peopleanalyst

Platform · Shipped

Zero-LLM-serving guarantee — CI-enforced, publicly verifiable

Every runtime AI import site is declared in a manifest with a fallback posture; CI (check:runtime-llm + runtime-llm-guard.yml) fails undeclared sites, stale entries, or serving paths without a fallback. hardDependencies is EMPTY (compiled plan + walk-back libraries serve the intent-router family deterministically). Published as the servingLlm field on GET /api/registry so buyers verify instead of trusting.

Cluster
Platform
Type
standard
Status
Shipped
Used by
people-analytics-toolbox, peopleanalyst-site

Maturity evidence

Functioning
Live 2026-07-02: guard green in CI, servingLlm.hardDependencies=[] verified on prod apex; trust page renders the live feed.
Valuable
The procurement/security-review differentiator (THE-HILL-WE-DIE-ON made enforceable); trust page is the sales asset.
Understood
BUILD-TIME-AI-PLAN.md doctrine + manifest _doc + trust page explain it at three altitudes.
Integrated
CI on every PR/push; registry feed consumed by pa-site trust page (ISR hourly).

How to use it

REST
/api/registry (servingLlm)
CLI
npm run check:runtime-llm
Data
src/lib/ai/runtime-llm-manifest.json

Other Platform capabilities

← Every platform capability

Capability detail sourced from the People Analytics Toolbox capability feed (source of truth), snapshot retrieved 2026-07-23.