Play 82
Construction Safety AI
Real-time construction site monitoring with PPE compliance and hazard detection.
Real-time construction site monitoring using computer vision for PPE compliance detection, hazard identification, unauthorized zone entry alerts, and safety incident reporting with photo evidence. AI Vision processes camera feeds for PPE and hazard detection, IoT Hub connects site cameras and sensors, OpenAI generates incident reports and safety summaries, Container Apps hosts the real-time processing pipeline, and Cosmos DB stores incident records with photo evidence.
Architecture Pattern
Vision-driven safety: camera feeds - PPE detection - hazard alerts - incident reporting
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Safety Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (213 lines), evaluate (132 lines), tune (278 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with Custom Vision + OpenAI inputs + envFile
TuneKit (AI Config)
- config/openai.json - incident analysis and safety report prompts
- config/safety.json - PPE rules, hazard zones, escalation thresholds
- config/guardrails.json - detection confidence, alert accuracy
- evaluation/eval.py - PPE detection >95%, Hazard identification >90%
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.