Verdict — Documentation
What Verdict is
Verdict is a verification service. It runs a submitted question — optionally with your assistant's draft answer — through a structured adversarial debate between AI models from different vendors. An independent rival model critiques the draft, the models exchange rebuttals, and an impartial judge synthesizes a final answer with a confidence score and a disagreement map. All outputs are AI-generated and not professional advice.
Using Verdict from your AI assistant
Connect Verdict as a custom connector (Claude) or app (ChatGPT), sign in with your Verdict account, and your assistant can then call the tools listed below. Setup steps and copy-paste activation snippets live on the Modes page of your dashboard after signing in.
The six tools
- debate
- Runs an independent adversarial critique of a provided answer by a rival-vendor model and returns a judged synthesis with a confidence score and a disagreement map. Accepts a question, optional context, and an optional draft answer to critique via caller_draft. Intended for verification of consequential answers, not simple lookups.
- get_debate_result
- Fetches the status and result of a previously started debate by job id.
- quick_verify
- Returns a single independent critique of a provided draft answer from a rival-vendor model, with an agree or disagree verdict.
- set_mode
- Sets the caller's Verdict debate mode (standard, prompted_only, research, complex, full_integration, or code_adversarial). Changes only the caller's own configuration.
- get_my_mode
- Returns the caller's current Verdict debate mode and judge configuration.
- usage_left
- Returns the caller's remaining verdict quota, plan tier, and the period it applies to.
Quotas
Usage is measured in verdicts. A standard debate costs 1 verdict, a deep-model debate 3, an adversarial code review 5, and a quick check 0.25. Each plan tier has a verdict allowance per period; when it's used up, the tools return a clear message and the allowance resets automatically. Check your remaining quota anytime with the usage_left tool or on your dashboard.
Privacy & data
Your questions and debates are never used to train AI models — not by us and not by the model providers. Delete your account and everything purges within 30 days. See the Privacy Policy and Terms.
Last updated: July 20, 2026.