Prism — AI Course Authoring

Prism powers every AI capability in LucentSkill. It generates structured course content from a plain-English brief, drafts reusable content-library blocks, auto-generates survey questions, and turns raw survey responses into an enterprise skill-gap vector.

Prism never executes code — code blocks it produces are illustrative only — and it is constrained to workplace AI upskilling (strategy, engineering, productivity).

• Course Authoring Studio: describe goals, target roles, and key concepts; Prism generates a full lesson with rich visuals (charts and diagrams, planned by a dedicated visual pass), tables, callouts, worked examples, inline knowledge-check questions, and exactly two graded exercises, self-validated before the admin sees them.
• Content Library: describe a section or exercise in one sentence; Prism writes the structured block.
• Survey questions: give a topic; Prism generates assessment questions.
• Synthesis: Prism reads survey responses and extracts concrete skill gaps, rated by urgency and mapped to a track.

Prism runs automatically when an admin uses any AI feature. It requires the platform AI key configured in the environment. No per-user setup is needed.

By default Prism uses the platform key and model. An org can instead bring its own OpenAI-compatible endpoint — see Bring Your Own Model.

OPENROUTER_API_KEY=sk-or-...       # platform AI key (required)
PRISM_MODEL=meituan/longcat-2.0     # model used by Prism generation
GRADING_MODEL=openai/gpt-4o-mini   # model used by exercise grading

• All user input is guarded against prompt injection and off-topic requests before any model call (lib/guard.ts).
• User data is delimiter-isolated so it is treated as data, never as instructions.
• Model output is schema-validated (Zod) and sanitized (stored-XSS + PII scrub) before it is persisted or shown.
• Every failure path is a structured, non-throwing return — the UI degrades gracefully if the key is missing or the model misfires.