — the agent narrows queries with WHERE and LIMIT — and prefer a read replica over production for anything heavy. What's Next? Now that PostgreSQL is connected: - Connect Supabase — if part of your data also lives in a managed Supabase project - Connect PostHog — complement database data with product analytics - View Integrations — see all available integrations --- # Microsoft Teams Integration URL: https://briefhq.ai/docs/teams-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Microsoft Teams is two things to Brief: a signal source (channel conversations you choose to share) and a full chat surface — you can talk to Brief, capture decisions, and approve agent actions without leaving Teams. What does Brief capture from Teams? - Channel messages — from the teams/channels you choose to share during setup - Thread context — the surrounding channel conversation, so an in-thread reply to Brief carries the discussion with it - Decisions — captured when you talk through a choice with Brief in a Teams conversation - Speaker attribution — who said what, matched to a Brief account where possible Why should I connect Teams to Brief? Signal from where your team already talks Product and customer context surfaces in Teams channels constantly. Connecting lets Brief fold that into the same product understanding it builds from your other tools — no separate export step. A chat surface without switching tools Once Brief is in your Teams tenant, you can ask it questions, review its answers, and confirm decisions in the same window you're already working in. Context-aware replies Brief reads the surrounding thread before it answers, so a reply in the middle of a channel conversation understands what came before it — not just the single message that mentioned it. How do I set up the Teams integration? Steps Go to Integrations in Brief Find Microsoft Teams and click Connect Authorize Brief in Microsoft's OAuth flow Choose channels to share — select which teams/channels Brief can read for signal, or skip if you only want the chat surface Done! Brief starts syncing selected channels This OAuth connection governs signal ingestion. Getting the Brief bot itself into Teams (so you can chat with it) is a separate, one-time step — see below. Chatting with Brief in Teams Brief's Teams bot mirrors the Slack chat experience: @mention Brief in a channel, message it directly, or add it to a group chat. Answers render as Adaptive Cards, so tables, decision proposals, and follow-up prompts show up as native Teams UI rather than plain text. - Thread context — in a channel, Brief pulls in the surrounding conversation before it replies, so it understands what's already been discussed - Decision capture — talk through a choice with Brief in a thread and it proposes a structured decision card with Confirm / Edit actions, the same pattern as Slack's /decide - Tool-approval cards — when Brief needs to take a gated action (an agent-management change, a bulk operation), it sends an Approve / Deny card rather than acting silently - Personal, group, and channel scope — the bot works in 1:1 messages, group chats, and team channels Getting Brief into your Teams tenant If your organization already uses Brief, an admin can install the Brief app from your Teams admin center (or your own Teams client) and add it to a team, channel, or chat. The first time you add Brief to a scope, Teams shows a one-time permission prompt. If your organization hasn't connected Brief yet, ask a workspace admin to connect it — an admin needs to install the Brief app and link your Teams tenant before Brief can respond in your organization. Common Issues "Your organization isn't set up with Brief yet" Cause: No one at your organization has connected Brief to your Teams tenant. Fix: Ask a workspace admin to connect Brief, then try again. "I couldn't look up your account just now" Cause: A temporary lookup hiccup — this is not the same as having no account. Fix: Try again in a moment. If it keeps happening, contact support. Brief replies with a stripped-down card Cause: The full answer exceeded Teams' card size limit, so Brief sent a compact version with a link to view the rest in Brief. Fix: No action needed — click through to see the complete answer. Channel replies don't seem to know the thread Cause: Brief couldn't read the channel's message history for that reply (a permissions or connectivity hiccup). Fix: Confirm Brief still has access to the channel. If it persists, contact support — Brief still answers, just without the surrounding context. What's Next? Now that Teams is connected: - Explore Brief Chat — See what you can do wherever you talk to Brief - Connect Slack — Use both chat surfaces together - Using Brief Agents — Approve and manage agent actions from chat - View Integrations — See all available integrations --- # Asana Integration URL: https://briefhq.ai/docs/asana-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Asana gives Brief understanding of your work pipeline and velocity. For teams using Asana, it's the primary source for understanding what you're building and how fast you ship. What data does Brief extract from Asana? - Tasks and Projects — What's backlogged, in progress, and completed - Sections and Milestones — How you organize and track work - Velocity Metrics — Completion patterns, cycle time, throughput - Custom Fields — Priority, status, and other metadata Why should I connect Asana to Brief? Work Pipeline See what's being built right now vs. what's planned vs. what shipped. Velocity Understanding Brief calculates how fast your team ships based on task completion patterns. MCP Write Access When using Brief via MCP, your AI can create and update Asana tasks directly from your IDE. How do I set up the Asana integration? Steps Go to Integrations in Brief Find Asana and click Connect Authorize Brief in Asana's OAuth flow Select workspace — Choose which Asana workspace to connect Choose projects to share — Select which projects Brief should track, or click "Don't share" to connect without sharing any projects (you can add them later from Settings) Done! Brief starts syncing the projects you selected What Happens Next After connecting: Initial sync — Brief fetches recent tasks and projects (1-2 minutes) Velocity analysis — Velocity agent calculates metrics Webhook registration — Brief subscribes to task updates Continuous sync — Updates automatically as tasks change Common Issues Why does it say "Workspace access denied"? Brief doesn't have permission to access the Asana workspace. Disconnect and reconnect, ensuring you select the correct workspace during OAuth. Why aren't any tasks syncing? Your Asana workspace may be empty or Brief may lack permissions. Check that Brief has read access to projects in Asana workspace settings. Why aren't tasks updating? This could be webhook delivery issues or Asana API rate limits. Wait 5 minutes for retry. If issues persist, disconnect and reconnect. Why does the connection show 'Disconnected'? Your OAuth token expired or was revoked. Click Reconnect in Brief integrations page to reauthorize. How long does setup take? Initial setup takes about 1 minute for the OAuth flow and scoping step. The initial sync takes 1-2 minutes to fetch your tasks and projects. Updates happen in real-time via webhooks. Can Brief create and update Asana tasks? Yes, when using Brief via MCP (Model Context Protocol), your AI can create and update Asana tasks directly from your IDE with write permissions. What permissions does Brief need? Brief needs read access to extract context. For MCP write features, Brief also needs write access. Permissions are granted during OAuth. What's Next? Now that Asana is connected: - Connect Notion — Link tasks to strategy docs - Connect GitHub — Track code alongside tasks - Set Up MCP — Create Asana tasks from your IDE - View Integrations — See all available integrations --- # Google Drive Integration URL: https://briefhq.ai/docs/google-drive-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Google Drive provides Brief with strategic context, product documentation, and data from your Google Workspace. Brief can read from Docs, Sheets, and Slides to understand your product strategy and metrics. What data does Brief extract? - Google Docs — Strategy docs, PRDs, meeting notes, decision records - Google Sheets — Roadmaps, metrics dashboards, research data - Google Slides — Presentations, pitch decks, quarterly reviews - Google Forms — Form structure and responses (read-only) - Shared Drives — Team-level documentation Why should I connect Google Drive to Brief? Strategic Context Extract goals, OKRs, product strategy, and roadmaps directly from your Google Workspace documents. Metrics & Data Brief reads metrics from Google Sheets to understand your product performance and goals. MCP Write Access When using Brief via MCP, your AI can create and edit Google Docs directly from your IDE. How do I set up this integration? Steps Go to Integrations in Brief Find Google Drive and click Connect Sign in with your Google account Grant permissions — Allow Brief to read and write to Drive Choose folders to share — Browse your folder tree and select which folders Brief should index, or click "Don't share" to skip Done! Brief starts syncing What happens after I connect? After connecting: Initial scan — Brief indexes shared files (2-5 minutes) Content extraction — Extracts strategic context from your Google Docs; Sheets, Slides, and Forms are available to chat and your AI tools on request Ongoing sync — Brief re-reads shared files as your agents and workflows need them, so updates stay current Supported File Types File Type | What Brief Extracts | MCP Write Support Google Docs | Full text content, headings, tables | ✅ Yes Google Sheets | Cell data and sheet structure | ✅ Yes Google Slides | Slide text content | ✅ Yes Google Forms | Form structure, questions, and responses | ❌ No PDFs | Text content (read-only) | ❌ No Other files | Metadata only (title, owner, dates) | ❌ No Permissions & Privacy What Brief Can Access - Files you explicitly share — Only files/folders you grant access to - Shared Drive content — If you're a member and grant permission - Metadata — File names, owners, modification dates What Brief Cannot Access - Private files — Files you don't explicitly share - Other users' private files — Even if in the same org - Deleted files — Trash items are not synced Common Issues "Access denied" during setup Cause: Your Google Workspace admin restricts third-party apps Fix: Ask your workspace admin to approve Brief in Admin Console → Apps → Marketplace apps Why aren't any files syncing? Cause: Brief doesn't have access to any files or folders Fix: Check sharing settings in Google Drive. Make sure Brief has at least "View" access. "Files not updating" Cause: Google API rate limits or a stale cache of the file Fix: Wait a few minutes and try again. If issues persist, disconnect and reconnect. "Can't write to file via MCP" Cause: Brief only has read access or file is restricted Fix: Grant Brief "Edit" access to the file in Google Drive sharing settings What's Next? Now that Google Drive is connected: - Connect Notion — Cross-reference docs across tools - Connect Linear — Link docs to work items - Set Up MCP — Create and edit Google Docs from your IDE - View Integrations — See all available integrations --- # Granola Integration URL: https://briefhq.ai/docs/granola-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Granola provides AI-powered meeting notes with high-quality transcription. Brief extracts research signals from your Granola calls to build customer understanding. What data does Brief extract? - Meeting Notes — Granola's AI-generated meeting summaries - Transcripts — Full conversation content - Research Signals — Customer pain points, feature requests, sentiment - Key Quotes — Notable customer statements for persona enrichment Why should I connect Granola to Brief? Customer Research Extract themes from sales calls, support calls, and user interviews automatically. Privacy-First Design Raw transcripts stay private to you. Your team sees aggregated insights (themes, trends, quotes) — never the full content. Simple OAuth Setup One-click OAuth connection — no API keys or webhooks to configure. How do I set up this integration? Steps Go to Integrations in Brief Find Granola and click Connect Authorize Brief in Granola's OAuth flow Review privacy settings — Brief shows you what data it will access and confirms that raw transcripts stay private Click Connect to confirm, or "Don't analyze my calls" to connect without analyzing call content (you can enable analysis later from Settings) Done! Brief starts syncing your meeting notes What happens after I connect? After connecting: Privacy confirmation — Brief shows what data will be shared and privacy guarantees Initial sync — Brief fetches recent meeting notes (1-2 minutes) Research extraction — AI agents analyze notes for themes and signals (skipped if you chose "Don't analyze my calls") Continuous sync — New notes are synced automatically If you chose "Don't analyze my calls", Brief will sync your meeting metadata (titles, dates, attendees) but won't extract research signals or analyze content. You can enable analysis later from Settings → Integrations → Granola. Privacy Guarantees Granola is a call recording integration, so Brief applies extra privacy protections: - Your transcripts stay private — Raw transcripts are only accessible to you. Your team won't see full conversation text. - Aggregated insights for your team — Brief extracts themes, trends, and key quotes — never the full content. - You control access — Disconnect or adjust permissions at any time from Settings. Common Issues "No notes synced" Cause: Granola hasn't recorded any meetings yet Fix: Ensure Granola is running and recording meetings. Check that you have recent notes in Granola. "No research signals extracted" Cause: Notes are too short or lack customer conversation Fix: Brief works best with customer-facing calls (sales, support, interviews). Internal team meetings may not generate research signals. "Setup session expired" Cause: Too much time passed between OAuth and confirming setup Fix: Go back to Integrations, disconnect Granola, and reconnect. Tips for Best Results Meeting Types That Work Best - Customer interviews - Sales discovery calls - Support calls - User research sessions Meeting Types That Don't Generate Signals - Internal team standups - Planning meetings - Social calls Granola vs. Fathom vs. Fireflies Feature | Granola | Fathom | Fireflies Setup | One-click OAuth | One-click OAuth | API key + webhook Setup time | 1 minute | 1 minute | 3-5 minutes Notes | AI-powered summaries | AI summaries | Transcripts Research extraction | High quality | High quality | High quality All three provide high-quality research signals. Choose based on which tool you already use. You can connect multiple — Brief deduplicates insights. What's Next? Now that Granola is connected: - Connect Fathom — Use alongside Granola - Connect Fireflies — Another meeting tool option - Connect PostHog — Add analytics for full picture - View Integrations — See all available integrations --- # Lightfield Integration URL: https://briefhq.ai/docs/lightfield-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Brief + Lightfield gives your team visibility into your AI-native CRM. Lightfield is built for founders and sales teams who want a modern, AI-first approach to customer relationships. Connect it to Brief so your product decisions are informed by real customer context. Without Lightfield | With Lightfield Connected Customer data siloed in CRM | AI sees your contacts and accounts Pipeline invisible to product | AI knows your opportunities Sales context missing | Decisions informed by CRM data What data does Brief access from Lightfield? - Contacts — People you're in touch with, including names, emails, and context - Accounts — Companies and organizations in your pipeline - Opportunities — Sales opportunities with stages and values Why should I connect Lightfield to Brief? Customer Context for Product Decisions When deciding what to build, Brief can reference your actual customer relationships — who they are, what they need, and where they are in your pipeline. AI-Native Data Model Lightfield's AI-first approach means your CRM data is already structured for intelligent queries. Brief can leverage this to give you better insights. Pipeline Visibility Brief can see your opportunities and their stages, helping you understand which product improvements could close more deals. How do I set up the Lightfield integration? Go to Integrations in Brief Find Lightfield and click Connect Get your API key from Lightfield Settings Enter your API Key Click Save What can I ask Brief with Lightfield connected? Once connected, try asking Brief: - "Who are our key contacts?" - "Show me our open opportunities" - "What accounts are in our pipeline?" - "Search for contacts at [company name]" - "What does our sales pipeline look like?" Common Issues Why does the connection fail? Double-check that you've entered the API key correctly. You can generate a new key in your Lightfield settings if needed. Why can't Brief see certain records? Lightfield respects your workspace permissions. If certain data isn't visible, check your Lightfield access settings. How do I get a Lightfield API key? Go to your Lightfield dashboard, navigate to Settings, and look for the API keys section. Generate a new key and copy it to Brief. What's Next? Now that Lightfield is connected: - Connect HubSpot — Alternative CRM option - Connect Attio — Another modern CRM - View Integrations — See all available integrations --- # Mixpanel Integration URL: https://briefhq.ai/docs/mixpanel-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Mixpanel gives Brief a direct read on how people actually use your product. Connect it once for the whole team and Brief turns raw event data into feature adoption, engagement trends, and behavioral segments — no dashboards to build first. What data does Brief extract? - Event Data — Raw product events, pulled through Mixpanel's Export API - Feature Adoption — Per-event usage: total count, unique users, adoption rate, and average use per user for your most active events - Engagement Metrics — Monthly active users, average daily actives, and the DAU/MAU stickiness ratio - User Segments — Power, Regular, Casual, and Dormant user tiers, derived automatically from activity patterns Why should I connect Mixpanel to Brief? One connection covers your team Mixpanel is a team-level integration. One person sets it up with a Service Account, and everyone on the team gets the same analytics context — no individual logins to manage. Feature adoption grounded in real usage Brief can tell you which features people actually reach for, not just what shipped. Adoption rate and average-use-per-user come straight from event volume, not survey guesses. Segments without extra setup Brief builds Power/Regular/Casual/Dormant segments directly from your event history. You don't need to define cohorts in Mixpanel first — Brief derives them from activity, so they're ready the moment data syncs. How do I set up this integration? Steps Part 1: Create a Service Account in Mixpanel In Mixpanel, go to Project Settings → Service Accounts Create a service account with read access Copy the Service Account Username and Secret, and note your numeric Project ID Part 2: Connect in Brief Go to Integrations in Brief Find Mixpanel and click Connect Enter your Project ID and Service Account Username Paste the Service Account Secret Choose your Data Residency Region — US (mixpanel.com) or EU (eu.mixpanel.com) Click Save What happens after I connect? After connecting: Initial sync — Brief streams recent event history through Mixpanel's Export API Feature adoption — Events are aggregated into adoption rate and usage-per-user for your top events Engagement metrics — MAU, average DAU, and stickiness are computed from the same window Segments — Power/Regular/Casual/Dormant tiers appear automatically, sized from real activity Polling updates — Brief periodically pulls new events; there's no webhook to configure Common Issues "Invalid credentials" Cause: The Service Account username or secret doesn't match, or the account lacks read access Fix: Recheck the username and secret in Mixpanel → Project Settings → Service Accounts. Create a new service account if needed and update the credentials in Brief. "No data syncing" Cause: The Data Residency Region doesn't match where the project actually lives Fix: Confirm whether your project is on mixpanel.com (US) or eu.mixpanel.com (EU), then update the region in Brief's integration settings. "No segments show up" Cause: No identified users generated events in the last 30 days — anonymous, unidentified activity doesn't count toward segments Fix: Segments need identified users (people, not anonymous devices) with recent event activity. Give it time after go-live, or check that your app identifies users in Mixpanel. What Mixpanel Data Powers Feature Understanding - Adoption rates — Which events real users actually trigger, and how often - Usage depth — Average actions per user for each feature Engagement - MAU / DAU — Monthly and average daily active users - Stickiness — DAU/MAU ratio as a quick read on habitual use Personas - Behavioral segments — Power, Regular, Casual, and Dormant tiers sized from real activity, feeding persona confidence What's Next? Now that Mixpanel is connected: - Connect PostHog — Another product-analytics option if you use both - Connect LangFuse — Add LLM-specific analytics alongside product data - View Integrations — See all available integrations --- # Webex Integration URL: https://briefhq.ai/docs/webex-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Webex covers two things Brief cares about: meeting recordings and transcripts from Webex Meetings, and team conversations from Webex Messaging spaces. Both connect through the same Webex OAuth app, but you set each up separately since they read different data. What does Brief capture from Webex? Webex Meetings - Recordings — Your cloud-recorded meetings - Transcripts — Text from Webex Assistant transcription, where enabled Webex Messaging - Group space messages — Content from spaces you categorize as customer or product - Space metadata — Titles and activity, so Brief can group what it reads Brief only reads group spaces in Webex Messaging — it never reads 1:1 direct messages. Why should I connect Webex to Brief? Meeting context without extra recording tools If your team already runs meetings in Webex, Brief can pull recordings and transcripts directly instead of asking you to add a separate meeting bot. Team and customer signal from spaces you choose Webex spaces often carry the same customer feedback and product discussion that Slack or Teams channels do. Categorizing spaces lets Brief extract that signal without reading anything you haven't opted in. One connection, two capabilities Because Meetings and Messaging share one OAuth app, connecting once gives your team the option to use either — or both — without a second app approval from your Webex admin. How do I set up Webex Meetings? Meeting transcript steps Go to Integrations in Brief Find Webex Meetings and click Connect Authorize Brief in Webex's OAuth flow Brief checks that your account can access cloud recordings Done! Brief starts syncing your recent recordings How do I set up Webex Messaging? Messaging steps Go to Integrations in Brief Find Webex Messaging and click Connect Authorize Brief in Webex's OAuth flow Categorize your spaces — for each group space, choose Customer (customer-facing: feedback, support), Product (internal product: engineering, design), Strategy (planning and leadership), or Skip (excluded from Brief entirely) Click Save & finish Every space starts as Skip. Brief only reads spaces you categorize: Customer and Product spaces feed research signals, Strategy spaces feed strategy context, and skipped spaces are excluded entirely. If you skip everything, Webex Messaging connects but nothing is ingested until you categorize at least one space. Common Issues "Webex Meetings won't connect" Cause: Your Webex account isn't licensed for cloud recording. Fix: This is a hard block, not a Brief error — Brief checks recording access before completing the connection. Ask your Webex admin to enable cloud recording, then reconnect. "Recordings show up but transcripts don't" Cause: Webex Assistant transcription is off by default and isn't retroactive. Fix: Turn on Webex Assistant transcription in your Webex meeting settings going forward. Past recordings without transcription enabled won't retroactively get transcripts. "No messages synced from Webex Messaging" Cause: All spaces are still set to Skip, or you only categorized spaces with little activity. Fix: Go to Brief → Integrations → Webex Messaging → reconfigure, and mark at least one active space as Customer or Product. "I don't see a space I expected" Cause: Brief's space list only shows group spaces — 1:1 direct messages are never listed, by design. Fix: If the space is missing and it's a group space, confirm you're still a member of it in Webex, then reopen the categorization screen. What's Next? Now that Webex is connected: - Connect Zoom — Another meeting recording option - Connect Microsoft Teams — A full chat surface alongside Webex Messaging - Connect Slack — Capture decisions from conversations in another channel - View Integrations — See all available integrations --- # Arize Integration URL: https://briefhq.ai/docs/arize-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Brief + Arize gives your team visibility into how your AI product is actually performing. If you're building with LLMs, Arize (or self-hosted Phoenix) traces every call your product makes. Connect it to Brief so decisions about your AI features are grounded in real usage — not guesswork. What data does Brief access from Arize? - Traces and spans — the calls your AI product makes through its LLM pipeline - Sessions — user and session identity carried on those spans, when present - Evaluations — pass/fail and scored annotations (correctness, hallucination, and similar checks) - Metrics — latency, error rate, and eval-derived quality signals From those spans, Brief derives engagement metrics for your product's Product Graph: sessions, unique users, messages per session, return rate, and satisfaction rate (from your evals) — these count only spans that carry user or session identity, or an eval annotation. Error rate and average latency are computed across all spans in the window. If none of your spans carry any identity or eval signal at all — a purely model-monitoring setup — Brief treats the project as not yet reporting engagement data rather than showing misleading numbers. Why should I connect Arize to Brief? Ground product decisions in real usage When your team debates whether an AI feature is working, Brief can reference actual session counts, return rate, and satisfaction — not anecdotes. Catch quality regressions early Brief sees your eval pass/fail trends, so a spike in hallucination or a drop in correctness shows up in context, not buried in a dashboard nobody checks. Works with Arize AX or self-hosted Phoenix Whether you run Arize's hosted platform or your own Phoenix instance (including inside a VPC), Brief connects the same way. How do I set up the Arize integration? Go to Integrations in Brief Find Arize and click Connect In Arize AX, create a Developer API key (or, for self-hosted Phoenix, a System API key) — Arize's API key docs walk through this. Read access is sufficient. Enter your API Key Optionally enter a Project name — Brief defaults to your first project if you leave this blank If you're self-hosted or running Phoenix behind a VPC, enter your base URL; leave this blank to use Arize Cloud Click Save Because Arize is a team-level connection, one admin sets it up once and the whole org benefits — no per-person authorization needed. What can I ask Brief with Arize connected? Once connected, try asking Brief: - "How's our return rate trending this month?" - "Show me sessions where evals came back negative" - "What's our average latency for the assistant pipeline?" - "Did our error rate change after last week's prompt update?" - "Which sessions have the most turns per user?" Common Issues "Connection fails" Cause: The key type doesn't match the host — a Developer (AX) key won't authenticate against a self-hosted Phoenix instance, and vice versa. Fix: Confirm you're using a Developer API key for Arize AX or a System API key for self-hosted Phoenix, and that the base URL field matches where that key lives. "No traces found" or metrics look empty Cause: The project name doesn't match an existing project, or your spans don't carry user.id/session.id attributes or eval annotations yet. Fix: Leave the project field blank to default to your first project, or double-check the name in Arize. Engagement metrics need at least one identity or eval signal per span — pure infrastructure spans won't populate them. "Self-hosted Phoenix not reachable" Cause: Your Phoenix instance's base URL isn't publicly reachable, or points somewhere Brief's servers can't resolve. Fix: Use a base URL that's reachable from the public internet (or your VPC's exposed endpoint), and confirm it's the root instance URL, not a specific project or trace link. "Satisfaction rate seems off" Cause: Eval label polarity varies by check — for a Hallucination eval, the "good" label might read as factual, not pass. Fix: Brief recognizes common Arize/Phoenix eval labels automatically (pass/fail, correct/incorrect, factual/hallucinated, and similar). An annotation with no label at all falls back to its raw score, but an annotation with a label Brief doesn't recognize is excluded from the satisfaction rate rather than guessed — rename it to a recognized label if you want it counted. What's Next? Now that Arize is connected: - Connect LangFuse — Another LLM observability option, useful if you run both - Connect PostHog — Add product analytics for the full picture - Connect Mixpanel — Another analytics option for user behavior - View Integrations — See all available integrations --- # Brief CLI Setup Guide URL: https://briefhq.ai/docs/cli-setup/ Category: Connecting Your Tools Last Updated: 2026-07-05 The Brief CLI (@briefhq/cli) gives you terminal access to everything in Brief—your Product Graph, decisions, documents, personas, signals, and more. Every builder stays aligned, even from the command line. Why Use the Brief CLI? Use Case | How the CLI Helps Quick lookups | brief decisions search "auth" is faster than opening a browser AI coding agents | Any agent with shell access can navigate to Brief—no MCP config needed Scripting & automation | Pipe JSON output into your own tools with --json and --jq Decision validation | brief ask --mode check "..." before you build. No team ships blind. CLI vs. MCP The CLI and Brief MCP access the same API and provide the same capabilities. Choose whichever fits your workflow: - MCP — Direct protocol integration for editors with MCP support (Cursor, Claude Code, Windsurf, VS Code). Navigates your AI automatically. - CLI — Works from any terminal and with any AI agent that has shell access. No protocol configuration needed. You can use both at the same time. Either way, every builder stays aligned. Quick Start Prerequisite: Node.js 22.13 or later. Check with node --version. If you don't have it, grab it from nodejs.org or your package manager. The fastest path from zero to a working Brief CLI: Then, from your project's root directory, run: On first run, brief init: Opens a browser to sign you in (OAuth PKCE). Credentials are stored securely in ~/.config/brief/ and tokens refresh automatically. Auto-detects your coding agent in the current directory (Cursor, Claude Code, GitHub Copilot / VS Code, Windsurf, Cline, Codex, Junie) and installs the Brief CLI skill + instruction file so the agent knows how to call Brief from the shell. Packs and uploads your codebase context so Brief can answer questions grounded in your actual code. Restart your coding agent once brief init finishes. You can then call brief ask, brief decisions, and the other commands below from the terminal — or your agent can call them for you via shell tool-use. > CLI vs MCP: this setup wires your coding agent to reach Brief through the shell CLI. If you prefer your agent to reach Brief through MCP tool calls instead (or in addition), follow the Brief MCP setup guide — MCP installation is host-native and separate from the CLI path. Zero-install alternative Prefer not to install globally? Run any command through npx: This always pulls the latest version, which is ideal for ephemeral runners and one-off invocations. pnpm supports a global install; for Yarn, use yarn dlx for one-off CLI runs (this works in Yarn Classic and Yarn Berry—Yarn 2+ removed yarn global add): CI / Headless Environments Skip the interactive login and pass a token via environment variable. This is the canonical path for CI pipelines, remote agents, and any non-TTY caller: Store BRIEF_TOKEN in your CI platform’s secret manager (masked or protected variables) and inject it at runtime—never commit it to the repository or check it into plaintext scripts. Commands such as brief ask consume it from the environment. Generate a token from Settings → Integrations → API Keys in the Brief web app, or run brief token on a machine where you're already logged in. BRIEF_TOKEN takes precedence over stored credentials and works for every brief command. The CLI resolves authentication in this order: BRIEF_TOKEN environment variable --token flag BRIEF_API_KEY environment variable Stored credentials from brief login (auto-refreshed if expired) For headless environments where you can't open a browser interactively at all, brief login --no-browser doesn't attempt browser-based OAuth — it prints instructions for generating a long-lived API key from the Brief web app and setting it as BRIEF_API_KEY on the host instead. Account Management Core Commands brief ask Ask Brief anything about your product. This is the primary command — Brief's AI agent has access to your decisions, personas, research signals, documents, and connected integrations (Linear, GitHub, Notion, Slack, etc.). Modes: - advise (default) — Open-ended strategic guidance grounded in your org's context - check — Validates your approach against existing decisions, returning conflict analysis - decide — Skips the discussion and returns a definitive recommendation --fast routes to a lightweight, sub-2-second pipeline instead of the full agentic loop — use it for quick inline lookups where a coding agent can't afford to wait. --model overrides the model Brief uses to answer. During long-running queries, brief ask shows real-time progress — you'll see which tools Brief's agent is using (e.g., brief_search, document tools) and when each completes. brief decisions Search, create, and manage product decisions. If the work seems experimental or temporary, pass --isolation with a relevant identifier (branch name, spike name, whatever fits) on writes — and on reads from that scope — so decisions stay contained to the exploration. Promote them to org-wide with brief decisions promote when the experiment graduates. brief docs Search, read, and create documents. brief context View your comprehensive product context — company info, goals, velocity metrics, and team data. brief signals View research signals and customer insights extracted from your connected tools. brief personas View user personas Brief has identified from your data. brief features View your product feature registry. brief pipeline View your work pipeline — what's being built, what's planned, and what's shipped. brief market View GTM data — competitors, deals, and positioning. brief status Show whether you're authenticated and which workspace you're scoped to — a fast sanity check before debugging anything else. brief conversations List and revisit past brief ask conversations. brief skill / brief skills brief skill (singular) prints the canonical Brief product skill markdown for installing into a local agent. brief skills (plural) manages your workspace's own skill registry — list, read, create, update, archive, or import skills your team has authored. brief build Submit a build task to Brief Agent directly from the terminal. Brief plans a spec, asks clarifying questions if it needs them, and — once you approve the spec — works the build. brief init — Coding Agent Setup brief init is the workhorse of the Quick Start above. It auto-detects coding agents in the current directory and writes the Brief CLI skill + instruction files, so your agent knows how to call Brief from the shell. Supported agents For each detected agent, brief init writes a skill file (teaching the agent how to use the Brief CLI) and an instruction file (reminding the agent to use Brief at the right moments): Agent | --agent value | Skill file | Instruction file Claude Code | claude | .claude/skills/brief/SKILL.md | CLAUDE.md Cursor | cursor | .cursor/skills/brief/SKILL.md | .cursor/rules/brief-context.mdc GitHub Copilot / VS Code | copilot (or vscode) | .agents/skills/brief/SKILL.md | .github/copilot-instructions.md Windsurf | windsurf | .windsurf/skills/brief/SKILL.md | .windsurfrules Cline | cline | .agents/skills/brief/SKILL.md | .clinerules Codex | codex | .agents/skills/brief/SKILL.md | AGENTS.md Junie | junie | .junie/skills/brief/SKILL.md | .junie/AGENTS.md All of the above | all | All of the above | All of the above After brief init finishes, restart your coding agent so it picks up the new skill and instruction files. Your agent can then call Brief from the terminal via shell tool-use — no further configuration required. > brief init only installs the CLI behavior layer — skill and instruction files for your agent. It doesn't write any MCP configuration. If you also want your agent to reach Brief through MCP tool calls, install that separately per host by following the Brief MCP setup guide — MCP install is host-native and independent of the CLI path. JSON Output and Scripting Any command supports --json for structured output: Filter with --jq: Multi-turn conversations in scripts: Global Options Option | Description --json | Output as JSON --jq | Filter JSON output with a jq expression -q, --quiet | Suppress non-essential output --no-color | Disable colored output --no-browser | Don't open browser for auth flows --token | Use a specific access token --org | Override organization ID --no-update-check | Skip update check Troubleshooting "command not found: brief" The CLI isn't in your PATH. Either: - Install globally: npm install -g @briefhq/cli - Use npx: npx @briefhq/cli@latest Authentication errors Re-authenticate: Wrong workspace Switch workspaces: Browser won't open If brief login can't reach a browser, don't retry it — the interactive OAuth flow needs one. Run brief login --no-browser to get instructions for generating an API key from the Brief web app, then set it as BRIEF_API_KEY on the host: Stale data The CLI always fetches live data from the Brief API. If results seem stale, check your integration sync status at Brief → Integrations. What's Next? Now that the Brief CLI is installed and your agent is wired up: Try brief ask "I'm new, show me around" to explore your product context Search before building — brief decisions search "..." to avoid redoing solved problems Record decisions as you go — brief decisions create to build institutional memory Validate approaches — brief ask --mode check "..." before an architectural change For more on using Brief effectively, see: - Brief MCP Setup Guide — alternative integration via MCP protocol - Tips for Better Answers - Example Prompts --- # Miro Integration URL: https://briefhq.ai/docs/miro-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Miro boards are often where roadmaps, planning sessions, and ideation actually happen — ahead of anything that makes it into a ticket or doc. Connect Miro and Brief reads your planning boards to keep its understanding of what your team is building toward current. What does Brief capture? - Planning text — frame titles, sticky notes, free-text items, and card titles/descriptions - Board metadata — board names and last-modified times, used to prioritize which boards matter - Nothing visual — shapes, images, connectors, and embeds are skipped; Brief only reads the words Brief connects read-only. It cannot edit, move, or delete anything on your boards. Why should I connect Miro to Brief? Planning context beyond tickets and docs Roadmap thinking often lives on a whiteboard before it's written down anywhere else. Connecting Miro means Brief's picture of your priorities isn't limited to what's already been formalized in Linear or Confluence. One connection covers your team Miro connects at the org level — an admin connects once, and every board Brief can see becomes available context. No per-person setup. Automatic prioritization Brief doesn't need you to pick boards. It automatically favors boards named like roadmaps, sprints, or timelines, and falls back to whatever's been edited most recently. How do I set up the Miro integration? Steps Go to Integrations in Brief Find Miro and click Connect You'll be redirected to Miro to sign in and authorize Brief for read-only board access Approve the requested permissions Done! Brief starts syncing your boards — there's no board picker to configure Because Miro is a team-level connection, only one active connection is needed per organization. If someone else already connected Miro, you'll see it as already connected rather than being asked to authorize again. What happens after I connect? Board scan — Brief lists your org's Miro boards Selection — boards with roadmap/planning-style names are prioritized, then the most recently modified boards fill out the rest Text extraction — Brief pulls frame titles, sticky notes, free text, and card content from the selected boards Context update — that planning text feeds into Brief's understanding of your goals, priorities, and challenges, alongside your other connected sources Resync — Brief periodically re-checks your boards to keep this current; there's no instant push from Miro when a board changes Common Issues "Nothing seems to have synced" Cause: Your org's boards don't contain much text Brief can read — for example, they're mostly diagrams, images, or empty frames. Fix: Brief looks for frame titles, sticky notes, and card text. A board that's purely visual (arrows, shapes, screenshots) won't produce planning signal, even though it synced successfully. "Brief connected to the wrong Miro account" Cause: Whoever clicked Connect was signed into a personal or unrelated Miro account rather than your team's workspace. Fix: Disconnect in Brief, then reconnect while signed into your team's Miro account. Since this is a team-level connection, reconnecting replaces the org's single active connection. "Connection shows as needing reauthorization" Cause: Miro access tokens are short-lived; Brief refreshes them automatically, but a revoked authorization in Miro (or a deactivated Miro account) will break that refresh. Fix: Check that the Miro account that authorized Brief is still active, then reconnect from Brief's Integrations page. "It only sees a few of our boards" Cause: Working as designed — Brief scans your boards but only ingests a bounded, prioritized subset per sync so the process stays fast. Fix: Name your key planning boards clearly (e.g. "Q3 Roadmap", "Sprint Planning") so they're picked up first. What's Next? Now that Miro is connected: - Connect Linear — Pair planning boards with the tickets they turn into - Connect Confluence — Add written strategy docs alongside board content - See how agents use your context — Understand where this planning signal shows up - View Integrations — See all available integrations --- # SharePoint Integration URL: https://briefhq.ai/docs/sharepoint-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 SharePoint gives Brief access to the product documentation and strategy docs living in your Microsoft 365 document libraries. It's the Microsoft equivalent of connecting Google Drive — read-only, so Brief never edits or moves anything. What data does Brief extract? - Document Libraries — Word, Excel, and PowerPoint files stored in SharePoint - Strategy Documents — Roadmaps, PRDs, and planning docs Brief recognizes as strategic context - File Metadata — Titles and modification dates for everything Brief can see Why should I connect SharePoint to Brief? Strategic Context Brief reads your product strategy, roadmaps, and planning docs directly from SharePoint, so agents and teammates stay aligned on what's already been decided. One Search Across Your Docs Once connected, SharePoint content becomes searchable through Brief chat alongside your other connected sources — no more digging through nested libraries. Read-Only by Design Brief only reads from SharePoint. It never creates, edits, or deletes files, so there's nothing to review before you connect. How do I set up this integration? Steps Go to Integrations in Brief Find SharePoint and click Connect Sign in with your Microsoft 365 account Grant permissions — Approve Brief's read access to your document libraries Done! Brief starts syncing There's no extra scoping step after sign-in — once you approve access, Brief starts indexing. What happens after I connect? After connecting: Initial scan — Brief indexes accessible document libraries (2-5 minutes) Content extraction — Brief reads Word, Excel, and PowerPoint files for strategic context Strategy tagging — Documents that look like strategy docs get flagged for the same treatment as your other sources Continuous sync — New and updated files are picked up automatically Permissions & Privacy What Brief Can Access - Document libraries you have permission to view — Brief inherits your Microsoft 365 permissions; it can't see anything you can't - File metadata — Names and modification dates What Brief Cannot Access - Files outside your permissions — Brief never bypasses SharePoint access controls - Write actions — Brief cannot create, edit, or delete anything in SharePoint Common Issues "Admin approval required" during setup Cause: Your Microsoft 365 admin restricts third-party app access to Graph data Fix: Ask your admin to approve Brief's access in the Microsoft 365 admin center, then reconnect. Why aren't any files syncing? Cause: Brief only sees what your Microsoft 365 account has permission to view Fix: Check that you have access to the relevant document libraries in SharePoint. Brief can't request broader access than your own account has. "Files not updating" Cause: Sync delay or a temporary Microsoft Graph API issue Fix: Give it a few minutes. If files still aren't updating, disconnect and reconnect the integration. What's Next? Now that SharePoint is connected: - Connect Google Drive — Cross-reference docs if your team uses both - Connect Notion — Bring in documentation from your other doc sources - Connect Microsoft Teams — Same Microsoft 365 sign-in, now for chat - View Integrations — See all available integrations --- # Zoom Integration URL: https://briefhq.ai/docs/zoom-integration/ Category: Connecting Your Tools Last Updated: 2026-08-27 Zoom is one of the most common places customer conversations happen. Brief connects to your Zoom Cloud Recordings so the themes, pain points, and feature requests buried in those calls surface without anyone re-watching a recording. This page covers the whole lifecycle: adding the Zoom integration, using it, and removing it. What does Brief capture? - Meeting transcripts — Brief downloads the VTT transcript Zoom generates for a Cloud Recording and reads it to extract signals. Brief does not store the transcript file itself; it stays in Zoom. - Recording metadata — meeting topic and start time - Research signals — customer pain points, feature requests, validation, and churn risk that AI agents extract from the transcript, each carrying verbatim quotes from the call Brief reads only recordings that belong to the account you connect — it uses your own per-user Zoom authorization, not an account-wide admin connection. How Brief uses your Zoom permissions Brief requests exactly three Zoom scopes, and no others: Zoom scope | What Brief uses it for user:read:user | Identify the Zoom user who authorized the connection, display the connected account, and check that the account's plan supports Cloud Recording cloud_recording:read:list_user_recordings | Find the Cloud Recordings that belong to the connected user cloud_recording:read:list_recording_files | Locate and retrieve the transcript file associated with those recordings To be explicit about the limits of that access: - All three permissions are read-only. Brief does not create, modify, or delete Zoom users, meetings, recordings, or files. - Each user authorizes their own Zoom account. This is a standard per-user OAuth connection, not an account-wide administrator install. - Brief only reads what it needs to import Cloud Recording transcripts and the meeting topic and start time that go with them. - Brief requests no scopes for chat, contacts, calendars, phone, webinars, or meeting control. Why should I connect Zoom to Brief? Turn calls into research automatically Sales calls, support calls, and customer interviews recorded in Zoom become research signals without anyone writing up notes. One-click authorization Brief publishes its own Zoom Marketplace app, so connecting is standard OAuth — no API keys, no admin setup, no custom app to register. Works alongside other meeting tools If your team already uses Fathom, Granola, or Fireflies for some calls and Zoom's native recording for others, connect all of them — Brief deduplicates insights across sources. How do I set up this integration? Steps Sign in to Brief and go to Integrations Find Zoom and click Connect Authorize Brief in Zoom's OAuth flow — each person connects their own Zoom account Brief checks that your Zoom plan supports Cloud Recording Done! Brief starts syncing your recent recordings Before you connect Brief needs two things on the Zoom side to actually produce transcripts: - A plan with Cloud Recording — Zoom's Basic (free) tier doesn't include cloud recording, so there's nothing for Brief to read. A paid plan with cloud recording enabled is required. - "Create audio transcript" turned on — this Zoom recording setting is off by default and isn't retroactive, so older recordings made before you enable it won't have a transcript. Turn it on in Zoom's recording settings before your next call. How to use Zoom with Brief Connecting is only the first step. Here is the full path from a Zoom call to a research signal you can act on in Brief. Turn on the Zoom settings. In Zoom, enable Cloud Recording and Create audio transcript in your recording settings. Do this before the meeting — Zoom does not generate transcripts retroactively. Record the meeting to the cloud. During the meeting, choose Record to the Cloud. Local recordings stay on the recorder's computer, are never sent to Zoom's API, and cannot be imported. Wait for Zoom to finish processing. Zoom produces the transcript as a separate step after the recording itself. Check the recording in Zoom to confirm the transcript exists before expecting signals in Brief. Wait for Brief's next sync. Brief polls Zoom on a regular cadence rather than receiving an instant push, so the import is not immediate. On each run Brief looks back over the last 90 days of Cloud Recordings. Open the meeting's signals in Brief. Go to User Intelligence and select the Research Signals tab. Read what Brief extracted. Each research signal shows the theme Brief identified, its signal type (feature request, pain point, validation, or churn risk), and the verbatim quotes pulled from the call, with the meeting topic and date attached as the source. Open a signal to see its full detail view. Act on the signal. From a signal's detail page you can set its urgency, change its status, and delete it with Delete Signal. Signals also become part of your workspace context, so you can ask about them in Brief chat. What to expect - A meeting appears only after Zoom finishes processing its Cloud Recording transcript. Until the transcript exists, there is nothing for Brief to read. - Locally recorded meetings are never imported. Only Cloud Recordings are visible to Zoom's API. - A recording with no transcript produces no transcript-derived signals. If "Create audio transcript" was off when the call was recorded, that call cannot generate signals. - The import is not immediate. Brief checks for new recordings periodically. - Not every recorded meeting produces signals. Brief classifies each call first and only extracts customer voice from customer-facing conversations — discovery calls, sales demos, user research interviews, support calls, onboarding, renewals, and churn conversations. Internal calls such as standups, team syncs, internal strategy and roadmap discussions, vendor demos, and job interviews are skipped by design, so they will not appear as research signals. - A customer call that contains no clear themes produces no signal. Brief only writes a signal when it can attach verbatim supporting quotes. Disconnect or remove the Zoom integration You manage the Zoom connection from Brief. Disconnecting in Brief is the removal path, and it is sufficient on its own. Because the connection is a standard OAuth grant, it also appears in your Zoom account's authorized apps, so the optional Zoom-side step below is available if you want to clear it there too. From Brief This is the removal path. It disables the Zoom credential Brief stores and stops all access and importing. Sign in to Brief. Open Integrations. Find Zoom. Click Disconnect — either from the actions menu on the Zoom card, or the Disconnect button on your Personal Connection row. Confirm Disconnect in the dialog. From Zoom (optional) You do not need this step. Disconnecting in Brief already ends Brief's access. If you also want to clear the authorization from your Zoom account's app list: Sign in to Zoom and open your installed apps at marketplace.zoom.us/user/installed. Find Brief in the list. Remove it using the app's action control, and confirm. Zoom labels this screen differently depending on which Marketplace experience your account uses — currently My library, and Manage → Added Apps in the classic view. The link above goes to the right screen either way. What happens after removal Brief stops accessing Zoom. Once you disconnect in Brief, the stored credential is disabled: Brief stops calling Zoom's API and stops importing new recordings and transcripts. Reconnecting requires authorizing again. There is no way to resume a removed connection silently — you go back through Zoom's OAuth screen and grant the three scopes again. Disconnecting in Brief is what starts the deletion clock. Clearing the authorization from your Zoom account does not by itself tell Brief to retire the connection, so disconnect in Brief to start the retention periods below. Imported Zoom data is deleted within 30 days of that disconnect. Recording metadata and transcript-derived content imported from Zoom are treated as Integration Data under Brief's privacy policy and are deleted within 30 days of disconnecting the integration. Research signals already extracted are kept. Signals Brief generated from your calls are workspace data, not Zoom data — they remain in your Brief workspace after you disconnect so your research history is not lost. They are retained while your account is active and deleted within 30 days of an account deletion request. Two qualifications apply to both deadlines, per the privacy policy: - Brief may retain specific information beyond these periods where required for legal compliance, dispute resolution, or enforcement of its agreements. - Backup copies may persist for up to 90 days after removal from active systems. See Data Retention and Your Rights for the governing terms, which take precedence over this summary. To delete signals sooner, you have two options: - Delete them yourself in Brief: open User Intelligence → Research Signals, open a signal, and click Delete Signal. - Request deletion: email privacy@briefhq.ai to request deletion of your personal information or of your entire account. Full details are in Brief's Privacy Policy, including retention periods by data category and how to exercise your access, correction, and deletion rights. Common Issues "Your current plan can't generate cloud recording transcripts" Cause: Your Zoom account is on a plan without Cloud Recording, or Cloud Recording isn't enabled on your account Fix: Upgrade to a Zoom plan tier with Cloud Recording, or ask your Zoom admin to enable it, then reconnect. "No recordings synced" Cause: No meetings have been recorded to the cloud since you connected Fix: Confirm you're recording to the cloud (not locally) in Zoom, and give the sync a few minutes to pick up new meetings. "Missing transcripts" Cause: "Create audio transcript" was off when the meeting was recorded Fix: Turn on Create audio transcript in Zoom's recording settings. It only applies going forward — past recordings won't retroactively get a transcript. "The recording synced but there are no signals" Cause: Brief classified the call as an internal or non-customer conversation, or the transcript contained no themes Brief could support with verbatim quotes Fix: This is expected for standups, internal planning, vendor demos, and interviews. Customer-facing calls with substantive discussion are the ones that produce signals. "Connection needs to be renewed" Cause: Your Zoom authorization expired or was revoked Fix: Reconnect from Integrations — Brief will prompt you to re-authorize. What's Next? - Connect Fathom — another meeting tool option - Connect Granola — use alongside Zoom - Connect Webex Meetings — if your team also meets on Webex - View Integrations — see all available integrations --- # Gong Integration URL: https://briefhq.ai/docs/gong-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Gong is a revenue intelligence platform that records and analyzes your team's sales calls. Connect it to Brief once at the workspace level, and every call your team runs through Gong can become research signal. What does Brief capture? - Call metadata — timing and duration for calls across your workspace - Transcripts — full conversation content, pulled call by call as they complete - Research signals — pain points, feature requests, and sentiment surfaced from what customers actually say Gong flags some calls as private. Brief filters those out before they ever reach extraction — private call transcripts are never ingested. Why should I connect Gong to Brief? One connection covers your whole team Gong is a team-level connection — a Gong admin authorizes once, and every rep's calls flow into Brief. No per-user setup required. Revenue intelligence, not just notes Gong calls are sales conversations, so the pain points, objections, and feature asks Brief surfaces skew toward revenue-relevant signal — the kind of detail that's easy to lose in a rep's own notes. Signals reach the whole org Once connected, themes and quotes from sales calls flow into the same research signals your team already sees from other sources — no separate dashboard to check. How do I set up this integration? Steps Go to Integrations in Brief Find Gong and click Connect Sign in with your Gong admin account and authorize Brief's OAuth app On the Connect Gong screen, copy the webhook URL Brief shows you, then in Gong go to Admin Center → Automation Rules → Add rule, set the trigger to New call and the action to Fire webhook, paste in that URL, and choose Signed JWT header for authentication Copy the public key Gong generates for that rule and paste it back into Brief Click Done — or Skip for now to finish the connection and set up the webhook later Because this is a team-level connection, only one person on your team needs to complete this — every rep's calls are covered from that point on. What happens after I connect? Webhook setup — Brief gives you a webhook URL and verifies incoming events using the public key you copy from Gong's Automation Rule Research extraction — as each call finishes, Brief checks whether Gong marked it private, then pulls the transcript and analyzes it for themes Continuous sync — new calls flow in automatically; Brief's daily sync picks them up, and the Automation Rule (once configured) delivers them in real time If you skipped the webhook step during setup, new calls still arrive via Brief's daily sync — configure the Automation Rule from Brief's Integrations page whenever you want them in real time. Privacy Guarantees - Private calls are never ingested — if Gong marks a call private, Brief drops it before extraction, every time - Aggregated insights, not raw transcripts, reach your team — Brief surfaces themes, trends, and key quotes rather than full call content - Admins control access — disconnect or adjust the workspace connection at any time from Settings Common Issues "No calls syncing" Cause: The Automation Rule webhook wasn't finished during setup, or no calls have completed in Gong since the connection was made Fix: Go to Brief's Integrations page and complete the Gong webhook setup (Automation Rule + public key) if you skipped it earlier. Once it's configured, new calls sync automatically as they finish — there's no backfill of historical calls. "Some calls are missing" Cause: The missing calls were marked private in Gong Fix: This is expected — Brief never pulls transcripts for calls Gong has flagged private. Nothing to fix on your end. "Connection needs re-authorization" Cause: The Gong OAuth token expired or was revoked Fix: Have a Gong admin go to Brief's Integrations page, disconnect Gong, and reconnect. "No research signals from a call" Cause: The call was short, or didn't contain much substantive customer conversation Fix: This is expected — Brief only creates a signal when it finds a clear pain point, request, or reaction in the transcript. Not every call will produce one. What's Next? Now that Gong is connected: - Connect Zoom — Cover calls that happen outside Gong - Connect Fathom — Another meeting source for signal - Connect HubSpot — Pair call signal with pipeline data - View Integrations — See all available integrations --- # Plaud Integration URL: https://briefhq.ai/docs/plaud-integration/ Category: Connecting Your Tools Last Updated: 2026-07-05 Plaud is an AI voice recorder that turns conversations into notes and transcripts. Connect it to Brief and those recordings feed the same research pipeline as your other meeting tools — themes, pain points, and quotes your team can act on, without anyone re-reading the transcript. What data does Brief extract? - Recordings list — Which conversations you've captured - AI Notes — Plaud's generated summary for each recording - Transcripts — Full conversation content - Research Signals — Customer pain points, feature requests, and recurring themes pulled from the above Why should I connect Plaud to Brief? Capture research from anywhere Plaud isn't tied to a meeting platform — it records in-person conversations, calls, and voice memos. Anything you capture becomes research material Brief can analyze alongside your other sources. One connection, no manual review Brief reads notes and transcripts directly through Plaud's connection and extracts themes automatically. You don't have to export files or paste transcripts anywhere. Fits your existing research stack Signals from Plaud sit alongside signals from Fathom, Granola, and your other meeting tools — Brief merges overlapping themes instead of showing you duplicates. How do I set up this integration? Steps Go to Integrations in Brief Find Plaud and click Connect Sign in to your Plaud account and authorize Brief Done! Brief starts syncing your recordings This is your personal connection — each teammate who wants Brief to read their Plaud recordings connects their own account. There's no admin step or team-wide setup. What happens after I connect? After connecting: Initial sync — Brief fetches your recent recordings, notes, and transcripts (1-2 minutes) Research extraction — AI agents analyze the content for themes and signals Continuous sync — New recordings are picked up on Brief's regular sync cycle (not instant — Plaud doesn't push updates in real time) Common Issues "No recordings synced" Cause: Plaud hasn't captured any recordings yet, or the connected account doesn't have any Fix: Confirm you have recordings in the Plaud app under the account you connected to Brief. "New recordings aren't showing up right away" Cause: Plaud updates arrive via periodic sync, not instantly Fix: This is expected — give it a sync cycle. If a recording is still missing after a while, disconnect and reconnect Plaud from Integrations. "No research signals extracted" Cause: The recording is short, or doesn't contain customer conversation Fix: Brief generates the strongest signals from customer-facing conversations (interviews, sales calls, support calls). Personal notes or short voice memos may not produce signals. "Connection stopped working" Cause: Plaud's authorization can expire or be revoked Fix: Go to Integrations, disconnect Plaud, and reconnect to re-authorize. Tips for Best Results Recording Types That Work Best - Customer interviews - Sales discovery calls - Support conversations - User research sessions Recording Types That Don't Generate Signals - Short personal voice memos - Internal team check-ins What's Next? Now that Plaud is connected: - Connect Fathom — Add a meeting-platform recorder alongside Plaud - Connect Granola — Another meeting notes option; Brief merges overlapping signals - Connect Gong — Add call-recording signals at the team level - View Integrations — See all available integrations --- # Troubleshooting Connections URL: https://briefhq.ai/docs/troubleshooting-connections/ Category: Connecting Your Tools Last Updated: 2026-07-05 Having trouble connecting a tool to Brief? This guide covers the most common issues and how to fix them. General Issues Why does my connection fail during OAuth? OAuth flow fails or shows "Connection failed" error. Common Causes: - Popup blocker preventing OAuth window - Missing permissions in the connected tool - Temporary service outage Fixes: Check popup blocker - Look for popup blocker icon in browser URL bar - Click and allow popups for Brief - Try connecting again Verify permissions - Ensure you have admin access to the tool you're connecting - For GitHub: Check that your org allows third-party apps - For Atlassian (Jira/Confluence): May need workspace admin approval Try again - Wait a few minutes - Clear browser cache - Try in an incognito/private window Why isn't any data syncing? Integration connected but no data appears in Brief. Common Causes: - Integration needs time for initial sync - Webhook not registered properly - Tool has no recent data to sync Fixes: Wait for initial sync Integration | Expected Sync Time Linear | 30-60 seconds GitHub | 1-2 minutes Notion/Confluence | 2-5 minutes Fireflies | 1-2 minutes PostHog | 1-2 minutes Check integration status - Go to Integrations page in Brief - Look for sync status indicator - If "Error", try disconnecting and reconnecting Verify data exists - Check that the connected tool has recent activity - For Linear: Ensure your workspace has recent issues - For GitHub: Ensure repo has recent PRs or commits Why is my data stale or out of date? Data in Brief is out of date. Common Causes: - Webhook stopped working - Service temporarily down - Rate limit hit Fixes: Check the integration status - Go to Integrations page - If the card shows a warning, click Reconnect Reconnect - Disconnect the integration - Wait 30 seconds - Reconnect it OAuth Issues Why does it say "Access Denied" during OAuth? OAuth flow shows "Access denied" or permission error. Fixes: Verify admin access - Ensure you have admin/owner permissions in the tool - For GitHub orgs: Need org admin or owner role - For Atlassian: May need workspace admin Check app restrictions - Some orgs block third-party apps by default - GitHub: Check org settings → Third-party access - Atlassian: Check admin console → App management Request approval - For Atlassian tools, ask your workspace admin to approve Brief - Send them the Brief app page to review What should I do if popups are blocked? Nothing happens when clicking "Connect". Fixes: Allow popups - Browser shows popup blocker icon in URL bar - Click it and select "Always allow popups from briefhq.ai" - Click "Connect" again Try different browser - Some browsers are more aggressive with popups - Try Chrome or Firefox if using Safari Webhook Issues Why aren't my webhooks firing? Initial sync worked but new changes don't appear. Fixes: Check webhook registration - For Linear: Settings → Webhooks → Look for Brief webhook - For GitHub: Repo → Settings → Webhooks → Look for Brief webhook Verify webhook URL - Webhook URL should include your org ID - Format: https://app.briefhq.ai/api/webhooks/{tool}?org_id=YOUR_ORG_ID Reconnect integration - Disconnect in Brief - Wait 30 seconds - Reconnect (this re-registers webhooks) Why does Fireflies show "Invalid signature" error? "Invalid signature" error in Fireflies integration. Fixes: Re-copy webhook secret - Go to Fireflies → Settings → Developer - After saving webhook, copy the secret shown - Paste it EXACTLY into Brief (no extra spaces) - Save in Brief Regenerate webhook - In Fireflies, disable webhook - Save - Re-enable webhook - Copy new secret - Update in Brief Tool-Specific Issues Linear "No issues synced" - Ensure your Linear workspace has recent issues - Check that you selected correct workspace during OAuth "Webhook not working" - Go to Linear → Settings → Webhooks - Look for Brief webhook - If missing, disconnect and reconnect GitHub "Can't see my organization" During GitHub OAuth, you must click "Grant" next to your organization. You need org admin or owner role to grant access. If you missed this step: Go to GitHub Settings → Authorized OAuth Apps Find "Brief" and click Revoke Return to Brief and reconnect GitHub This time, click "Grant" next to your organization "Want to use personal repos" Brief supports both organization and personal repositories. In the setup screen, select your username with "(personal)" label. Your personal repos will appear in the repository dropdown. "Need to change repo selection" Click Configure in the GitHub integration's actions menu. This opens the configuration screen where you can change org/repo. No need to disconnect and reconnect. "Cross-referencing not working" - Include your Linear issue key in PR titles: feat(ACME-123): Add feature - Brief looks for pattern: (TICKET-ID) in title Notion "No pages found" - In Notion, you must explicitly share pages with Brief integration - Go to page → Share → Invite "Brief" integration "Missing content" - Check page permissions - Brief only sees pages explicitly shared with it - Share parent pages to include nested pages Granola "No notes synced" - Ensure Granola has recorded meetings. Check that you have recent notes in Granola. "Setup session expired" - Too much time passed between OAuth and confirming setup. Disconnect Granola and reconnect. Fireflies "Transcripts not syncing" - Ensure webhook is enabled in Fireflies - Check "Transcription Completed" event is selected - Verify webhook URL includes your org ID "No themes extracted" - Ensure meetings have actual transcription content - Check Fireflies settings to enable transcription for all meetings PostHog "Invalid API key" - Ensure you selected "MCP Server" scope when creating key - Try regenerating API key in PostHog "No projects shown" - API key needs project:read permission - Create new API key with correct permissions "No events synced" - Ensure PostHog project has events in selected time range - Check that PostHog is actually tracking events Slack "Bot not responding" - Re-add Brief to the channel: /invite @brief-bot - Check bot is installed in workspace "Can't see /decide command" - Re-install Slack app - Slash command may not have registered properly "Wrong workspace" - Disconnect in Brief - Reconnect selecting correct Slack workspace Still Having Issues? If you've tried these fixes and still can't connect: Contact support — Email hello@briefhq.ai with: - Which integration - What you tried - Screenshot of error (if any) - Your org ID (from Settings) Sync Timing Reference For reference, here's how long each integration takes: Integration | Setup Time | Initial Sync | Updates Linear | 1 minute | 30-60 seconds | Real-time GitHub | 1-2 minutes | 1-2 minutes | Real-time Notion | 1 minute | 2-5 minutes | Real-time Confluence | 1 minute | 2-5 minutes | Real-time Google Drive | 1 minute | 2-5 minutes | Real-time Jira | 1 minute | 1-2 minutes | Real-time Asana | 1 minute | 1-2 minutes | Real-time Granola | 1 minute | 1-2 minutes | Polling Fireflies | 3-5 minutes | 1-2 minutes | Real-time Fathom | 1 minute | 1-2 minutes | Real-time PostHog | 2-3 minutes | 1-2 minutes | Polling Slack | 1-2 minutes | Instant | Real-time --- # Brief MCP Setup Guide URL: https://briefhq.ai/docs/mcp-setup/ Category: Connecting Your Tools Last Updated: 2026-07-05 Why Connect Brief to Your AI Coding Assistant? Brief MCP navigates your AI coding assistant to your product context. Instead of AI that's building blind, you get AI that's aligned with your decisions, customers, and strategy. Without Brief MCP | With Brief MCP AI is building blind | AI is aligned with your vision Context resets every session | Context persists and compounds Generic coding suggestions | Navigated to the right approach No decision memory | Validates approach against past decisions Setup takes 2 minutes and works with Cursor, Claude Code, VS Code, Claude Desktop, Codex, and any other MCP-compatible host that supports Streamable HTTP + OAuth. What is Brief MCP? Brief's Model Context Protocol (MCP) integration navigates your AI coding assistant to your product context. When you're coding in Cursor, Claude Code, VS Code, or other MCP-compatible tools, Brief keeps your AI aligned with your decisions automatically. What You Get - Navigate to decisions without leaving your IDE - Record technical decisions as you make them - Access personas and features when designing UX - Validate your approach against past decisions before implementing Think of it as your Navigator that keeps every builder aligned. How Brief MCP authenticates Brief MCP is OAuth-first. Most clients trigger a browser popup automatically on first tool call; a few (like Codex) need one explicit sign-in command instead. Either way, you sign in once, tokens refresh automatically, and there is no API key to copy or rotate. - ✅ No API key management - ✅ Automatic token refresh - ✅ Per-org scoped tokens - ✅ One canonical endpoint: https://app.briefhq.ai/mcp The legacy mcp-remote wrapper and the /api/mcp/sse endpoint are no longer used. If an older guide (or an LLM from last year) tells you to set them up, that guide is stale. Cursor Fastest path: one-click install via the Cursor deep link from the Brief app. From Integrations → MCP → Install, click the "Add to Cursor" button. Or add to ~/.cursor/mcp.json manually: When Cursor connects, a browser window opens for OAuth. No API key required. Claude Code Then run /mcp inside Claude Code and pick brief to authenticate. Verify with: Look for brief ✔ connected. VS Code Add this to .vscode/mcp.json in your project root: VS Code opens a browser window for OAuth on first tool call. Then open Copilot Chat in Agent mode and invoke a Brief tool. Claude Desktop One-click install (recommended) Download brief.mcpb Claude Desktop → Settings → Extensions → Advanced settings → Extension Developer → Install Extension → pick the downloaded file Sign in via browser when prompted on your first tool call The bundle connects to Brief over Streamable HTTP with no config file editing — tools and OAuth work immediately. Add as a Custom Connector (richer UI) Claude Desktop → Settings → Connectors → Add custom connector (on Pro/Max plans the menu may appear as Customize → Connectors) URL: https://app.briefhq.ai/mcp Sign in via browser when prompted Use the Connector path if you want the richer interactive panels — decision approval cards, integration setup UI — since those render best through a Connector. Both paths handle OAuth natively — no API keys, no manual config files. Codex Codex reads MCP server config from ~/.codex/config.toml (not .mcp.json). Add: Then authenticate once from your terminal: A browser window opens for OAuth. After sign-in, Brief tools are available in every subsequent Codex session. JetBrains IDEs (IntelliJ, WebStorm, PyCharm, etc.) JetBrains AI Assistant (2025.1+) supports MCP via Settings → Tools → AI Assistant → Model Context Protocol (MCP). Click +, then Command → As JSON, and paste: Save and invoke a Brief tool from an AI Assistant chat — a browser popup should open for OAuth. Windsurf Settings → Cascade → MCP Servers → Add custom server, with URL https://app.briefhq.ai/mcp and transport http. Windsurf opens a browser window for OAuth on first connect. ChatGPT Brief works with ChatGPT via Connected Apps. Setup is done via ChatGPT Settings → Apps & Connectors → Enable Developer Mode (if eligible) → Create, then enter connector metadata and your HTTPS MCP server URL (https://app.briefhq.ai/mcp). Create the connector via ChatGPT Settings and optionally contact hello@briefhq.ai for help. Other MCP clients Any MCP client that supports Streamable HTTP + OAuth can connect to Brief at https://app.briefhq.ai/mcp. Point your client at the URL with transport http and trigger a tool call — the browser popup will handle OAuth. Step 2: Install the Brief agent behavior layer Once MCP is connected, the agent has access to Brief's tools — but it won't know when to use them unless you tell it. For repo-aware coding agents (Cursor, Claude Code, VS Code, Codex), paste this into a new agent chat in your project's root directory: Your agent will fetch agent-setup.md, detect your repo's existing agent conventions (Cursor rules, CLAUDE.md, AGENTS.md, .cursorrules, etc.), and install Brief skills, rules, and commands — the same setup the Brief team uses internally. Claude Desktop and ChatGPT don't auto-install repo-local skills (no project root), but you can still give them behavioral guidance via a Project's custom instructions. Onboarding-specific entry points Once the behavior layer is installed, prefer these onboarding entry points: - /brief-setup — first-time setup on hosts that surface Brief prompts - /brief-welcome-back — returning workspace, new surface - /brief-context — pull a product context summary any time, optionally filtered to strategy, personas, decisions, or features - brief_get_onboarding_context — raw fallback when prompts are not surfaced - brief_ask with onboarding: true — fresh coding-repo synthesis path after reading the README, package/manifest files, and recent git log --oneline -20 Example fresh-repo onboarding call for coding agents: Not every host surfaces Brief prompts consistently. If you don't see /brief-setup or /brief-welcome-back, fall back to brief_get_onboarding_context, then use brief_ask(..., onboarding: true) on a fresh coding repo. Available Tools The Brief MCP server exposes a small flat top-level surface plus one escape-hatch tool. Top-level tools (direct tool picker) Tool names use the brief_ prefix. Older clients may still show aliases such as ask_brief or bare search / browse — they call the same tools; use the brief_ names in new prompts and docs. Tool | What it does brief_get_onboarding_context | Load Brief's strategic snapshot — decisions, features, personas, velocity, recent work. Call at session start. Supports scopes full, product, or identity. brief_ask | Talk to Brief. mode: 'advise' for open-ended strategic guidance, mode: 'check' to validate an approach against existing decisions, mode: 'fast' for sub-second inline lookups. brief_search | Universal search across decisions, documents, and features. Panel-backed — MCP Apps hosts render results as an interactive card. Pass types: 'decision' to narrow to decisions. brief_browse | Browse folders and documents by path or folder ID. brief_record_decision | Propose a new decision. Renders an approval card; the decision persists after the user clicks Approve. brief_confirm_decision | Transition a proposed decision to active by ID. brief_reject_decision | Reject a proposed decision with a required reason. brief_archive_decision | Archive an outdated decision by ID. brief_list_pending_decisions | List decisions awaiting confirmation (status: proposed). Prefer this when you need the pending queue; use brief_search with types: 'decision' for keyword search across decision history. brief_update_product_context | Partial update to product context (company, goals, velocity, team, metrics). brief_get_integration_status / brief_get_integration_buckets / brief_show_integrations | Check which integrations are connected and show connect cards. brief_get_integration_buckets returns your personal, teammate-connected, and still-available integrations — the agent calls it before telling you something "isn't supported." brief_show_integrations renders connect cards (single integration, a category, or the full grid) as an interactive panel on MCP Apps–capable hosts. brief_execute_operation | Escape hatch. Run operations that don't have a direct top-level tool: create_document, folder operations, bulk ops, guard_approach (prefer brief_ask with mode: 'check'), personas/features/market listings, etc. Takes operation + parameters. Prefer direct tools when they exist. Using Brief in Your IDE Example 1: Check for Past Decisions You: > "I'm about to implement authentication. Are there any existing decisions about this?" AI: > Searches Brief > > "Yes, we decided to use Clerk for authentication (Decision D-42, logged 2 weeks ago). The rationale was to avoid building auth from scratch and get SSO support out of the box." Example 2: Record a New Decision You: > "We're using Postgres instead of MongoDB for the new API because of our relational data needs." AI: > Records decision to Brief > > "I've logged that decision to Brief as D-89. Would you like to add any additional tags or link it to a feature?" Example 3: Get User Personas You: > "Who are we building this feature for? What do they care about?" AI: > Fetches personas from Brief > > "You have 3 personas: > > 1. Product Founders (Primary) — Care about velocity, need strategic clarity > 2. Solo Makers — Want simplicity, low maintenance > 3. Small Teams — Need collaboration, shared context" Example 4: Validate Your Approach You: > "I'm planning to refactor the API to use GraphQL. Does this conflict with anything?" AI: > Calls brief_ask with mode: "check" > > "⚠️ Potential conflict: We decided to stick with REST for simplicity (D-56, 3 months ago). Should we revisit that decision or keep the current approach?" CLI as a sibling channel Brief MCP and the Brief CLI are separate install paths, and you can use both at once. - MCP wires your coding agent to Brief via tool calls inside the host (Cursor, Claude Code, VS Code, etc.). - CLI wires your coding agent to Brief via shell commands — your agent runs brief ask, brief decisions search, etc. from a terminal. If shell-based access is your primary path, follow the Brief CLI setup guide — it's independent of the MCP installation above. Troubleshooting "Connection failed" or "Internal server error" Restart your MCP client to clear its in-memory connection state. If that doesn't help, reinstall the host-native config above. "401 Unauthorized" Your OAuth token expired or was revoked. Sign in again from your host: - Claude Code: /mcp → pick brief → re-auth - Cursor / VS Code / Windsurf: trigger any Brief tool; the browser popup will reappear - Claude Desktop: restart and invoke a Brief tool; the popup will reappear - Codex: run codex mcp login brief again MCP not showing up in your client Verify your config is in the right place: - Cursor: ~/.cursor/mcp.json - Claude Code: managed by claude mcp add — check claude mcp list - VS Code: .vscode/mcp.json (or the extension) - Claude Desktop: the installed .mcpb bundle, or Settings → Connectors if you used the Connector path - Codex: ~/.codex/config.toml Check JSON/TOML syntax is valid. Restart your client. "Tools not found" or AI doesn't respond The MCP server needs to initialize. Restart your IDE/client after configuring. Multi-org mismatch If you're in multiple Brief workspaces and MCP is returning data from the wrong one, switch to the correct org in the Brief web app first, then re-run the install steps (this rotates the token to the active org). Verify Your Setup Claude Code: Look for brief ✔ connected. Cursor: Go to Settings → Features → MCP Servers. Status should be green. Test a query: Ask your AI: "Search Brief for recent decisions" — if it works, you're connected. What's Next? Now that Brief is connected to your IDE: Try the example workflows above to get comfortable Let your AI guide you — it will proactively suggest using Brief Record decisions as you go — don't wait until later Search before implementing — avoid redoing solved problems For more on using Brief effectively, see: - Tips for Better Answers - Example Prompts - Brief CLI Setup — shell-based access for coding agents --- # Chat Overview URL: https://briefhq.ai/docs/chat-overview/ Category: Using Brief Chat Last Updated: 2026-07-05 Brief Chat navigates you to answers about your product, customers, work pipeline, and strategy—backed by your actual data. Every decision is informed. Every builder stays aligned. Where to Find Chat Chat meets you wherever you work: - Web app — Always available in a panel on the right side of the app. Click the chat icon to open or close it, from any page in Brief. - Slack — DM Brief directly for the full agent experience: streaming answers with a collapsible reasoning trace, decision capture, and file understanding. See Slack Integration. - Microsoft Teams — Chat with Brief in Teams with rich Adaptive Cards, thread context, and tool-approval cards. See Microsoft Teams Integration. - Mobile app — Chat on the go, including by voice. See Brief Mobile. - Chrome extension — The same presets and chat experience alongside whatever you're browsing. The same product context powers every surface, so an answer in Slack draws on the same data as an answer in the web app. What Chat Can Do Navigate Your Product Graph - Get your Product Graph, current state, features, personas, research signals - Understand what's built, what's planned, and what's shipped - Track work pipeline and velocity Document Management - Create, read, update, and delete documents in Brief - Write to connected tools — Create docs in Notion, Confluence, or Google Drive - Search across all your documentation Writing & Creation - Write PRDs, specs, and user stories in Brief or connected doc tools - Create tickets in Linear, Jira, or Asana - Generate documentation from existing context Decision Support - Log decisions with context and rationale - Search decision history - Get decision context for strategic questions Cross-App Reasoning - Synthesize information across ALL connected integrations simultaneously - Answer questions like "What are customers asking for that we haven't built?" (pulls from Fireflies + Linear + GitHub) - Connect dots between strategy docs, customer feedback, and shipped features - Query your databases — Ask questions answered by read-only SQL against connected Supabase or PostgreSQL databases Working with Files Chat understands the files you're already working with: - Paste screenshots — Paste an image straight into the composer and it attaches automatically - Attach documents — Drag and drop or use the + button for PDFs, images, and Office documents (Word, Excel, PowerPoint) - @mention Brief documents — Type @ to pull any Brief document into the conversation as context Up to 10 files per message, 10 MB each. Choosing a Model A model picker in the chat composer lets you choose which model answers you. Claude Sonnet 5 is the standard and the best balance of speed and intelligence for most questions; other Claude models are selectable when you want deeper reasoning on a hard problem. How Chat Works Multi-Turn Conversations Chat maintains full conversation history. You can: - Ask follow-up questions - Drill deeper into answers - Build on previous context Conversations are saved automatically and can be resumed later. Real-Time vs. Synced Data Data Type | Freshness Brief documents & decisions | Real-time Integration data (Linear, GitHub, etc.) | Live queries when asked Product graph | Updated by background agents (not real-time) Dashboard metrics | From last sync Read & Write Across Your Stack Tool | Read | Write Brief | ✅ All data | ✅ Full CRUD Notion, Confluence, Google Docs | ✅ Search & read | ✅ Create & update Linear, Jira, Asana | ✅ Issues, projects, sprints | ✅ Create tickets, update issues GitHub | ✅ Repos, files, PRs | ⚠️ Read-only PostHog | ✅ Events, funnels | ⚠️ Read-only Fireflies, Fathom, Granola | ✅ Transcripts | ⚠️ Read-only Supabase, PostgreSQL | ✅ Read-only SQL queries | ⚠️ Read-only Chat can only see the tools you've connected—more integrations mean richer answers. Browse the full list in the Integrations Overview. Empty State & First Use When you first open chat, you'll see a welcome message with preset prompts—pre-built questions matched to your context. Presets are contextual: which ones appear depends on the page you're on, the tools you've connected, and how long you've been using Brief. If you've been away a few days, a catch-up preset offers to summarize what you missed. Click a preset to get started, or type your own question. Conversation Limits No explicit character limit on messages, but there's a context window limit from the model. As a long conversation approaches that limit, Brief automatically compacts earlier context so the conversation keeps going—no need to start over. Managing Conversations Conversation History - Recent conversations appear in the sidebar, sorted by most recent - Access and search older conversations through the History view (clock icon in header) - Conversations stored indefinitely Actions - Copy any answer — one click copies it to your clipboard, ready to paste into your docs or messages - Regenerate last response — ⟳ button appears on hover over assistant message - Edit and resend your own messages — pencil icon appears on hover (not available on messages with attachments) - Delete entire conversation — Trash icon (cannot delete individual messages) What's Next? Ready to start using chat? - Getting Started with Presets — Learn how contextual presets work - Example Prompts — See what questions work well - Tips for Better Answers — Best practices for effective prompts --- # Getting Started with Presets URL: https://briefhq.ai/docs/chat-presets/ Category: Using Brief Chat Last Updated: 2026-07-05 Brief Chat includes pre-built prompts designed for common product management questions. These presets are optimized to pull from your connected integrations and give you actionable answers fast. Presets Are Contextual Presets aren't a fixed list—Brief curates which ones you see from a larger catalog based on: - The page you're on — presets match what you're looking at - The tools you've connected — presets that need data you don't have yet step back - How long you've been using Brief — onboarding presets fade as you settle in - Time away — if you've been gone a few days, a catch-up preset ("What did I miss?") appears first Below are some of the most common presets you'll see. Common Presets 🔭 "I'm new to Brief, show me around" Get started with Brief - What it does: Guided tour of your connected context - Best for: First-time users, onboarding - Response time: ~10 seconds - Integrations needed: None required (works with any) 🚏 "What should we build next?" Prioritize next bets based on context - What it does: Analyzes research signals, work pipeline, and current state to recommend priorities - Best for: Sprint planning, roadmap decisions - Response time: ~25 seconds - Integrations needed: None required — richer with Linear, GitHub, Notion, and a connected meeting tool 👤 "Who are we building for?" Clarify ICP segments - What it does: Synthesizes customer personas from docs, calls, and analytics - Best for: ICP validation, marketing alignment - Response time: ~20 seconds - Integrations needed: None required — richer with Fireflies, Fathom, Granola, Notion, and PostHog 📏 "How do we know it's working?" Measurement plan with outcomes validation - What it does: Creates a measurement plan based on current features and goals - Best for: OKR planning, metrics definition - Response time: ~20 seconds - Integrations needed: None required — richer with Linear, PostHog, and GitHub ⚖️ "What should we stop doing?" Identify low-ROI work to pause or cut - What it does: Analyzes work pipeline to identify low-impact projects - Best for: Quarterly planning, focus decisions - Response time: ~15 seconds - Integrations needed: None required — richer with Linear, GitHub, and Notion How Presets Work Where They Appear Presets show as a vertical list of buttons in the chat empty state, centered below the welcome message. Each button displays: - Icon - Label (main question) - Description (what it does) Click to Execute When you click a preset: Creates a new conversation (if needed) Auto-executes immediately — no need to confirm Sends the preset text as your message Applies hidden context template for better results You'll see the preset working through tool calls (expandable sections showing what Brief is doing). Using Presets Without Integrations If you click "Who are we building for?" with no integrations: - Brief uses product graph data from onboarding - Explains what additional context it needs - Suggests connecting Fireflies, Fathom, Granola, Notion, or customer research tools - Still attempts an answer based on available info Example response: > "Based on your onboarding info, you're targeting early-stage startups. However, I don't have customer call data or analytics to validate this. Would you like to connect a meeting tool (Fireflies, Fathom, or Granola) to capture customer insights?" Response Times Preset | Typical Time | Complexity Show me around | ~10 seconds | Simple What to build next | ~25 seconds | Moderate (queries current state) Who are we building for | ~20 seconds | Moderate Is it working | ~20 seconds | Moderate What to stop | ~15 seconds | Simple Customizing Presets Can't create your own presets currently — presets come from a catalog Brief curates, and which ones appear is chosen for you based on your context. However, you can: - Use presets as templates for your own questions - Modify preset questions in follow-ups - Save your own common prompts externally Getting Better Results Connect More Integrations No preset requires a specific integration to run, but every preset gets sharper with more connected context—Linear, GitHub, Notion, a meeting tool (Fireflies, Fathom, or Granola), and PostHog each add evidence Brief can draw on. Follow Up Presets give you starting points. Always follow up to drill deeper: After "What should we build next?": - "Tell me more about that second recommendation" - "What evidence supports this?" - "Show me customer quotes about this feature" - "What's the smallest version we could ship?" Use with Documents Drag documents into chat before running a preset for even better context. What's Next? Now that you understand presets: - Example Prompts — See more questions you can ask - Tips for Better Answers — Best practices for effective prompts - Chat Overview — Learn more about what chat can do --- # Example Prompts URL: https://briefhq.ai/docs/chat-examples/ Category: Using Brief Chat Last Updated: 2026-07-05 Brief Chat works best when you ask specific, contextual questions. Here are real examples of prompts that work well, organized by use case. Strategic Planning Big Picture Questions What are our biggest product risks right now? - Analyzes roadmap, customer feedback, and technical debt - Identifies gaps between strategy and execution How aligned is our roadmap with customer feedback? - Cross-references Linear roadmap with Fireflies/Fathom/Granola transcripts - Highlights misalignment or validation What features are most requested but not built yet? - Searches customer calls and support conversations - Compares against shipped features in GitHub/Linear Feature Prioritization Comparison & Trade-offs Compare the impact of building X vs Y - Analyzes customer mentions, usage data, and technical complexity - Provides evidence-based recommendation What's the smallest thing we could ship to test this hypothesis? - Reviews current architecture and feature scope - Suggests MVP approach What dependencies are blocking our next release? - Checks Linear/Jira for blocked tickets - Identifies critical path issues Customer Research Understanding Your Users What pain points do enterprise customers mention most? - Searches Fireflies/Fathom/Granola transcripts - Groups by theme and frequency Show me the top themes from recent customer calls - Analyzes last 30 days of call transcripts - Ranks by mention frequency Who are our happiest customers and what do they have in common? - Combines PostHog behavior data with customer calls - Identifies success patterns Velocity & Operations Team Performance How long does it typically take us to ship a feature? - Analyzes Linear cycle time - Shows average and distribution What's our bug-to-feature ratio in the last quarter? - Queries Linear/Jira for issue types - Calculates ratio and trend Which team members are overloaded right now? - Checks GitHub commits and Linear assignments - Identifies bottlenecks Decision Support Decision History What decisions have we made about pricing? - Searches Brief's decision log - Shows chronological decision history Show me all documented trade-offs for the mobile strategy - Finds decisions tagged with "mobile" and "trade-off" - Displays rationale and context What did we decide about authentication last month? - Time-scoped decision search - Includes who decided and why Follow-Up Questions After any initial answer, drill deeper: Get More Detail - "Tell me more about that third point" - "Explain the reasoning behind this recommendation" - "What are the counter-arguments?" Request Evidence - "What evidence supports this?" - "Show me specific quotes from customer calls" - "Which customers mentioned this?" - "What's the data behind this claim?" Validate Confidence - "How confident are you in this answer?" - "What else would you need to be more certain?" - "Are there gaps in this analysis?" Explore Alternatives - "What if we did X instead?" - "What are we missing?" - "What's the opposite perspective?" What Works Well ✅ Specific Questions Good: "What do customers say about our onboarding flow?" Better: "What pain points do SMB customers mention about onboarding in the last 30 days?" ✅ Using Exact Names Good: "What's the status of that new feature?" Better: "What's the status of Project Phoenix?" ✅ Time-Scoped Questions Good: "What did we ship?" Better: "What features did we ship last quarter?" ✅ Context-Rich Prompts Good: "What should we prioritize?" Better: "Given our focus on SMB customers and limited eng resources, what should we prioritize next quarter?" What Doesn't Work ❌ Vague Questions Bad: "How are things going?" Why: Too broad, no clear answer Better: "How is our sprint velocity trending over the last 3 months?" ❌ Questions Requiring Unconnected Data Bad: "What do Salesforce leads say?" (if Salesforce not connected) Why: Can't access unconnected data Better: First connect Salesforce, then ask ❌ Future Predictions Bad: "Will we hit our Q4 goals?" Why: Can analyze trends but not predict future Better: "Based on current velocity, are we on track for Q4 goals?" Advanced Prompt Patterns Context + Question + Format Comparison with Criteria Time-Scoped Analysis Tips for Better Prompts Start specific, get general when exploring - Specific gets actionable answers - General surfaces unexpected patterns Reference your exact data - Use project names, feature names, customer segments - Brief searches your actual content Ask for evidence - "Show me the data" - "What supports this?" - Gets traceable answers Use follow-ups - Don't try to ask everything at once - Build on previous answers Mention constraints - Time, resources, team size - Gets more realistic recommendations What's Next? Ready to improve your prompts further? - Tips for Better Answers — Best practices and common mistakes - Getting Started with Presets — Use pre-built prompts - Chat Overview — Learn more about chat capabilities --- # Tips for Better Answers URL: https://briefhq.ai/docs/chat-tips/ Category: Using Brief Chat Last Updated: 2026-07-05 Get better answers from Brief Chat by following these best practices and avoiding common pitfalls. Top 5 Tips Be Specific About Scope Bad: "What should we build?" Good: "What should we build next for enterprise customers?" Adding context about WHO or WHAT helps Brief filter relevant data and give actionable answers. Reference Your Data Use @mentions or drag documents into chat for instant context. Example: "@PRD-Feature-X What customer feedback supports this approach?" Brief will search that specific document plus related context. Ask for Evidence Don't just accept answers—ask where they come from. Follow-up prompts: - "Show me the quotes that support this" - "What data backs this recommendation?" - "Which customers mentioned this?" Gets you traceable, verifiable answers. Use Presets as Templates Preset prompts are optimized for common PM questions—Brief surfaces the ones that match your context. Use them as starting points: - 🚏 "What should we build next?" - 👤 "Who are we building for?" - 📏 "How do we know it's working?" - ⚖️ "What should we stop doing?" Then follow up with specific details. Follow Up to Drill Down Don't try to ask everything in one prompt. Start broad, then drill: "What should we prioritize next?" "Tell me more about that second recommendation" "Show me customer quotes about this feature" "What's the smallest version we could ship?" What Brief Excels At Brief is designed to answer strategic product questions by synthesizing data from your connected tools. Here's where it shines: Strategic Planning - "What should we build next?" - "What are our biggest product risks?" - "How aligned is our roadmap with customer feedback?" - "What opportunities are we missing?" Customer Understanding - "Who are we building for?" - "What pain points do enterprise customers mention most?" - "What themes are emerging from recent calls?" - "Who are our happiest customers and what do they have in common?" Feature Prioritization - "Compare building feature X vs Y" - "What features are most requested but not built?" - "What's the smallest thing we could ship to test this hypothesis?" - "What dependencies are blocking our next release?" Decision Support - "What did we decide about pricing last quarter?" - "Show me all trade-offs we documented for the mobile strategy" - "What decisions are related to authentication?" Velocity & Operations - "How long does it typically take us to ship a feature?" - "What's our bug-to-feature ratio this quarter?" - "Which team members are overloaded right now?" What Brief Can't Do Understanding Brief's limitations helps you avoid frustration: No Future Predictions ❌ "Will we hit our Q4 revenue goals?" ❌ "How many users will we have next month?" Brief can analyze trends and historical data but won't predict the future. Limited to Connected Data ❌ "What do Salesforce leads say about our product?" (if Salesforce isn't connected) ❌ "Show me all customer interviews" (if Fireflies/Fathom/Granola aren't connected) Brief can only work with tools you've connected. More integrations = richer answers. Integration Capabilities Via Brief Chat: - ✅ Search and read from all connected tools - ✅ Create documents and decisions in Brief - ✅ Create and update Linear issues, Jira tickets, Asana tasks - ✅ Write to Notion, Confluence, Google Docs - ✅ Query connected Supabase or PostgreSQL databases (read-only) - ❌ Can't push code to GitHub directly Recommended Prompt Structure The Context-Question-Format Pattern Why it works: - Context narrows the scope - Question is specific and actionable - Format makes the answer useful Other Effective Patterns Comparison with criteria: Time-scoped analysis: Constraint-aware: Specific vs. General Prompts Start Specific Specific questions get actionable answers: - ✅ "What's the status of Project Phoenix?" - ✅ "What has Sarah been working on this sprint?" - ✅ "Show me bugs related to authentication" General questions surface unexpected patterns: - ✅ "What themes are emerging from customer research?" - ✅ "What are we not talking about that we should be?" - ✅ "What decisions are we avoiding?" Strategy Start specific for immediate answers Go general when exploring or brainstorming Return to specific to take action Questions vs. Statements Both work, but questions signal what you want better: Questions (preferred): - ✅ "What's our current sprint velocity?" - ✅ "How do customers feel about our pricing?" Statements (also work): - ✅ "Show me our sprint velocity data" - ✅ "Summarize customer feedback on pricing" Too vague (doesn't work): - ❌ "Sprint velocity" - ❌ "Pricing" Common Mistakes Asking Without Context Connected Problem: "What are customers saying?" with no integrations Fix: Connect at least Fireflies, Fathom, or Granola first Expecting Real-Time Data Problem: "What was just committed to GitHub?" Reality: Brief queries integrations live but may have a sync delay Fix: Ask "What was committed today?" instead of "just now" Not Using @Mentions Problem: Asking about documents without referencing them Fix: Type @ to mention documents, or drag them into chat Example: "@Q4-Strategy What metrics should we track?" is better than "What metrics should we track?" Describing What You Could Just Show Problem: Typing a long description of a UI issue, chart, or error message Reality: Brief reads images and documents directly Fix: Paste a screenshot or attach the file (PDFs and Office docs work too) Not Following Up Problem: Accepting first answer as final Reality: First answers are starting points Fix: Always drill deeper: - "Tell me more" - "What's the evidence?" - "What are we missing?" How Specific Should You Be? About Features/Products/People Use exact names: - ✅ "What's the status of Project Phoenix?" - ❌ "What's the status of that new feature?" - ✅ "What has Sarah been working on?" - ❌ "What has the team been doing?" Brief searches your actual data, so YOUR terminology works best. About Integrations You don't need to mention integration names: - "What's our current sprint?" → Brief checks Linear automatically - "Check Linear for our current sprint" → Works but unnecessary Mentioning integrations CAN help: - More targeted queries - Clearer intent - Faster responses Use when you want to be explicit, skip when it's obvious. Advanced Usage @Mentions for Context Type @ to see autocomplete of your documents: - Search by title - Select to add to context - Brief will reference that document Attach Files: Drag, Drop, or Paste Drag documents or files directly into chat, or paste a screenshot straight into the composer: - Adds the file to conversation context - Works with images, PDFs, markdown, and Office docs (Word, Excel, PowerPoint) - Up to 10 files, 10MB each No Slash Commands (Yet) Currently no special syntax like /search or /summarize. Just ask naturally: "Search for..." or "Summarize..." What Persists Between Conversations The context you build up compounds over time: ✅ Decisions you log become searchable context ✅ Documents you create persist and are searchable ✅ Product graph updates persist across sessions ✅ Past conversations are saved and searchable in History The more you log and create, the sharper future answers get. Providing Context in Prompts You can (and should) add context about yourself: Role context: - "As a founder evaluating product-market fit, what should I focus on?" - "I'm a new PM on this team—what decisions have been made about our mobile strategy?" Situation context: - "I'm preparing for a board meeting—summarize our Q3 progress" - "We're deciding between feature X and Y tomorrow—what data do we have?" Constraint context: - "With 2 engineers and limited time, what's most important?" - "Assuming we can't hire, what should we cut?" This helps Brief tailor answers to your specific needs. Most Surprising Capabilities Drag Any Document Into Chat Not just Brief documents—PDFs, images, and Office docs (Word, Excel, PowerPoint) all work. Brief will read and incorporate them into answers. Preset Prompts That Actually Work Unlike generic AI tools, Brief's presets are designed for PM work and actually give useful answers out of the box. See Exactly What Brief Is Doing Tool calls expand to show you: - Which integrations Brief queried - What documents it read - What data it analyzed Transparency into the "thinking" process. Cross-Integration Synthesis Ask: "What are customers asking for that we haven't built?" Brief will: - Check Fireflies for requests - Compare against Linear roadmap - Scan GitHub for shipped features - Synthesize the gap Decision Memory That Works "What did we decide about X?" actually works if you've logged the decision. Your past decisions become searchable institutional memory. What's Next? Keep exploring chat: - Example Prompts — See more questions that work well - Getting Started with Presets — Use contextual preset prompts - Chat Overview — Learn what chat can do --- # Brief Agents URL: https://briefhq.ai/docs/agents-overview/ Category: Using Brief Agents Last Updated: 2026-07-05 Chat is how you ask Brief questions. Agents are how Brief works for you when you're not asking — they run on schedules in the background, read the data from your connected tools, and deliver findings so your team never ships blind. Chat vs. agents When you chat with Brief, you start the conversation. Agents flip that around: each one has a job, a schedule, and a place it delivers results. While you work, they keep your product context current — decisions, signals, competitors, pipeline, roadmap — and surface what matters without being asked. Every agent is grounded in your connected tools. The more you connect, the more your agents can see. The Agents page Open Agents in Brief to see your workspace's roster. Each agent appears as a card showing its status, when it last ran, and what it produced — pending suggestions awaiting your review, items synced, or signals extracted. Click any card to open the agent's detail view. The detail view has four tabs: - Skill — the agent's job description, written in plain language. This is what the agent actually follows on every run, and it's editable: change what the agent focuses on, the tone of its output, or what it should ignore. - Options — configuration: the schedule it runs on, which model it thinks with (where the agent supports a choice of the latest Claude models), and the sources it reads from. You can see each source's connection health and jump straight to connecting an integration the agent would benefit from. - Grading — the quality rubric the agent's output is held to. You can customize the rubric for your workspace, and reset back to the default at any time. - Runs — the full run history: when each run started, how long it took, what triggered it, and whether it produced results, found nothing new, or hit an error. How agents deliver their output Agents write results in one of two ways, and the detail view shows which applies: - Suggested for your review — agents working on subjective, strategic material (strategy, positioning, personas, features, decisions) propose changes as pending suggestions. Nothing lands in your product context until someone on your team accepts it. The agent proposes; you decide. - Written directly — agents syncing observed facts (revenue, pipeline, work items, competitor pages, signals) write straight to your workspace. A subscription exists or it doesn't — there's nothing to approve. For review-gated agents, the agent card shows how many suggestions are waiting and links to the review surface. Reading agent status Each card carries a status so you can tell health at a glance: - Active — the latest run completed recently and produced output - Empty — the latest run completed but found nothing new to report - Failing — the latest run hit an error - Stalled — the agent hasn't produced a decisive result recently - Never run — the agent hasn't executed yet Brief distinguishes real agent failures from infrastructure interruptions (like a routine deploy): an interrupted run shows as an interruption, not a failure, and doesn't mark a healthy agent as broken. Edits are quality-checked before they go live When you save a change to an agent's skill, Brief reviews the edit against the agent's grading rubric before it takes effect. Edits that pass become the new live version; edits that would degrade the agent's output are blocked with specific, actionable reasons so you can adjust and resave. The running agent is never affected by an in-progress draft — only an approved version changes what it does on its next run. Every approved edit is versioned. The Skill tab keeps a full history, and admins can restore any prior version. Create your own agents You can create custom agents without leaving chat. Describe what you want watched and where results should go — for example: > "Every Monday morning, digest what our competitors changed on pricing and post it to #competitive-intel." Brief drafts the agent — its skill, schedule, and delivery target — and shows you an approval card before anything is created. Once you approve, the agent joins your roster on the Agents page like any other, with the same Skill, Options, Grading, and Runs tabs. Start from a preset Brief ships a catalog of vetted agent archetypes so you don't have to design from scratch. Ask Brief in chat what agents it can create, or pick a preset directly. The catalog includes: - Target account monitor — watch a named account and digest new signals, news, and activity - Competitor pricing digest — track a competitor's pricing changes and post them to a Slack channel - Keyword mention digest — track mentions of a keyword or brand across your research signals - Competitive landscape monitor — digest movement across your whole competitor set - Decisions digest — summarize the decisions your team recorded - Positioning & messaging brief — digest your canonical positioning into a shareable brief - Persona insights digest — surface insights across your persona set - Feature roadmap signal — digest roadmap movement across your feature set - Pipeline deal digest — summarize deal movement across your pipeline - Revenue metrics summary — recap your revenue metrics - Research theme digest — cluster recent research signals into themes - Strategy brief — tie recent decisions back to your stated strategy - Velocity & throughput report — report delivery velocity across your work pipeline - Product usage insights — digest usage insights from your product analytics Most presets take a focus variable — a specific account, competitor, keyword, or area — so the same archetype can run several times with different scopes. Schedules and delivery Custom agents run on the cadence you choose — hourly, daily, or weekly, with a time and timezone you set for daily and weekly runs. Results are delivered in-app, and you can route them to a Slack channel: Brief shows you a channel picker from your connected Slack workspace when you set the agent up. See the Slack integration for connecting Slack. Edit agents from chat You don't have to open the Agents page to tune an agent. Ask Brief in chat to change an agent — "make the competitor digest shorter" or "move my pipeline digest to Fridays" — and Brief loads the agent, proposes the specific change as a plan, and applies it only after you approve. The same quality check runs on chat edits as on edits made from the Agents page. Built-in briefings Two briefings come with every workspace — no setup needed beyond connecting your tools. Weekly Brief The Weekly Brief is a strategic digest delivered once a week to every workspace with data: what shipped, what changed, what your signals are saying, and where things are drifting from plan. It's on by default and built as a full tool-calling agent, so it reads your live data rather than a stale snapshot. It appears on the Agents page like any other agent, so you can read its skill, check its runs, and tune its rubric. Daily Pulse The Daily Pulse is an opt-in daily summary of activity across your workspace, delivered by email and — if you've connected Slack — posted to your team's notification channel. Each pulse includes an AI-written summary up top and a Discuss with Brief link that opens chat pre-loaded with the digest's context, so you can go from "what happened" to "what should we do about it" in one click. Proactive nudges Beyond scheduled briefings, Brief speaks up on its own when something specific needs you: - Review invitations — when Brief has accumulated things worth your attention, it opens your next chat session with a short "I noticed a few things since we last talked — want to run through them?" If you've been away from chat for a while and something important is queued, Brief sends a single Slack DM with a link to review together. - Decision-expiry reminders — when a decision you recorded is coming up for re-confirmation, Brief emails a short recap: what you decided, why, and what's changed since — so you can re-confirm or revisit with current context. - Signal-surge alerts — when a theme suddenly spikes across your research signals, Brief flags the surge so you see the pattern while it's still forming. Nudges are deliberately gentle. Brief rate-limits how often it interrupts, and deferring a review invitation ("later") quiets nudges for a week while your queue keeps accumulating — you control the cadence, and nothing is lost. What's next - Connect your tools — agents are only as good as the data they can see - Chat overview — create and edit agents conversationally - Slack integration — route agent output and nudges into Slack - Quick start — new to Brief? Start here --- # Billing & Seats URL: https://briefhq.ai/docs/billing/ Category: Account & Billing Last Updated: 2026-07-05 Brief uses simple seat-based billing: your workspace pays for the seats it purchases, and everything about adding or removing people shows you the cost before anything is charged. This page covers plans, seats, billing periods, and promo codes. Plans at a Glance - Free — every workspace starts here, with a monthly usage allowance per member. No credit card required. - Pro — a personal plan with a larger monthly allowance, billed per seat. - Team — a workspace plan billed per seat with a pooled usage allowance that scales with your seat count. Team plans have a 5-seat minimum. - Enterprise — a custom contract for larger organizations. Contact us to talk through your needs. Pricing is shown in the app on the upgrade page and at checkout — current per-seat prices always live there, so we don't repeat them here. Upgrading Your Workspace Go to Settings → Billing and choose a plan, or visit the upgrade page directly. You're taken to a secure Stripe checkout. For Team plans, the seat count is pre-filled from your current member count (minimum 5) and you can adjust it before paying. After payment, you're returned to your billing settings with the plan active. Only a workspace admin can purchase a Team plan. The admin who completes the purchase becomes the billing owner for the workspace. Seats: Purchased vs Used A seat is used by an active member or a pending invitation — invites hold a seat until they're accepted or revoked. Admins see a plan banner on the Members page showing your plan, how many seats you've purchased, and how many are in use, along with your renewal date. The Billing settings page shows the same seat summary. Inviting Teammates When you invite people from the Members page: Enter one or more email addresses and choose a role. If the invites need more seats than you've purchased, Brief shows a cost preview — the prorated charge for the added seats and your new monthly total. You confirm, the charge is applied, and only then are the invitations sent. Assigning the admin role to teammates requires a Team plan. Removing Members and Proration Changing an existing member's role or removing them from the workspace requires a Team plan — on Free, membership is invite-only and roles and removal aren't available until you upgrade. When you remove a member, the confirmation dialog shows a proration preview — the credit applied to your subscription for the unused portion of that seat's billing period. Seat counts update automatically, and pending invitations you revoke free their seats the same way. Billing Periods Your billing period is anchored to the day you joined or upgraded — not the calendar month. If you signed up on the 17th, your usage allowance resets on the 17th of every month. Your current period's end date is shown on the Billing settings page. Managing Your Subscription From Settings → Billing, choose Manage Billing to open the secure Stripe customer portal, where you can: - Update your payment method - View and download invoices - Change or cancel your subscription For workspace plans, the billing owner manages the subscription. Promo Codes If you have a promo code, apply it through either link: - New to Brief: briefhq.ai/sign-up?promo=YOURCODE — the code is carried through sign-up, and after you create your account you land on the upgrade page with the discount already applied. - Existing account: briefhq.ai/upgrade?promo=YOURCODE — the discount is applied through checkout. An invalid or expired code never blocks sign-up; you'll simply see standard pricing. Common Questions Do pending invitations cost a seat? Yes — a pending invite reserves a seat until it's accepted or revoked. Revoking an invite frees the seat. Who can manage billing? Any team member can invite people to the workspace. Only admins can change roles, remove members, and see the seat usage banner; the billing owner (the admin who purchased the plan) manages the subscription in the Stripe portal. What happens to usage limits on a Team plan? Your workspace's pooled usage allowance scales with the number of seats you've purchased, and resets each billing period. What's Next - Quick Start — get your workspace set up - Integrations Overview — connect the tools your team already uses ---