capture_lesson
Document lessons learned by providing details manually, extracting them from text automatically, or searching existing lessons by keyword.
Instructions
Capture lessons: inline / batch write, or lookup by keyword.
Inline mode (default): provide title, context, problem, solution.
Batch mode: provide text to extract lessons automatically via worker.
Lookup mode: provide find to surface top-ranked existing
lessons whose heading matches the keyword.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| project | Yes | Project slug (directory under 10_projects/). | |
| title | No | Short descriptive title (inline mode). | |
| context | No | What you were doing (inline mode). | |
| problem | No | What went wrong or what decision was needed (inline mode). | |
| solution | No | What fixed it or what was decided (inline mode). | |
| tags | No | Optional tags (e.g. ["python", "testing"]). | |
| text | No | Raw text to extract lessons from (batch mode). | |
| min_confidence | No | Minimum confidence for batch extraction. Default 0.7. | |
| max_lessons | No | Maximum lessons to extract / surface. Default 5. | |
| find | No | Keyword to look up in existing lesson headings (lookup mode). | |
| rank_by | No | Lookup ranking — 'reinforcements' (default), 'confidence', or 'hybrid'. Ignored unless ``find`` is set. | reinforcements |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |