Skip to content

docs(ai/lab): add LESSONS_LEARNED.md on knowledge kinds, memory analogy, and the context/harness stack#15

Merged
kunalsuri merged 3 commits into
mainfrom
claude/ai-repo-architecture-design-sex1nt
Jul 3, 2026
Merged

docs(ai/lab): add LESSONS_LEARNED.md on knowledge kinds, memory analogy, and the context/harness stack#15
kunalsuri merged 3 commits into
mainfrom
claude/ai-repo-architecture-design-sex1nt

Conversation

@kunalsuri

Copy link
Copy Markdown
Owner

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

claude added 3 commits July 3, 2026 05:53
…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
Copilot AI review requested due to automatic review settings July 3, 2026 06:02

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

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, and ai/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.

@kunalsuri kunalsuri merged commit e2b7a4e into main Jul 3, 2026
9 checks passed
@kunalsuri kunalsuri deleted the claude/ai-repo-architecture-design-sex1nt branch July 3, 2026 06:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants