Most failed field visits fail before the van leaves: wrong skill, missing part, no access arranged, no history. AI field service management fixes the preparation, and leaves the dispatcher in charge of the plan.
All Telecoms →
A telecom field job draws on several systems at once: the fault ticket, the network inventory, the site record with its access arrangements and hazards, the stock in each van, the engineer’s skills and accreditations, and the customer appointment. Dispatchers reconcile them under time pressure, and the information that would have prevented a repeat visit is often in a free-text note from the last one.
There are two different problems here, and they need two different tools. Reading tickets and notes and writing a clear job brief is a language problem, where a model helps. Building a day’s schedule across hundreds of jobs, skills and travel times is an optimisation problem, where a constraint solver does far better than any language model. We use each where it is strong.
from the NOC, care or a planned order
history, likely fault, parts, hazards
skills, permits, access, stock
solver proposes, dispatcher approves
brief on the mobile app, notes captured
missing permit, part or access
It is the use of models to prepare, schedule and support field work: summarising ticket and site history into a job brief, predicting the likely fault and parts, matching skills and permits, and optimising schedules. The most effective systems combine a language model for the reading and writing with a constraint solver for the scheduling, and leave dispatchers able to override.
No. It works with the platform you run, such as ServiceNow Field Service Management, Salesforce Field Service, IFS, Oracle Field Service or Microsoft Dynamics 365 Field Service. It reads tickets and inventory and writes briefs and proposed schedules back, so engineers keep using the same mobile app.
Scheduling many jobs against skills, time windows and travel is a mathematical optimisation problem. A constraint solver handles it reliably and can explain its plan; a language model cannot. We use language models only for the parts that are about understanding text, such as job notes and briefs.
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.
Start with a month of repeat visits. We will show what the brief would have said before the first one.
30-minute technical call · no deck