Coldwater Board of Public Utilities Deploys eSmart Systems Grid Vision for AI-Powered Grid Inspection

Title

Coldwater Board of Public Utilities Deploys eSmart Systems Grid Vision for AI-Powered Grid Inspection

Content

The Coldwater Board of Public Utilities (CBPU) — a Michigan municipal utility serving electric, water, wastewater, garbage and recycling, and telecommunications to Coldwater since 1891 — has deployed eSmart Systems' Grid Vision AI-enabled platform for distribution grid inspection and asset management, scaling from a proof of concept covering approximately 100 assets across two distribution feeders to an architecture validated to handle roughly 16,000 assets across the utility's full distribution system without adding headcount. Utility Director Paul Jakubczak described the operational shift in concrete terms: "If you drive by a pole, you're not going be able to see what's on top. By using this technology and our drone, we're able to gather all these different images and then analyze them back at the office to decide what work orders need to be made." He framed the deployment as a customer-experience investment: "If this helps to eliminate even one outage, it's well worth that. Especially from a customer perspective." CBPU had historically relied on manual walkthroughs, paper records, and inconsistent visual checks across its poles, conductors, switches, and ground-level components. Without structured visual records, the utility could not trend asset degradation over time or catch developing defects before they caused outages — and brief outages have outsized impact in a small city. The utility began evaluating AI for structural monitoring in 2023 and launched a pilot in 2024, integrating the eSmart platform into its existing work order management rather than running it as a parallel system. The pilot began as a focused POC across two feeders. CBPU and eSmart Systems used a train-the-trainer implementation model — eSmart staff worked directly with CBPU personnel through each phase of the inspection workflow, building internal competency step by step. After validating that a team of CBPU's size could operate AI-supported drone inspection workflows without additional headcount, the POC converted into a five-year SaaS agreement with eSmart Systems — a $248,000 contract approved by the CBPU board on December 3, 2025. The deployment uses eSmart Systems' Grid Vision platform with drone imagery ingested into an AI defect-detection model; each flagged finding is reviewed by trained analysts before action, creating a structured visual asset repository where every pole, component, and ground asset has a linked image, condition assessment, and recommended action. Recommendations feed directly into CBPU's existing work order management, forming a closed loop from imagery capture to maintenance dispatch. Jakubczak explained the integration: "We worked with them on generating a 5-year agreement where we'll continue to upload these images to them. And then their software will take pictures and start doing predictive maintenance by prioritizing what they've found." A contributed case study in Renewable Energy World by eSmart Systems VP of market development Donald McPhail added that drone footage identified an open-wire secondary with a broken neutral wire that CBPU would otherwise not have found until customers reported it — the utility dispatched a crew that afternoon to repair it. The initial POC inspected approximately 100 assets across two feeders and is now architected to scale to approximately 16,000 assets across CBPU's full distribution system. The five-year SaaS program covers the electric, water, wastewater, garbage and recycling, and telecommunications infrastructure that CBPU has operated for Coldwater since 1891. Jakubczak framed the cost rationale: "you can see its lower cost compared to the cost of hiring someone to constantly do line inspections." Reported in a January 2026 Public Power magazine interview with Jakubczak and detailed in an April 2026 contributed case study by Donald McPhail, the deployment is positioned as a replicable blueprint for the hundreds of similarly constrained municipal utilities and electric cooperatives nationwide — demonstrating that AI-enabled inspection is no longer the exclusive domain of large investor-owned utilities with enterprise budgets and dedicated innovation teams.