docs: split README into operational guide + docs/design.md essay#2
Merged
docs: split README into operational guide + docs/design.md essay#2
Conversation
- README cut to its operational core (786 -> 384 lines): features,
prereqs, getting-started, CLEARS, configuration, testing, deployment,
layout, limitations. Lead now points to docs/design.md and runbook.md.
- New docs/design.md holds the essay material: why this exists, the
four architecture diagrams, the Spec-Kit + Claude Code three-pillars
story, the chicken-egg deploy-ordering walkthrough, and "what you can
learn from this repo."
- Minor copy edits in specs/001-doc-intel-10k/{quickstart,research,plan}
to drop vague hedges ("under 30 minutes" -> matches actual 15-25 min
estimate; "improving relevance materially" -> concrete claims).
- docs/_social_preview.py + regenerated docs/social-preview.png: arch
line now ends "eval-gated cited agent" (was "cited agent on Mosaic AI",
which redundantly repeated the DATABRICKS eyebrow). Surfaces the CLEARS
gate as the agent's distinguishing trait.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
docs/design.mdfor the essay anddocs/runbook.mdfor day-2 ops.docs/design.md(355 lines) holds the essay material: why this exists, the four architecture diagrams, the Spec-Kit + Claude Code three-pillars story, the chicken-egg deploy-ordering walkthrough, and what you can learn from this repo.specs/001-doc-intel-10k/{quickstart,research,plan}.md— drop vague hedges: "in under 30 minutes" → matches the actual 15–25 min estimate; "improving relevance materially" → concrete claims about top-5 ordering.docs/_social_preview.py+ regenerated PNG: architecture line now ends "eval-gated cited agent" (was "cited agent on Mosaic AI", which redundantly repeated the DATABRICKS eyebrow). Surfaces the CLEARS gate as the agent's distinguishing trait.Why split?
The pre-split README was doing two incompatible jobs: an essay (motivation, architecture, build workflow) and an operational guide (prereqs, getting started, configuration, deployment). A reader in "I want to deploy this" mode had to scroll past 145 lines of architecture diagrams; a reader in "teach me the pattern" mode hit
databricks auth loginmid-narrative. The TOC papered over the genre clash without fixing the flow.Test plan
docs/design.mdfrom the README header pointer; confirm internal anchors resolve and cross-links torunbook.mdworkdocs/social-preview.pngrenders with the updated architecture line (1280×640)🤖 Generated with Claude Code