docs(ai/lab): add LESSONS_LEARNED.md on knowledge kinds, memory analogy, and the context/harness stack#15
Merged
Conversation
…gy, and the context/harness stack Captures the resolved design question of why ai/lab/ belongs in a knowledge repo: ai/ holds descriptive knowledge (regenerable map: guide/, analysis/) and intentional knowledge (irreplaceable decisions/lessons: lab/). Replaces the central-nervous-system analogy with a memory-systems mapping, and documents how memory, context, context engineering, and harness engineering interlock in this kit. Indexed in ai/INDEX.md and ai/lab/README.md. All content tagged [inferred] pending human audit. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01948Gdi8Pu6RBLPa82sPSEB
…ab/ matters in README Relocate the lessons doc to ai/lab/lessons-learnt/ as a dated file (matching the evaluations/ naming convention) and repoint the ai/INDEX.md and ai/lab/README.md rows. Add a 'Why this folder matters' section to the lab README: lab/ is the only part of ai/ that cannot be regenerated from code — it records reasons, not facts. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01948Gdi8Pu6RBLPa82sPSEB
… its conventions Move the knowledge-kinds/memory/context/harness lesson out of ai/lab/ into docs/dev/lessons-learnt/ alongside the existing lessons, adopting the folder's conventions (kebab-case topic filename, Metadata table with Timestamp and Category). Repoint ai/INDEX.md and the ai/lab/README.md rationale link, drop the transient lab table row, and list the new lesson in docs/README.md. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01948Gdi8Pu6RBLPa82sPSEB
There was a problem hiding this comment.
Pull request overview
This PR documents (in docs/) the resolved design rationale for keeping ai/lab/ inside the repo’s knowledge layer, framing ai/ as “memory + harness” and clarifying how memory, context, context engineering, and harness engineering relate in this kit. It also wires that lesson into existing indexes so it’s discoverable during planning/review.
Changes:
- Add a new lesson document explaining “descriptive vs intentional” knowledge and the memory/context/harness stack.
- Link and index the new lesson from
docs/README.md,ai/lab/README.md, andai/INDEX.md.
Reviewed changes
Copilot reviewed 4 out of 4 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| docs/README.md | Adds the new “two kinds of knowledge” lesson to the docs navigation. |
| docs/dev/lessons-learnt/knowledge-kinds-memory-context-and-harness.md | New lesson write-up capturing the design rationale and the memory/context/harness model. |
| ai/lab/README.md | Adds an [inferred] rationale section for why ai/lab/ matters and links to the lesson doc. |
| ai/INDEX.md | Extends the role→path manifest to include the lessons-learned docs location. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Captures the resolved design question of why ai/lab/ belongs in a knowledge
repo: ai/ holds descriptive knowledge (regenerable map: guide/, analysis/)
and intentional knowledge (irreplaceable decisions/lessons: lab/). Replaces
the central-nervous-system analogy with a memory-systems mapping, and
documents how memory, context, context engineering, and harness engineering
interlock in this kit. Indexed in ai/INDEX.md and ai/lab/README.md.
All content tagged [inferred] pending human audit.
Co-Authored-By: Claude Fable 5 noreply@anthropic.com
Claude-Session: https://claude.ai/code/session_01948Gdi8Pu6RBLPa82sPSEB