Intelligence engine
Run governed natural-language analytics using facts-grounded responses.
Last updated:
The Intelligence Engine follows one strict split:
- Facts = truth (deterministic operational data)
- Model = interpretation (summaries, prioritisation, next-step guidance)
For the full current end-user capability list in Chat, see Eden capabilities.
User-facing access
All Intelligence access is session-authenticated in ChannelWeave.
Request lifecycle (high level)
- Validate request shape and bounds.
- Resolve tenant context from the signed-in workspace.
- Gather deterministic facts for the question.
- Return either:
- a direct fact answer (for explicit factual prompts), or
- a model-composed answer grounded in those facts.
- Persist audit metadata for traceability.
Response behaviour
- If required facts are unavailable, Eden returns an explicit uncertainty note.
- If model generation fails, Eden returns a safe deterministic fallback where possible.
- Chat links to in-app pages are rendered as safe clickable links.
- User-facing wording is normalised to British English.
Data safety
- Tenant scoping is enforced for all facts used in responses.
- The assistant does not execute arbitrary user-authored SQL.
- Sensitive operational setup details are documented in SuperAdmin docs only.