Enterprise delivery · health, fleet and manufacturing

Data and AI products inside large companies

Allocated by Triggo Labs, I designed products for real operations: clinical chat at a health insurer, fleet maintenance at a rental company, and internal data products in manufacturing and heavy rental. An internal user does not choose the tool, so they forgive no friction and read no tutorial.

My role: Senior product designer, allocated via Triggo Labs
When: 2023 to 2025
Outcome: Internal products the operation adopts without formal training, which is the only test that counts with this kind of user.

What I did

Unimed: a conversational interface in a clinical context, with an explicit scope of what the assistant answers and what it hands to a person, and a one click exit to human support.
Unidas: a maintenance MVP, from the ticket to the workshop, with the vehicle's status visible to the people doing the work.
Grupo Vamos and Grupo 3 Corações: internal data and operations products, designed for the people who run the routine and not only for the ones who read the report.
The same rule in all of them: before the screen, understand who gets held accountable for what. An internal product that ignores how its users are measured becomes a parallel spreadsheet within two weeks.

AI contract analysis: every clause comes with a reference to the source passage and a thumbs up or down, because whoever answers for the risk has to be able to disagree with the model

Opening a new analysis, with the incoming document

The proposal discussed in chat, with the document alongside

Clinical chat: the conversation where a wrong answer has real consequences

Professional registration check at the door: whoever is asking has to be who they say they are

See all work