Guides

User Memory

Let your AI remember facts about users across conversations for personalized experiences.

|View as Markdown
Hunter HodnettCPTO at Chipp
|6 min read

User Memory enables your AI to remember important facts about users across conversations. Instead of starting fresh every time, your AI can recall preferences, past interactions, and relevant details.

What Is User Memory?

User Memory automatically extracts and stores durable facts from conversations:

Memory TypeExamples
Saved Facts"User's company is Acme Corp", "Prefers email over phone"
Preferences"Likes concise answers", "Uses metric system"
User Insights"Technical background", "Decision maker for purchases"
Topic Highlights"Interested in enterprise pricing", "Asked about API limits"

How It Works

User: "I'm the CTO at Acme Corp and we're evaluating your enterprise plan"
           ↓
    [Conversation ends]
           ↓
    [Memory extraction runs]
           ↓
    Memories stored:
    - Role: CTO
    - Company: Acme Corp
    - Interest: Enterprise plan
           ↓
    [Next conversation]
           ↓
AI: "Welcome back! Last time we discussed enterprise pricing for Acme Corp..."

Enabling User Memory

1
Open Memory Settings

Go to your app's Build page and find Memory Settings in the sidebar.

2
Enable Memory Extraction

Toggle on Enable User Memory. This activates automatic memory extraction from conversations.

3
Configure Categories (Optional)

Choose which types of information to remember:

  • Saved Facts: Concrete information (names, companies, roles)
  • Preferences: How users like to interact
  • Topic Highlights: Key discussion topics
  • User Insights: Inferred characteristics
  • Recent Queries: Common questions asked
4
Set Custom Instructions (Optional)

Add specific extraction guidance:

Focus on:
- Company size and industry
- Budget constraints mentioned
- Technical requirements discussed
- Decision timeline

Do NOT remember:
- Personal contact information
- Specific financial figures
- Confidential business details

Memory Categories

Saved Facts

Concrete, verifiable information:

  • Names and roles
  • Company information
  • Product preferences
  • Account details

Preferences

How users like to interact:

  • Communication style (formal/casual)
  • Response length preference
  • Preferred formats (bullet points, paragraphs)
  • Language preferences

Topic Highlights

Key subjects from conversations:

  • Features they're interested in
  • Problems they're trying to solve
  • Questions they've asked
  • Products they've discussed

User Insights

Inferred characteristics:

  • Technical expertise level
  • Decision-making authority
  • Industry background
  • Use case patterns

Viewing Stored Memories

Go to Chats > select a user > Memories to see:

  • All memories for that user
  • When each memory was created
  • Which conversation it came from
  • Confidence score

Managing Memories

Editing Memories

Click on any memory to edit or correct it:

  1. Update the content
  2. Change the category
  3. Adjust confidence score

Deleting Memories

Remove memories that are:

  • Incorrect
  • Outdated
  • No longer relevant

Go to Memories > click the memory > Delete.

Bulk Management

For compliance or cleanup:

  • Delete all memories for a user: User profile > Clear Memory
  • Export memories: Download as CSV for review

Best Practices

What to Remember

Do remember:

  • Professional context (company, role, industry)
  • Stated preferences
  • Key topics discussed
  • Problems they're solving

Don't remember:

  • Sensitive personal information
  • Temporary states ("having a bad day")
  • Information they asked you to forget
  • Confidential business data without consent

Privacy Considerations

⚠️

Always inform users that your AI has memory capabilities. Consider adding to your system prompt: "I can remember relevant details from our conversations to provide better assistance. Let me know if you'd prefer I not remember something."

Memory in Your System Prompt

Help your AI use memories effectively:

You have access to memories about this user from past conversations.
Use these to:
- Personalize greetings and responses
- Avoid asking questions they've already answered
- Reference their specific context

Don't:
- Mention that you "remember" things in a creepy way
- Assume memories are 100% accurate
- Reference memories if they seem outdated

How Memory Extraction Works

Memory extraction happens automatically after conversations:

  1. Conversation ends: User leaves or 10 minutes of inactivity
  2. Queued for processing: Conversation enters the memory queue
  3. AI analysis: GPT-4 analyzes the conversation for memorable facts
  4. Structured extraction: Facts are categorized and scored for confidence
  5. Storage: Memories are encrypted and stored with the user profile

Extraction Timing

TriggerWhen It Happens
Inactivity10 minutes without messages
User leavesExplicit session end
Batch processingEvery 10 minutes for queued sessions

Confidence Scores

Each memory has a confidence score (0-1):

  • 0.9-1.0: Explicitly stated by user
  • 0.7-0.9: Strongly implied
  • 0.5-0.7: Reasonable inference
  • Below 0.5: Uncertain, may need verification

Use Cases

Customer Support

Remember:

  • Product version they're using
  • Past issues they've reported
  • Preferred contact method
  • Technical expertise level

Sales Conversations

Remember:

  • Company size and industry
  • Budget discussions
  • Decision timeline
  • Stakeholders involved

Personal Assistants

Remember:

  • Work schedule preferences
  • Project names and contexts
  • Communication preferences
  • Recurring tasks

Educational Apps

Remember:

  • Learning progress
  • Topics mastered
  • Areas needing work
  • Preferred learning style

Troubleshooting

Memories Not Being Extracted

  1. Verify memory is enabled in settings
  2. Check that conversations are ending properly
  3. Allow 10-15 minutes for extraction to process
  4. Verify the user is identified (not anonymous)

Incorrect Memories

  1. Review and edit incorrect memories
  2. Adjust custom extraction instructions
  3. Add negative examples to instructions

Too Many Memories

  1. Focus extraction on specific categories
  2. Add instructions to prioritize durable facts
  3. Periodically clean up outdated memories

Limitations

Current limitations to be aware of:

  • Extraction delay: Memories aren't available instantly (10+ minute delay)
  • No real-time recall: Current implementation extracts but doesn't automatically inject into prompts
  • Token limits: Very long conversations may be truncated for extraction
💡

We're actively improving the memory system. Future updates will include real-time memory recall and more sophisticated memory management.