Play 82
Construction Safety AI
High✅ Ready
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
Azure AI VisionAzure IoT HubAzure OpenAIAzure Container AppsAzure Cosmos DB
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
PPE detection confidenceHazard zone definitionsAlert escalation rulesCamera placement strategyIncident severity levels
Estimated Cost
Dev/Test
$100-250/mo
Production
$3K-10K/mo