Telematics tells you a great deal about every vehicle. The work is turning fault codes, mileage and defect reports into a list of what to fix, when, and what should not leave the yard today.
All Automotive & Mobility →
AI for fleet management means using models on telematics, maintenance and driver-reported data to plan servicing, triage defects, predict likely failures and keep compliance records current. Platforms such as Samsara, Geotab and Webfleet already collect the data; what most fleets lack is the layer that combines it with workshop history and turns it into the next decision.
We build that layer on top of what you have. Fault codes are read with the vehicle’s service history and the manufacturer’s bulletins, walkaround defect reports are classified, and a weekly plan proposes which vehicles go to the workshop, in what order, given parts and bay capacity. For electric fleets, charging and battery health data join the same picture.
Compliance sits in the same data. Tachograph and drivers’ hours rules (Regulations (EU) 165/2014 and 561/2006), roadworthiness inspections and operator licence obligations all leave records that can be checked continuously rather than at audit.
fault code, walkaround, mileage
runs first
history, bulletins, parts
against workshop capacity
written to the maintenance system
possible safety defect
For maintenance planning, predicting likely failures from fault codes and history, triaging driver-reported defects, routing and utilisation, fuel and charging analysis, and compliance tracking. Most of the data already exists in telematics and workshop systems. AI adds the reasoning that combines it into a recommendation a fleet manager can approve or change.
It can estimate which vehicles are likely to need work soon from fault codes, mileage, duty cycle and repair history, and it improves as your own history grows. It will miss some failures and flag some vehicles that are fine, so we validate it against your past repairs before use and keep the fleet manager deciding what goes off the road.
Monitoring is not banned, but AI that monitors and evaluates workers’ behaviour for decisions about their employment is classed as high-risk, with duties on oversight, transparency and documentation, alongside GDPR and, in many countries, works-council consultation. We design driver data for coaching and safety, not automated discipline. Your legal assessment of your use is yours to make.
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
We start with a few months of your telematics and workshop data, and backtest what the plan would have said.
30-minute technical call · no deck