IGNIS: Traceable maintenance intel & audit reports

Maintenance teams are stretched and their history is hard to trust. In MaintainX's 2025 survey of 1,320 maintenance professionals, 71% called preventive maintenance a core strategy, yet under 35% spend most of their time on it and 58% spend over half their time reacting to breakdowns. The records meant to guide them are often weak: a peer-reviewed 2024 Semantic Web study (Woods et al.) found data-quality issues in 55% of eight years of work orders for one centrifugal pump. Meanwhile, Siemens (True Cost of Downtime, 2024) estimates one hour of unplanned downtime costs a large automotive plant $2.3 million. That is why we built IGNIS: an evidence desk for supervisors and reliability engineers who must turn messy work orders into decisions they can defend. Models propose, code computes and people approve. Users import CSV or Excel exports, confirm column mappings and review AI-suggested components, faults and actions anchored to exact spans of the original text. Approved records form a versioned snapshot. Code calculates counts, priorities and alerts, so numbers stay reproducible. A reviewed asset-and-component graph keeps wrong-model and superseded manuals out of retrieval, and the top passages feed a cited draft with alternatives and uncertainty, or an abstention when evidence is missing. Validators check every citation and numeric binding; an expert signs off before IGNIS can issue an evidence-linked PDF report. IGNIS runs on AMD Token Factory: DeepSeek-V4-Flash-Vision-Exp extracts work-order entities, DeepSeek-V4-Flash drafts cited explanations, and MinerU2.5-Pro reads scanned manuals, behind one rate-aware API gateway with recorded replay. On MaintIE's held-out test split, 105 of 108 extraction outputs were valid. Unlike chat assistants, IGNIS never lets a model set a number or approve a finding, and every claim resolves to a record and passage. The demo labels synthetic, replay and live data; it claims no failure prediction or measured production savings yet.