Data and AI processing

What Praxis sends to models, and what it does not do with that information.

Praxis can draft evaluation sections, goal language, and service recommendations from evidence the therapist has entered or confirmed. Generation is bounded by the current evaluation context. Unconfirmed or rejected prior-report extractions are excluded.

When a live model is connected

If an AI provider key is configured on the server, selected evaluation context is sent to that provider to produce a draft. Provider keys stay server-only. The application does not use student records to advertise a certified clinical model, and it does not claim that drafts are independently verified facts.

When no live key is configured

The labeled sample workspace uses a deterministic mock provider and does not present mock output as a live-model result. Authenticated live accounts do not fall back to mock generation.

Guardrails

Drafts are checked so entered scores are not rewritten, missing scores are not invented, missing baselines are not fabricated, suggested targets stay labeled, and service rationale does not silently invent frequency or duration. Diagnosis, eligibility determinations, and claims that occupational therapy is legally required are blocked.

Human review

Therapists review, edit, approve, and finalize. Exporting a PDF records an audited export.Praxis does not submit documents to a district IEP system.