Overview
Spinnable AI workers learn and improve through two complementary systems:- Conversational Refinement - Real-time learning during interactions
- Long-term Memory - Persistent knowledge that carries across conversations
Conversational Refinement
How It Works
During a conversation, workers learn from:- Corrections you provide
- Clarifications you offer
- Preferences you express
- Context you share
Example
Limitations
- Learning persists only within the current conversation
- Resets when you start a new conversation
- Best for immediate corrections and session-specific preferences
Long-term Memory
What Gets Remembered
Workers store important information in their memory knowledge base:Personal Preferences
Personal Preferences
- Communication style preferences
- Favorite tools and formats
- Decision-making criteria
- Work schedule and availability
Work Context
Work Context
- Team structure and roles
- Project backgrounds
- Company policies
- Standard procedures
Domain Knowledge
Domain Knowledge
- Industry-specific terminology
- Technical specifications
- Best practices
- Historical decisions and rationale
Task Patterns
Task Patterns
- How you like tasks completed
- Common workflows
- Quality standards
- Exception handling
How Memory Is Created
1
Worker Identifies Important Information
During conversations, the worker recognizes potentially valuable information worth remembering.
2
Memory Proposal
The worker asks: “Should I remember this for future conversations?”
3
Your Confirmation
You approve or decline the memory suggestion.
4
Memory Storage
Approved information is stored in the worker’s knowledge base.
Memory in Action
First Conversation:Memory Management
Viewing Memories
Access your worker’s stored memories through:- The Knowledge Base section in worker settings
- Direct request: “What do you remember about me?”
Updating Memories
Memories can be modified when circumstances change:Deleting Memories
Remove outdated or incorrect information:- Manually through the knowledge base interface
- By asking: “Forget my preference about [topic]“
Best Practices
Be Explicit
Clearly state when information should be remembered long-term vs. just for the current task.
Confirm Memory Saves
When the worker asks to save information, confirm to ensure important preferences are retained.
Regular Reviews
Periodically review stored memories to keep them current and relevant.
Provide Context
Help workers understand why something matters for better memory decisions.
Privacy & Control
Your Rights
- Full visibility into all stored memories
- Edit access to modify any memory
- Delete capability for any stored information
- Approval required before new memories are created
Data Handling
- Memories are specific to each worker
- Information is encrypted and secured
- You can export or delete all memories at any time
- Memories are only used to improve your worker’s assistance
Common Questions
How long do memories last?
How long do memories last?
Memories persist indefinitely until you remove them or the worker suggests an update due to changed circumstances.
Can workers remember everything from our conversations?
Can workers remember everything from our conversations?
No. Workers selectively identify important, reusable information. Routine task details aren’t automatically stored.
What if a worker remembers something incorrectly?
What if a worker remembers something incorrectly?
You can correct any memory at any time. Simply point out the error, and the worker will update its knowledge base.
Do memories transfer between workers?
Do memories transfer between workers?
No. Each worker maintains its own knowledge base. However, you can manually share relevant information with other workers.
How many memories can a worker store?
How many memories can a worker store?
There’s no practical limit. Workers efficiently organize and retrieve information regardless of quantity.