Picture a technician who answers the same 33 questions on every visit, even when most don't apply. They learn to tap through on autopilot, and sooner or later the row they tap past is the safety check. This is more of a design problem than a training one. FieldOps, an app for technicians who install home EV chargers, shows how AI-first design can solve it.
One form for every job
FieldOps is a concept app we designed for technicians who install home EV chargers. The screens are a design study, not a running build.
A standard form gives every visit the same 33 questions across four screens. A newer house with power to spare gets the same form an older house with its power almost maxed out receives, even though most questions apply to only one of them.
The technician works multiple homes, with one hand on the phone and the other on the job. Each row that doesn't apply to the job still gets read, ruled out and tapped past. Designers call that cognitive load. The homeowner sees it as a slow visit.
The question that matters most, whether the house can safely handle a charger, sits on page 3, styled like every row around it. Don Norman wrote that human error is usually a result of poor design. Page 3 is a textbook case.
Let the software do the sorting
AI-first UX/UI design starts from one rule: the software adapts, so the person doesn't have to. FieldOps reads what it knows about the job, then asks only what this visit needs.
On a routine job (a newer house with power to spare), that's four questions. Four taps, no scrolling, phone back in a pocket.
What happens in an older home
- The technician enters panel size. This info determines the rest.
- The app sees the power is almost maxed out. A charger could overload the panel, so the screen shifts to amber.
- Safety moves to the top and locks. The checklist from page 3 now comes first, and the rest of the form opens once it's done.
- A supervisor is asked to approve. The app sends the request automatically, so the technician can keep working.
This job takes about as long. It gains a step the old form never had. What changed is order: the question that could hurt someone comes first, and can't be tapped past.
The routine job gets less to do. The risky job gets less to hunt for, and one thing it can't skip.
Old principles, applied per job
These principles are well established. Progressive disclosure means showing what the moment needs and holding back the rest. That's the routine job. Error prevention, the fifth of Nielsen's usability heuristics, says the best designs prevent problems from occurring in the first place.
The hard part has always been the sorting. The technician completed all of the questions manually, regardless of job type. Now AI can make that call for each job, in the moment.
The rule we held to: the adaptation changes what's on the screen, never how the screen works. Layout, buttons and navigation stay where the technician expects them.
A person still approves the risk
In the concept, the AI shapes the screen, but a supervisor signs off on the panel before the lock opens.
Any model can be wrong. It can be built to return only a clean answer, routine or needs care, but a clean answer isn't always a correct one. A false alarm costs a few extra questions and a supervisor's minute. Missing a nearly full panel costs far more. So we'd tune the model to lean toward needs care, and keep a person on every job it flags.
We spent the most time on how the approval feels. It arrives as a quiet notification, and the amber settles back to green. The technician should feel that someone has their back.
When you build this, track both kinds of miss before and after launch, especially risky jobs tagged routine. It's the same discipline that keeps LLM features from rotting.
Adapting only works if it's fast
If the screen waits, the design fails. Jakob Nielsen's 1993 summary of response times puts the limit at about one second: past that, a person's flow of thought is interrupted.
FieldOps needs one quick choice from a short list, routine or risky. That's work for a model built for fast, structured decisions. In the concept, that model is Jev, made by TypeSafe AI.
In Ariful Islam's independent test of 400 decisions (dev.to, September 2026), Jev's median was about half a second. Three mid-tier chat models took about 2 to 3.5 seconds. At list prices, a million decisions would cost about $8, compared with $240 to $500.
The test used support tickets rather than field service, so treat the numbers as a ballpark. Half a second sits between what Nielsen calls instant (0.1 seconds) and the one-second line, and Jev was the only model under that line.
Our team calls this layer System 0, a term Chiriatti and colleagues proposed in Nature Human Behaviour (2024) for AI that takes on part of our thinking. TypeSafe calls Jev a "System One" model. Either way, the decision is made before the technician sees the screen.
Software that fits the person
If you lead a product team, you can start this week. Pick the form your field team fills in most. Next to each question, write which jobs need it. Find the one that would hurt most if skipped, and check whether it looks like every other row. If it does, that's your first fix, and it doesn't need a model.
AI comes in when the sorting has to happen for each job, in real time. Then response time becomes a design constraint, one more reason engineers belong in the discovery room. Prototype one job type first, and ship it to answer one question: do technicians still tap past the safety check?
In a stranger's garage, with one hand free, software that fits the person asks for what the job needs, then gets out of the way.
Four questions when that's all the job needs. A lock when it needs more. A person on the call that matters.
Gadiel Alcántar is a UI/UX designer at Metova, designing the screens people use on the job, often standing up, with one hand free and a customer waiting.
