Skip to content
artifx
← Case studies

Agentic UX: designing for AI agents that work in the background

AI agents keep working after people look away. How to design their limits, hand-offs, notifications and activity trail, from two products with agents built in.

Vytrac provider app on three phones: dashboard with heart-rate alert, red alerts list and patient overview

Most AI features answer when asked. Agents keep working after people look away: they watch data, talk to customers and run optimisations on their own. Nobody is watching when the agent acts, so the interface has to set its limits beforehand and explain what happened afterwards. These patterns come from two products I designed: Vytrac and Zentra.

Make the limits visible

Vytrac’s AI health engine watches each patient’s readings against thresholds, and the care team can see and adjust those thresholds from any alert. People should be able to read, in plain words, what an agent watches and what it will never do on its own.

Vytrac provider app on three phones: dashboard with heart-rate alert, red alerts list and patient overview

Let the person win

In Zentra, the optimisation agent runs only when a manager starts it, and its suggestions wait next to the tickets they concern until someone acts. Any action a person takes should override work the agent hasn’t finished yet.

Escalate instead of guessing

When an agent isn’t sure, it should hand over rather than act. Notifications follow the same rule: they go out when a person needs to take over, not for every step the agent takes.

Report back with the next step

Vytrac’s AI health engine monitors patients all the time. When something needs attention, it arrives as an alert card with the actions on it: contact the patient, send a questionnaire, assign or adjust the threshold. Those cards appear on the provider’s phone too, because alerts come in away from the desk.

Keep a trail

Each Zentra ticket keeps an activity timeline beside its AI risk assessment, so anyone can see what happened and why.

Zentra phone screens: overview with risk assessment, ticket list, and ticket detail with activity

In short: visible limits, people override the agent, escalate instead of guessing, end every report with a next step, and keep a trail with undo. See AI product design.

Questions about this work? Let’s talk it through.

Set a meeting

Let’s talk it through

30 minutes on Google Meet, at a time that suits you.

Set a meeting

Set a meeting

Book a call in an open slot, or just send a message.

What is it about?
Pick a time

Choose a day