Documentation

Setup guides, component architecture and validation methods for the Open Clinical AI projects. Choose a topic below or search the documentation.

Browse by topic

The data we test against — 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 — 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 — 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 — 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 — How the ChartSearchAI relay, med-agent-hub profiles, and optional Querystore source are organized into reviewable OpenMRS upstream contributions.

Component documentation & contracts — Native setup and current contracts from each product owner.
Why local-first clinical AI — The cited evidence behind the mission — offline realities, data sovereignty, right-sized open models, and WHO SMART Guidelines.
Workspace README — The OpenClinAI projects and workspace.
Workspace architecture — Components, independent validation and website publication boundaries.
Background & evidence (research) — Cited global-health grounding: WHO SMART Guidelines, LMIC realities, data sovereignty, open-model right-sizing.
Guardrails methodology (research) — Prompt-injection and unsafe-answer defenses — the safety research behind the harness.

Validation research — Evidence model, evaluation methodology, and the run-manifest traceability spine.
Demo-data profile & cohorts — The May 2026 OpenMRS 2.8 demo-corpus profile: landscape, completeness, and validation cohorts.
Catalyst demos — Query-to-table on two real data sources — watch a two-turn conversation on each.