Each portrait reveals what the pose conceals. — Oscar Wilde

A synthetic visitor moves through your website and reports what they noticed.

Three inputs — environment, scenario, the signal worth tracking — produce a timestamped log of the session, ending in a structured summary that's comparable across deploys.

This is what poseur produces

A synthetic visitor with a specific persona, specific stakes, and a specific signal to track. They move through your website and produce a timestamped inner monologue, ending in a structured signal line.

URLhttps://example-ai.com Personaskeptical developer, first visit, no prior context Signaltrust — does this page earn a demo booking in under a minute?
[00:05] Page loads. Headline: "AI for your team." Vague.
[00:15] Scrolling. Testimonials from companies I don't recognize. Not a trust signal.
[00:28] Still unclear what this actually does. No screenshot, no demo link.
[00:40] "Book a demo" — the only CTA. I don't book demos for things I don't understand yet.
[00:52] Back button. I'm out.
[SIGNAL] decreased; moderate; the page asked for a demo booking before earning enough trust to justify one

The [SIGNAL] line is structured: a direction, an intensity, a key moment that carries the why. Compare across deploys. Plot across sessions. A qualitative signal that behaves like a number when you need it to.

What your current evals miss

Unit tests say pass

But the landing page buries pricing. Your visitor bounces. The tests don't see it.

Thumbs-up says 👍

A scalar. You don't know what the visitor liked, hated, or silently stopped trusting.

LLM-as-judge says 8/10

An AI graded your AI against a rubric. Whose taste is that, exactly?

Human evals say good

Three weeks ago, in a scheduled session you can't re-run on today's deploy.

Three inputs, one output

Environment

The visitor's context. Device, browser, network, session state. Plain text.

Scenario

What they're trying to do on your site. Who they are, when they'd give up.

Signal

The emotional dimension your product depends on. Trust for an e-commerce checkout. Conviction for a landing page. Momentum for a developer tool.

Who it's for

Teams shipping AI agents whose web-facing surface is the product — landing pages, chat UIs, onboarding flows, playgrounds. Wire poseur into CI. Know whether your new prompt, new model, or new layout actually landed.

Also: product teams who want a faster signal than the next focus group can deliver — for the decisions that don't justify a full study.

Poseur only scans sites you've proven you own. Verification is one file upload away.

Get started

Poseur scans public websites you own. Sign in with Google, verify a domain, and watch the experience log stream back.