Building an AI-powered text-and-image compliance monitor: From training to tracking to chat

What happened

Built as an AI quickstart for Red Hat OpenShift AI , it demonstrates how these capabilities come together in a production-grade application that can be used in many monitoring situations. Organizations face a persistent challenge maintaining workplace safety, security, asset tracking, and operational compliance across facilities with multiple video feeds.

Manual monitoring is resource-intensive, inherently reactive, and often misses critical events or patterns indicating safety risks. A single safety officer watching a bank of screens can't reliably track whether every worker on a busy factory floor is wearing their hardhat, vest, and mask—let alone recall compliance trends from last week.

This project tackles that problem with a complete, end-to-end AI monitoring system combining computer vision and large language model (the kind of AI system trained on text to produce text)s (LLMs) into a single platform. It goes beyond simple object detection—it helps train custom models, serves them in real time, tracks people and equipment across video frames, persists relevant data to a database, and lets users query it all through a natural-language chat.