A case study contributed by Donald McPhail, VP of market development at eSmart Systems, and published by Renewable Energy World states that the Coldwater Board of Public Utilities (CBPU) in Michigan began with a Grid Vision program covering approximately 100 assets across two distribution feeders, and that the architecture is now validated to scale to approximately 16,000 assets across its full distribution system without requiring additional staff. That proof of scalability converted the proof of concept into a five-year SaaS program, and CBPU is now in a multi-year engagement with eSmart Systems. Engineering Manager Andrew Cameron said Grid Vision gave CBPU "a clearer picture of our system and a practical path to modernizing inspections". CBPU is a municipally owned utility that has served Coldwater since 1891, providing electric, water, wastewater, garbage and recycling, and telecommunications services. It operates with a lean team and a distribution network that includes aging assets, and even brief outages have an outsized impact in a small city. Its inspections relied on manual walkthroughs, paper records and inconsistent visual checks, which left gaps in asset visibility, no structured digital record of asset condition, no systematic way to prioritize maintenance by defect severity, and no reliable link between field observations and workforce dispatching. The utility needed a way to modernize inspections without hiring additional staff or committing large upfront capital. CBPU partnered with eSmart Systems to deploy Grid Vision, an AI-enabled platform for distribution grid inspection and asset management, starting with a proof of concept across two distribution feeders. Drone imagery captured by CBPU's own staff and partner field resources is analyzed with AI-supported defect detection, and each flagged finding is reviewed by trained analysts before it is actioned. The output is a structured visual asset repository in which every pole, component and ground asset inspected has a linked image record, a condition assessment and a recommended action. Those recommendations feed into CBPU's existing workforce management tools, creating a closed loop from imagery capture to maintenance dispatch, so staff can move from a drone image to a prioritized work order without switching between disconnected systems. Implementation used a train-the-trainer model in which eSmart Systems staff worked directly with CBPU personnel through each phase of the inspection workflow. According to the article, the proof of concept showed that a team of CBPU's size could operate AI-supported drone inspection workflows without adding headcount. CBPU is using Grid Vision as the foundation for ongoing inspection, maintenance prioritization and grid planning.