Sentinel: Explainable AI Investigator

Industrial facilities generate massive volumes of telemetry, maintenance records, and technical documentation, yet engineers still spend hours performing manual root cause analysis. Traditional predictive maintenance systems detect anomalies but rarely explain why failures occur, delaying repairs and increasing costly downtime. Sentinel is an explainable AI platform that transforms industrial data into actionable engineering insights. Its Retrieval-Augmented Generation (RAG) pipeline combines telemetry, error logs, and maintenance history from SQLite with semantic retrieval from OEM manuals and historical failures stored in ChromaDB. Instead of generating generic summaries, Sentinel uses Fireworks AI's grammar-constrained JSON generation to produce structured, evidence-backed investigations. Each analysis includes an interactive causal reasoning graph, supporting evidence, confidence-aware root-cause identification, self-validation against conflicting signals, and prioritized maintenance recommendations. Engineers can trace every conclusion instead of relying on opaque AI outputs. Sentinel is production-ready, running in a containerized architecture with Docker, Docker Compose, and Nginx. AI inference is accelerated by AMD Instinct™ MI300X GPUs through AMD Developer Cloud using Fireworks AI, generating complex structured investigations in under 12 seconds. By combining explainable AI, RAG, structured reasoning, and AMD-accelerated inference, Sentinel goes beyond anomaly detection to become an intelligent engineering copilot that helps reliability teams diagnose failures faster, reduce downtime, and make evidence-based maintenance decisions.