Intelligent Predictive Maintenance Hackathon
A hands-on workshop that builds a multi-agent predictive-maintenance workflow for a fictitious tire factory using Microsoft Agent Framework, Microsoft Foundry and Azure.
This is a hackathon workshop that teaches how AI agent workflows can support predictive maintenance: faster triage, more consistent diagnosis, and smoother handoffs from detection to repair planning. Using a code-first approach with Microsoft Agent Framework, Microsoft Foundry and Azure, participants build a small multi-agent workflow modeled on a real maintenance process across a fictitious tire manufacturing company.
Participants implement five focused agents, Anomaly Detection, Fault Diagnosis, Repair Planner, Scheduler and Orderer, connect them to data and tools, add persistent agent memory through threads for scenarios where history matters, and instrument the solution to inspect outputs, tool calls, logs and traces during development. The workshop also uses GitHub Copilot, including a custom coding agent, to accelerate development while keeping changes reviewable, and builds an end-to-end workflow hosted in Aspire with agent-to-agent communication.