Play 65
AI Training Curriculum
Adaptive learning platform with personalized exercises and micro-certifications.
Personalized AI-powered learning platform that assesses learner knowledge through diagnostic evaluations, generates custom exercises calibrated to skill level, provides instant detailed feedback, and tracks progression across competency maps. The curriculum engine dynamically recommends next modules based on demonstrated mastery and issues micro-certifications upon competency thresholds. Built on Static Web Apps for the learner portal with Cosmos DB tracking individual learning paths.
Architecture Pattern
Adaptive assessment: competency-gated progression, generative exercises, micro-certs
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Curriculum Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (245 lines), evaluate (109 lines), tune (187 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI key input + envFile
TuneKit (AI Config)
- config/openai.json — gpt-4o for exercise generation and feedback
- config/guardrails.json — responsible AI, educational accuracy
- evaluation/eval.py — Progression rate >70%, Assessment validity >85%
Tuning Parameters
Machine evidence
FrootAI evidence lifecycle
This is an internal evidence maturity label, not third-party certification, accreditation, legal compliance, or a production guarantee. Missing or expired evidence demotes automatically; catalog claims cannot promote a play.
This play currently has design evidence only. A runnable scenario, endpoint evaluation, and build receipts are the next contiguous gates.
Repo Intelligence
v1A no-clone, revision-pinned map for agents and humans. Observed evidence is separated from inferred flow so the output stays useful without pretending to be a full call graph.