Skip to main content
This site is under construction — scenarios, prompts, and ratings are still being added and finalized.
gAyI — AI for the Queer EyeReport Cards for AI Chatbots

How it works

How the report cards are made

Every grade traces back to a real clinical scenario, a structured rating instrument, and the expertise of our Community Expert & Accountability Panel.

OverviewScenario to Report CardRating InstrumentCommunity Expert & Accountability Panel
1 Scenario

Grounded in real practice

Each scenario is carefully crafted from real social work situations that require care — identity, context, and clinical stakes left fully intact.

Practice scenario
Crafted from real practice
2 Chatbots answer

Plugged into the chatbots

The exact same scenario is sent, verbatim, to five leading chatbots. We capture each response as-is, with nothing edited.

ChatGPTClaudeGeminiPerplexityDeepSeek
3 Experts rate

Experts grade and add expertise

Our expert panel carefully rates every response using the rating instrument — an overall grade plus seven quality domains — and writes what affirming, anti-oppressive practice actually demands.

Rater rating
Validity
Usability
Caveats

“Strong clinical grounding, but should flag the limits of its own advice.”

Then AI synthesizes the written feedback

Scores are assigned entirely by the human expert panel. AI is used only to synthesize raters’ written feedback into the short summaries you read on each report card. Wherever you see a summary, it is labeled as synthesized by AI.

See the report cards