Select your models and enter a prompt to begin.
Bridget works best for stress-testing arguments, not verifying facts. For legal work: conduct your own case law research and citation verification first, then upload verified materials as document context. Bridget will stress-test your argument against those materials through adversarial multi-model debate. Bridget is the crucible — not the library.
Bridget does not store your prompts, documents, or AI responses. Your prompts are sent directly to the AI platforms you select — OpenAI, Anthropic, Google, xAI, Venice.ai, DeepSeek, Mistral, or Cohere — using your API keys or the pre-configured system keys. Session metadata (not content) is stored securely in an encrypted database to enable session history and Verdict permanence. For Collaborator and above accounts, API keys may optionally be stored server-side using AES-256-GCM encryption. Free and Guest users retain keys in their browser only.
Bridget was built to bridge AI platforms — to make them argue, synthesize, and converge. It became something more: a bridge between artificial intelligence and the blockchain. 3% of revenues are committed to The Bitcoin Museum Trust. Both technologies decentralize truth. Bridget debates it. Bitcoin records it. Bridget is also a proud sponsor of The Bitcoin Museum — because the same instinct that built this platform built that commitment.
Press ? anywhere to show this panel. Shortcuts are inactive while modal dialogs are open.