AI 智能体 feature-store 更新于 2026-10-02

Feature Store 工程规则

Feature store rules: point-in-time correctness and train/serve parity

✓ 应当这么做

✓ Version datasets and pipelines together so a model and its inputs are traceable
✓ Validate schema and null-rate drift on every ingestion run
✓ Write idempotent transformations that can be re-run safely

42 篇

Vector search rules: chunking strategy, recall evaluation and index rebuild path

Skill design rules: narrow triggers, explicit boundaries and verifiable outputs

Tool-call rules: server-side authorisation and deny-by-default allow-lists

Memory rules: scoped retrieval, expiry and user-visible deletion

RAG rules: citation-grade retrieval and evaluated recall before shipping

Eval rules: versioned prompt datasets and regression gates in CI