Play 58
Digital Twin Agent
Physical system simulation with predictive modeling and anomaly detection.
AI-powered digital twin platform for physical system simulation, predictive modeling, and real-time anomaly detection. Integrates Azure IoT Hub telemetry with Azure Digital Twins for state management and OpenAI agents for natural language scenario testing. Covers manufacturing, energy, and infrastructure domains with optimization recommendations and what-if analysis.
Architecture Pattern
IoT-driven digital twin: AI agent overlay for predictive analysis and optimization
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Digital Twin Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (225 lines), evaluate (125 lines), tune (160 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with ADT URL + OpenAI key inputs + envFile
TuneKit (AI Config)
- config/openai.json — anomaly detection, prediction config
- config/guardrails.json — alert thresholds, simulation bounds
- evaluation/eval.py — Prediction accuracy >85%, Anomaly F1 >0.80
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.