Tips for Better Answers

Get better answers from Brief Chat by following these best practices and avoiding common pitfalls.

Top 5 Tips

1. 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.

2. 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.

3. 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.

4. Use Presets as Templates

The 5 preset prompts are optimized for common PM questions. 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.

5. Follow Up to Drill Down

Don't try to ask everything in one prompt. Start broad, then drill:

1. "What should we prioritize next?"
2. "Tell me more about that second recommendation"
3. "Show me customer quotes about this feature"
4. "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 External Web Access

❌ "What's Notion's pricing strategy?" ❌ "How does Stripe's API work?" ❌ "What are competitors building?"

Brief only knows about YOUR product data from connected tools.

No Real-Time External Status

❌ "Is Linear down right now?" ❌ "What's the weather for our launch event?"

Brief can't check external services or real-time information.

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 aren't connected)

Brief can only work with tools you've connected. More integrations = richer answers.

Integration Capabilities

Via Brief Chat (Web UI):

• ✅ Search and read from all connected tools
• ✅ Create documents and decisions in Brief
• ❌ Can't write to external tools (Linear, Jira, Notion, etc.)

Via MCP (AI Coding Assistants):

• ✅ Full read/write access to Brief (documents, decisions)
• ✅ Can create and update Linear issues, Jira tickets, Asana tasks
• ✅ Can write to Notion, Confluence, Google Docs
• ✅ Search GitHub PRs, read analytics from PostHog
• ❌ Can't push code to GitHub directly

Recommended Prompt Structure

The Context-Question-Format Pattern

[Context] + [Question] + [Format Request]

"Given our focus on SMB customers, 
what features should we prioritize next quarter? 
List the top 3 with evidence from customer calls."

Why it works:

• Context narrows the scope
• Question is specific and actionable
• Format makes the answer useful

Other Effective Patterns

Comparison with criteria:

Compare building feature X vs Y. 
Consider: customer demand, technical effort, strategic fit.

Time-scoped analysis:

What decisions did we make about pricing in Q3? 
Show the evolution of our thinking.

Constraint-aware:

With 2 engineers and 6-week runway, 
what's the highest-impact thing we could ship?

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

1. Start specific for immediate answers
2. Go general when exploring or brainstorming
3. 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

1. Asking Without Context Connected

Problem: "What are customers saying?" with no integrations Fix: Connect at least Fireflies or Fathom first

2. 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"

3. 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?"

4. Asking About External Topics

Problem: "What's Notion's pricing?" or "How does Stripe work?" Reality: Brief only knows YOUR product data

Fix: Ask about YOUR products, customers, and data

5. 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

Drag and Drop

Drag documents or files directly into chat:

• Adds document to conversation context
• Works with PDFs, docs, markdown
• 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..."

Does Chat Learn?

No persistent learning between conversations.

Each conversation starts fresh. However:

✅ Decisions you log become searchable context ✅ Documents you create persist and are searchable ✅ Product graph updates persist across sessions ❌ Chat doesn't remember your preferences or style

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, Google Docs links, anything. 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 the 5 built-in prompts
• Chat Overview — Learn what chat can do