Files

T

jackyu66gitandCursor 2fb1dfee14 chore: seal Design Vision v1 and monorepo scaffold

Archive the differentiated YuXinGu product docs, AI engineering system,
design contract, and Go/Vue scaffold. Next execution prioritizes Cece-parity
over early innovation (see .ai/product/STRATEGY.md).

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-08-02 16:00:44 +08:00

1.3 KiB

Raw Blame History

AI System Evolution Roadmap

Do not build everything at once. Rules have maintenance cost.

Phase 1 — Now (shipped)

Rules: constitution, architecture, domain, coding, api, database, ui, …
ADR, patterns, examples, playbooks
Review / DoD / checklists / forbidden / commands / workflow / file-map
ai-contract.md
Cursor runtime: .cursor/* → symlink → .ai/ (no content copy)

Invest next engineering time in: polishing patterns/, examples/, playbooks/ while building real features — not more rule files.

Phase 2 — When the codebase grows

Add only when pain appears:

Item	Why wait
`anti-patterns/`	Useful after real mistakes accumulate
`metrics.md`	Numbers matter once CI exists
`quality-gates.md`	Wire when lint/test gates are real
`memory/` (known-bugs, tech-debt, todo)	Fill from actual incidents

Phase 3 — Multi-agent / heavy automation

Item	Why wait
`graph/domain.yaml`	Knowledge graph for relation reasoning
`mcp/*.json`	Structured context servers
`skills/<feature>/`	Packaged feature kits (login, payment, …)

Markdown remains human-readable; JSON/YAML for machines — introduce when agents > 1 or retrieval latency hurts.

Rule of thumb

If adding a rule file does not prevent a repeated AI failure this week, do not add it.

1.3 KiB Raw Blame History