ETOT
ETOT
DESIGN STUDIO
ETOT
type
product & UX
since
2020
where
Vienna & Minneapolis
tools
1 shipped · 3 queued
surfaces
MCP · CLI · plugins
Get in touch

Design tools that measure before they ship.

etot.field · letters sized by distance to a curve · under the cursor the field resolves into the ETOT monogram

We're ETOT, a two-person product and UX design studio in Vienna and Minneapolis. We build verification tools for AI-assisted design work — tools that check what AI produces and show what's wrong with it. We measure every tool and publish the results before it ships, including the parts that didn't work.

01

Tools that show their work

the family

One core, several tools. They each do a piece of work, check the result against rules a team can read, and report what they couldn't fix. What they have in common is verification — they all check work — not the task.

ETOT
TOOL · RESEARCH SYNTHESIS

Motif

type
agentic loop
version
0.2 · MCP
surface
MCP server · CLI · FigJam via Figma MCP
license
MIT · data CC-BY-NC

Turns a folder of interview transcripts into findings, then tries to knock them down — and shows you what survived.

1.7 → 0.7unsupported claims out of every four checked — a single prompt, then the loop
ETOT
TOOL · DESIGN SYSTEMS · IN QUEUE

Design-system drift

type
deterministic check + critic
status
not started

Finds where a design file has drifted from the team's design system — its colors, type and spacing, its components — with the receipt — the evidence you can check — for each finding.

ETOT
TOOL · GENERATED PROTOTYPES · IN QUEUE

Constraint adherence

type
deterministic check + critic
status
not started

Checks an AI-generated prototype against the rules it was given, and lists what it silently dropped.

ETOT
TOOL · DESIGN CRITIQUE · IN QUEUE

Critique

type
agentic loop
status
not started

A critique tool measured against a known-correct answer before it ships — the Baymard 2023 benchmark, re-run on 2026 models.

02

We measure before we ship

the method

A tool is a claim: this works better than what you're doing now. Motif's claim: this loop makes fewer unsupported findings than a single prompt. So we set the number before we build anything. Whoever builds the tool does the task by hand first, so we know how well a person does it. Then we measure the tool against that, without knowing which result came from which method. The write-up reports what got worse alongside what got better. We write down what failure would look like before we start. If that's what we get, we don't ship.

Read the ETOT method — the phases, the discipline, and why a null result, a test that found no improvement, is the most credible thing in a write-up.

03

Work with us

contact

We take on product and UX design work, and it gets the same discipline as the tools. We measure it, and we tell you what didn't work. The tools sit alongside the craft, not in place of it.

where

Vienna & Minneapolis
Vienna CET · Minneapolis CST
Available remotely

ETOT · Vienna & Minneapolishello@etot.designPrivacy© ETOT 2026