Everyone is building agents. In industrial operations and process safety — where software output can end up in a regulatory filing or a court exhibit — we found that the properties that make an architecture agentic are the same ones that make it unauditable. Free tool selection, opportunistic replanning, and self-narrated reasoning produce results you can't reproduce, bound, or defend six months or 3 years later. This talk covers what we built instead: a gate-controlled pipeline where LLMs do bounded extraction and judgment inside fixed contracts, and orchestration stays deterministic. I'll walk through the principles that survived contact with real customer deployments in refining and chemicals — fail-closed over fail-open, absence of a verdict is not trust, provenance over self-attestation, no arithmetic across unknown states — and show how each one cashes out in concrete engineering: sealed execution manifests, evidence binding with full source provenance, and a reproducibility guarantee scoped precisely to the generative step rather than hand-waved across the whole system. I'll also cover the trade-offs honestly: what we gave up, where agentic patterns still earn their place, and why small models handle far more of this work than we expected — with the cost implications that follow.
Ivo Dujmovic is Co-Founder and CEO of uc2c.ai, where he is building HazNav, an AI-native operational intelligence platform for high hazard industries like refining, chemicals, and oil and gas. He volunteers on the CCPS Technical Steering Committee and its subcommittee on AI in process safety. Previously he worked on enterprise data and AI systems at C3.ai, Interana, Datacoral, and Oracle. He holds a B.S. in Computer Science and Mathematics from Yale and an MBA from Wharton.
