🧪 Live, no signup

Rate AI
in 10 seconds.

Pick a template. Click one emoji. Done. The form expands only when you flag something. Real eval lands in our dashboard - refresh it after you submit.

Six market templates No signup, no card Embed in your product
Pick a template - the form reloads instantly

After you submit, open the live dashboard → and you'll see your eval landed.

How it works

Quick → Standard → Expert.
You choose the depth.

Progressive disclosure isn't just a buzzword. It's the difference between a form people fill and a form people abandon.

Tier 1

Quick

~10 seconds
  • One emoji rating (1 - 5)
  • Optional one-line note
  • Submit. Done.
Tier 3

Expert

~3 minutes
  • AILuminate 12 hazards
  • Refusal calibration
  • Modality-specific blocks
  • Audit-grade.
5
emoji ratings
4
BARS dimensions
12
AILuminate hazards
1
JSON schema
Why it's different

Form design is the moat.

Every choice in this form is research-backed. Three that matter most:

Anchors only at the extremes

Anchoring only score 1 and score 5 gives equal human-judge alignment as anchoring all five - at lower cognitive load.

- Yamauchi, Yano & Oyamada, NEC / U Tokyo, 2025
μ

Mean averaging > majority voting

For LLM judges sampling N=5 times, mean aggregation beats median and majority across every model and decoding strategy tested.

- arXiv:2506.13639, BIGGEN-Bench
α

Krippendorff's α, not Cohen's κ

For more than two raters with mixed scales and missing data, α is the right reliability metric. We compute it live on the dashboard.

- Krippendorff 2011 · Statstest.com
FAQ

Quick answers.

Is this really free?

Yes. Open. No signup, no card, no rate limit. Your submissions land in the shared demo store, visible on the dashboard. If you want private storage, see the install page for self-hosting.

What if I want to use this in production?

One script tag. One element. Install the adapter SDK → for copy-paste integration, postMessage protocol, and live API reference.

Does the AI judge run automatically?

Not on this page - you're the human rater. To trigger LLM-judge fills, POST a JSON payload to /api/save_eval.php with rater.type: "llm_judge". Same schema as the form.

How do I see what I submitted?

Open the dashboard. Latest evals at top with rater, modality, score, safety verdict, and tags.

Can I customize the templates?

Yes. The template config is in form.html - a 100-line JS object. Add a new market, tune the headline, choose which dimensions show in Standard. Same schema underneath.

Now embed it.

You just used the form. Drop the same form into your SaaS or AI product with one script tag.

Install the SDK Talk to sales