# Open Clinical AI documentation

> Setup guides, component architecture, validation methods and cited research.

## Docs
- [Component documentation & contracts](/openclinai.org/spec/specs/background/component-contracts.html): Native setup and current contracts from each product owner.
- [Why local-first clinical AI](/openclinai.org/spec/specs/background/why-local-first-clinical-ai.html): The cited evidence behind the mission — offline realities, data sovereignty, right-sized open models, and WHO SMART Guidelines.
- [Workspace README](/openclinai.org/spec/README.html): The OpenClinAI projects and workspace.
- [Workspace architecture](/openclinai.org/spec/specs/architecture.html): Components, independent validation and website publication boundaries.
- [Background & evidence (research)](/openclinai.org/spec/specs/artifacts/planning/global-health-ai-background-research-2026-06-14.html): Cited global-health grounding: WHO SMART Guidelines, LMIC realities, data sovereignty, open-model right-sizing.
- [Guardrails methodology (research)](/openclinai.org/spec/specs/artifacts/planning/guardrails-methodology-research.html): Prompt-injection and unsafe-answer defenses — the safety research behind the harness.

## Canvases
- [Validation research](/openclinai.org/canvas/specs/artifacts/canvases/validation-research.html): Evidence model, evaluation methodology, and the run-manifest traceability spine.
- [Demo-data profile & cohorts](/openclinai.org/canvas/specs/artifacts/canvases/demo-data-profile.html): The May 2026 OpenMRS 2.8 demo-corpus profile: landscape, completeness, and validation cohorts.
- [Catalyst demos](/openclinai.org/canvas/specs/artifacts/canvases/catalyst-demos.html): Query-to-table on two real data sources — watch a two-turn conversation on each.

## Topics
- [The data we test against](/openclinai.org/topic/data-corpus.html): A realistic 5,284-patient OpenMRS demo corpus, modernized from the public 2.7 demo and bound to the CIEL clinical terminology — so validation runs against believable charts, not toy fixtures.
- [Evidence, evaluation & traceability](/openclinai.org/topic/evidence.html): How an AI answer is judged: scored against the patient chart, every claim traceable to a specific record, recorded on a run-manifest provenance spine — directional evidence, not a leaderboard.
- [Safety & governance](/openclinai.org/topic/safety-governance.html): Guarding against unsafe answers, and the change-control discipline (validator audits, PCCP-style records) that keeps validation baselines reviewable.
- [Catalyst — query-to-table for lab and program data](/openclinai.org/topic/lab-ai.html): Technical examples of source context, advisory query review, explicit execution and saved results in Catalyst. Recorded examples retain their own deployment dates; current capabilities and walkthroughs are described on the Catalyst project page.
- [Upstream & compatibility](/openclinai.org/topic/upstream.html): How the ChartSearchAI relay, med-agent-hub profiles, and optional Querystore source are organized into reviewable OpenMRS upstream contributions.