We watch the reviewer. Not the sensor.
Sovel is a reviewer-operated knowledge-risk detection and governance workspace for industrial maintenance. We read the work-order narrative, the shift log, and the operator chat — and tell a named human reviewer which closures don't have the evidence they need to hold up under audit.
What Sovel is
- CMMS-adjacent. We sit on top of Maximo, SAP PM, AiM, AMOS, the spreadsheet your planner actually uses. We do not replace any of them.
- Detection-first. We surface closures that look fine in the CMMS but have no evidence anchor — repeat failures, prerequisite-readiness gaps, shift-handover holes, operator overrides nobody captured.
- Knowledge-governance-first. Every governed artifact carries provenance, an evidence anchor, and a full audit trail. Designed for OSHA PSM 1910.119, NERC CIP-010-4, 21 CFR Part 11, MSHA Part 50/56, IMO ISM Code, and the regulators that follow.
- Reviewer-primary. AI drafts. Reviewers approve. No autonomous writes to governed truth, ever. The architecture is the moat.
What Sovel is not
- Not a CMMS replacement.
- Not a generic chatbot or search-over-PDFs product.
- Not a connected-worker / workforce / HR tool.
- Not an autonomous-agent vendor that promises closed-loop control.
Ben Klement
Background spans operations research, industrial systems engineering, and hands-on time with reviewers in PSM-, NERC-, and FDA-regulated facilities. The product is shaped by a single rule: nothing ships if it would let an unsupervised model write a regulated record.
Reach out: bklement@usesovel.com · book 20 minutes on Cal.com
Where we are
Pre-pilot. The reviewer app and the gap engine are in active build under design partners; the first paid pilots open as the evaluation harness graduates from synthetic to customer data. If you operate a regulated industrial facility and you've ever closed a work order that you knew lacked the supporting evidence — we want to talk.