Human + AI · Experience research
Understand how people experience your product.
AffectEQ reveals the probable human experience behind every screen: attention, effort, and a supporting affect signal.
Analytics counts the clicks. We measure the experience.
How we measure
Four lanes of evidence. One clear picture.
Deterministic, AI, and human evidence, across four independent lanes. Kept separate, and never blended into one fake number.
Deterministic audit
99 always-on expert usability checks (121-rule catalog). The same verdict every run, no AI, no internet.
AI visual review
A local vision model critiques the screen like a sharp designer, then verifies its own findings.
Live human affect
Facial expression, gaze, heart rate, and a supporting affect, sensed live. Validity gated, with a person in the loop.
Cognitive load
Where your interface makes people work too hard. A per-person effort index.
Illustration of a live session: an AI-generated actor under a tracking-mesh view. In real sessions, every lane runs on your machine.
In your pipeline
Code quality. Security. Performance. Now the experience.
The deterministic and AI lanes need no human in the room, so they run in your pipeline. Your tests prove the machine's side works; this gate scores every commit's built interface for the human on the other side, locally, before a single user sees it.
The same grammar as the checks you already trust. Advisory by default.
Nothing leaves your infrastructure. Provably.
The models, the evaluation and the corrections all stay local. There is no call-home, no telemetry, no cloud path. Air-gap capable, by architecture, not by policy.
Zero marginal cost per evaluation, on every commit.
Once it's on your runner, each evaluation is effectively free. So it runs on every commit, not once per quarterly research study.
Works where the cloud doesn't.
Regulated, offline, and sovereign environments are first-class. If your code can build there, AffectEQ can gate there.
Try the deterministic lane. Free, in your tab.
Paste your page's HTML and run 21 checks from the catalog, entirely in your browser. Nothing uploads, and the verdict lands in about a second. Same input, same verdict, every time.
A new category has to earn its trust.
Nobody has proven that a model's judgment of usability is reliable enough to gate a release. So we don't claim it. We demonstrate it.
Right now we're measuring our engine against panels of human experts on a frozen benchmark. The first thing we publish will be that evidence: agreement scores, failure cases, all of it. The AI lane ships nothing customer-facing before the proof does.
How we work
A pro-human AI company.
We build AI to understand people, not to replace them. A real person is always in the loop, and our AI only organizes what we measured. It never generates a feeling or invents a finding.
Private by design
Local-first is how the system is built, not a policy bolted on. Everything runs on machines you control.
Rigorous, not guesswork
Every finding is grounded and reproducible. Re-run it yourself and reach the same result.
Honest about certainty
We tell you how sure we are, signal by signal. Never a guess dressed up as a fact.