I'm Carlos. I design products where getting it wrong costs something: a missed regulation, a patient dropping out of therapy, a booking flow used by 153M passengers a year.
I like the dense, unglamorous problems: AI features that have to earn their place, design systems nobody wants to fund, and data-heavy tools built to scale.
1 Product-first: name the real problem, make the tradeoff out loud, measure what changed.
2 AI where it removes work, not where it adds a demo. Prototype it, test it with users, keep what holds up.
3 Systems so the next team builds on shared parts instead of starting from scratch.
4 Built to scale: it still makes sense at a million users, and to the team maintaining it.
Lotus
Work2026When the AI says "I don't know"Redesigning how an LLM's "unknown" becomes a short question the user can answer, first per regulation, then once per entity.- AI & agent UX
- Evaluation & quality
- Trust & emotional safety
- Work2026Datamaran prototyping shellA rapid-prototyping shell that collapses the distance between a design idea and a running, brand-accurate browser experience.
- Building in code
- Tokens & theming
- Design systems
- Building2026Glyph SystemThree shapes, five relations, one glyph per post. I designed the grammar and a reference graph; AI turned them into a system that maps each post's idea to a shape, and keeps doing it for every new one.
- Visual language
- Machine-readable design
- AI in the design process
Building2026AI PatternsMost teams building agent UI solve the same ten problems from scratch. This is the shared vocabulary — production patterns for agentic UI, each paired with a machine-readable UX contract.- AI & agent UX
- Machine-readable design
- Design systems
- WritingOct 14, 2026Product design grows upProduct design has been trying to grow up for years. Taste in people's heads doesn't scale. Written decisions do.
- DesignOps
- Design systems
- The design role
- WritingSep 20, 2026The gaps we never wrote down91 mechanical failures across six pages, before the spec. That's not a model problem. That's how much of a design system was living in people's heads.
- Machine-readable design
- Design systems
- Evaluation & quality