create_learning
Create entries in institutional memory to document scars, wins, and patterns from past sessions, enabling AI agents to recall and learn from prior experiences.
Instructions
Create scar, win, or pattern entry in institutional memory. Frame as 'what we now know' — lead with the factual/architectural discovery, not what went wrong. Good: 'Fine-grained PATs are scoped to one resource owner'. Bad: 'Should have checked PAT type first'.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Frame as a knowledge discovery — what we now know. Lead with the factual insight, not self-criticism. | |
| domain | No | Domain tags | |
| project | No | Project namespace (e.g., 'my-project'). Scopes sessions and searches. | |
| keywords | No | Search keywords | |
| severity | No | Severity level (required for scars) | |
| scar_type | No | Scar type (process, incident, or context). Defaults to 'process'. | |
| description | Yes | Detailed description. Include the architectural/behavioral fact that makes this retrievable by domain. | |
| applies_when | No | When this pattern applies | |
| learning_type | Yes | Type of learning | |
| problem_context | No | Problem context (for wins) | |
| counter_arguments | No | Counter-arguments for scars (min 2 required) | |
| solution_approach | No | Solution approach (for wins) | |
| source_linear_issue | No | Source Linear issue |