Sentin8:AI — Platform AI Capability Layer
AI with the same authorization discipline as everything else: embeddings, chat, completions, and document ingestion behind Shield scopes and tenant isolation. Per-env configuration, tenant-authored knowledge bases, and audit on every call.
Use cases
- Semantic search — embed documents per tenant; queries retrieve only that env's vectors.
- Assistants — chat surfaces in vertical apps (teller support, front-desk guest help) call the platform's AI through the BFF with user tokens.
- Document intelligence — ingestion pipelines chunk, embed, and index uploads from Sentin8:Storage.
API surface
| Endpoint | Method | Gate |
|---|---|---|
/v1/health | GET | none |
/v1/embed | POST | Shield sentin8:ai:embed |
/v1/chat | POST | Shield sentin8:ai:chat |
/v1/documents | POST/GET | Shield sentin8:ai:documents:write |
/v1/documents/{id} | DELETE | Shield sentin8:ai:documents:write |
Full documentation
The complete detail lives in this product's sub-pages:
- Architecture (DDD) — the full document, harvested from the unit's repository at build time.
- Business rules (BRD) — the full document, harvested from the unit's repository at build time.
- Security — the full document, harvested from the unit's repository at build time.
- Overview (repo README) — the maintainer's README in the consolidated reference section.