Play 68
Predictive Maintenance AI
IoT-driven equipment failure prediction with RUL estimation and maintenance scheduling.
Predictive maintenance platform that ingests IoT sensor data via Azure IoT Hub, applies anomaly pattern recognition through Stream Analytics, and uses Azure Machine Learning for remaining useful life (RUL) estimation. GPT generates maintenance window optimization recommendations, spare parts forecasts, and technician dispatch priorities. Built for manufacturing, energy, and infrastructure verticals where unplanned downtime costs millions.
Architecture Pattern
IoT streaming: ML-based RUL prediction, anomaly detection, AI maintenance scheduling
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Maintenance Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (235 lines), evaluate (111 lines), tune (169 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + IoT Hub inputs + envFile
TuneKit (AI Config)
- config/openai.json — gpt-4o for recommendations, mini for sensor triage
- config/guardrails.json — reliability focus, alert thresholds
- evaluation/eval.py — RUL accuracy >85%, False alarm rate <10%
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.