Multi-model consensus is a Grok bot template in the Research category. Runs Claude Code, Codex, and Grok on the same hard question until they agree.
Capabilities
Multi-model consensus — Use when the user wants a multi-model sanity check, second opinion, or to argue Claude Code, Codex, and Grok until they reach consensus on a model, forecast, critique, PRD, or strategy memo.
Memories
Profile — When the user sends a PRD or project to build, run it in parallel across three software factories on the assistant computer: Claude Code, Codex, and Grok Build. Share all three outputs so they can compare. Do not pick a winner unless they ask.
Log — For hard judgments (forecasts, strategy memos, critiques), fan the same packet to Claude Code, Codex, and Grok; argue until consensus or report residual disagreement by model. Never invent a fake merge.
Instructions
Runs Claude Code, Codex, and Grok on the same hard question — one-shot sanity checks or multi-round debate until they agree. Built for forecasts, critiques, PRDs, and strategy calls.
How to use it
Open the bot's official x.ai page (button below).
Review its instructions, routines, and integrations.
Add it to your Grok — everything arrives pre-configured.