Reference — generated from the toolkit

Source of truth: toolkit/training/README.md. Edit it there; this page is regenerated on build.

Training

One umbrella curriculum with modules per role — not ten separate courses. Practical labs against the RAPID project scaffold, with a graded exercise.

Scaffold — modules are authored in the enablement pass (TASKS.md §6 "Role-based training curriculum"). Planned modules:

• Directing agents (developers)
• Spec-writing for agents (PO / BA)
• Expressing rules as decision tables (SMEs)
• Reviewing AI-generated code and tests (devs / testers)
• Design-agent direction (design)
• Security failure modes of generated code
• Support handover
• "Running STOP with agents" — the first module delivered, because STOP is the safe training ground for the direct / review / govern muscle.
• Common foundation: responsible AI use (EU AI Act Article 4 AI-literacy).