How it works
A small, repeatable usability test. Run by synthetic users.
The method is inspired by Steve Krug: watch a few people use the site, find the few problems that hurt most, fix them with the smallest change, and test again.
The method
-
First impression
Before doing anything, each user looks at the page for a few seconds and answers: what is this, who is it for, and where would I click first? If the answers are wrong, the page is not saying what you think it says.
-
Tasks with expectations
Each user gets a realistic goal, like “find the price for two nights” or “change my delivery address”. Before every click they write what they expect to happen. When reality differs from the expectation, that gap is the finding.
-
The 3 worst problems
We rank everything we saw by how many sessions it blocked and how badly. You get three problems at the top, not a list of sixty. Three is what a team can actually fix before the next round.
-
The smallest fix
For each problem we propose the least change that removes it: a label, a moved button, a visible price. Redesigns can wait. The fix comes as a mockup and as a prompt for your coding agent.
-
Test again
After you ship, the same profiles repeat the same tasks. The history shows what got better, what did not, and anything the change broke.
Profiles and simulated abilities
Every study mixes profiles. Each profile has a goal, a pace, a level of digital skill and, where it matters, a simulated limitation. We apply those limits to what the agent sees and does, not just to how it is described.
| Profile | How we simulate it | What it tends to reveal |
|---|---|---|
| Reduced vision | Screenshots are blurred and their contrast is lowered before the agent sees them. | Pale grey text, small icons, low-contrast buttons, text over images. |
| Imprecise taps | Tap and click coordinates get a random offset of a few pixels. | Tiny targets, links packed together, close buttons in corners. |
| In a hurry | Fewer steps and less time. The agent skims and gives up after a few wrong turns. | Buried calls to action, long pages before the point, slow feedback. |
| Low digital skill | The agent avoids jargon, hesitates at unlabelled icons and does not assume hidden menus exist. | Hamburger-only navigation, icon-only buttons, technical wording. |
| No context | Starts cold, as if arriving from a search result, with no knowledge of your brand. | Home pages that assume you already know what the product is. |
Profiles are also varied by goal (browse, compare, buy, get support) and by device format (desktop, mobile, tablet).
What synthetic users are, and what they are not
They are
- AI agents that operate a real browser or Android emulator, on your real site.
- Recorded: video, screenshots and the reasoning behind each step.
- Good at spotting what trips up a first-time visitor: unclear labels, hidden prices, dead ends.
- Fast and repeatable, so you can test again after every fix.
They are not
- Your customers. They have no budget, no history with you and no real stake.
- A replacement for talking to people about needs, prices or trust.
- Statistically representative. Six sessions show problems, not percentages.
- Always right. Some findings will be wrong. The video lets you check.
Every report ends with a short script to confirm the top findings with three to five real people. That is where synthetic testing hands over to research with humans.
Safety
Read-only on public sites
Public tests only navigate and read. Users do not create accounts, send messages or place orders.
Domain verification for apps
Testing behind a login needs proof that you control the domain, and test accounts you create for us.
No payments, ever
Agents stop before any payment step. They never enter or submit card details.
EU data hosting
Recordings and reports are stored in the EU, in Madrid, and deleted after 90 days.
See where people get lost on your site.
Paste your URL. In a few minutes you get the 3 worst problems and one session video.