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
- Comp audit self-serve — CSV intake, free validate, commerce-gated watermarked run (HO-155)
- Gift pass — gifted ownership on the entitlement store (magic-link claim)
- JobFrame canonical Job Family × Focus × Level taxonomy + classifier
- SMB pay-system wizard — chocolate/vanilla over the pay-system catalog
- Support channel — portfolio-wide /support form → ticket store → operator email
- Ask-your-data — generalizable NL→rank→tier→cite spoke (HO-378)
- Diagnostic acquisition — next-best-ask over a live hypothesis set
- Executive-Priorities Elicitation Instruments (static catalog)
Capability detail sourced from the People Analytics Toolbox capability feed (source of truth), snapshot retrieved 2026-07-23.