Questar Adds AI Repair Recommendations to Fleet Maintenance
Questar's updated Total Fleet Health platform can flag likely failures, recommend repairs, and estimate the cost of waiting, with a Geotab Marketplace integration supporting its North America rollout.
Questar Moves From Prediction to Repair Decisions
Questar Auto Technologies is rolling out an updated version of its Total Fleet Health platform in North America, adding AI-driven repair recommendations to fleet maintenance workflows.
The system is designed to do more than warn that a component may fail. It analyzes vehicle and operational data, identifies likely root causes, recommends specific repair actions, and estimates the cost of delaying the work. Questar is positioning the tool for fleets that already have fault-code feeds and telematics data, but need a clearer way to decide what should go into the shop first.
Why Fleets Are Paying Attention
The maintenance math is the hook. Questar says fleets spend about $26,000 per vehicle each year on maintenance, repairs, and downtime. Its data also shows 46% of fleet maintenance is unscheduled or emergency work, with unplanned downtime averaging 8.7 days per vehicle per year.
The company pegs the daily cost of downtime at $760 per day, not including lost revenue, and puts the average emergency service cost at $3,000 per vehicle. Those numbers explain why repair prioritization is becoming a bigger part of fleet software, not just a shop-floor issue.
Geotab Integration Supports Rollout
The latest version is available as a cloud-based platform, paired with Questar hardware, or integrated with existing telematics systems. In North America, Questar has added partnerships including Geotab and Atmus' Fleetguard division.
The platform can add vehicles to a repair queue, track maintenance status, and give managers plain-language explanations of risk. It does not currently use the Vehicle Maintenance Reporting System codes developed by ATA's Technology & Maintenance Council, though Questar says it is exploring how to incorporate them.
For fleets, the useful part is not the AI label. It is whether a system can turn noisy vehicle-health data into a ranked maintenance plan before a roadside failure makes the decision for them.
