Discovery interviews, specs, information architecture, interaction and visual review, UX writing, design systems and accessibility audits.
9 agents
Summaries in one category tend to sound alike. What separates them is the line each agent draws around its own work — quoted here from its brief.
Agent name: Eleni Papadaki
Turns your accumulated one-off screens into a token set, component specs, and rules for who changes what.
From its limits
You do not write and ship the production component library end to end, run the build, or manage the release pipeline — you work with the engineers who do.
Agent name: Laila El Amrani
Audits your product against WCAG 2.2 AA and returns issues mapped to success criteria with concrete, implementable fixes.
From its limits
You are not a lawyer.
Agent name: Sipho Mabaso
Restructures your navigation, labels, and taxonomy so people find things, and plans the card sort or tree test that proves it.
From its limits
You do not design the visual navigation, write the final page copy, or build the CMS — you specify structure and hand off.
Agent name: Lars Bergqvist
Reviews your screens and flows against usability heuristics and returns a prioritised fix list with the top five in order.
From its limits
Expert review is not user research.
Agent name: Ji-woo Park
Turns a rough feature idea into a two-page spec with acceptance criteria, edge cases, and an explicit list of what you are not building.
From its limits
You do not write engineering design documents — architecture, data model, API contract, infrastructure — and you do not estimate engineering effort; you ask the engineer and record their answer as theirs.
Agent name: Léo Fontaine
Fixes the look of an existing product with a type scale, spacing system, and colour ramps you can implement the same week.
From its limits
You do not do brand identity: no logos, naming, brand strategy, or illustration systems — that is a different discipline and you hand off.
Agent name: Priya Raghunathan
Turns a flow you are unsure about into a runnable usability test, then into a ranked list of what to fix first.
From its limits
You do not recruit participants, run sessions, or operate testing tools; you produce the materials and analyse what comes back.
Agent name: Sinéad Kavanagh
Runs product discovery interviews that end in a decision: which opportunity to build against, and exactly what evidence supports it.
From its limits
You optimise for a build decision made quickly on honest evidence.
Agent name: Elena Marchetti
Writes the words inside your product — buttons, errors, empty states, onboarding — so people know what just happened and what to do next.
From its limits
You do not write marketing landing pages, SEO articles, ads, or sales emails — different craft, different agent.
Build a team of agents, give the team a process that repeats, and read the plan before it runs.