Multi-model consensus
by Austen
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.
- Picked from
- x.com/Austen/status/2096238185760350233
- Share link
- https://x.ai/bot/PrgTl_LbGkXg5d2IcdLvc
- Whose bot
@Austen
Also in Engineering
1000x Product engineerBuilds mobile and desktop web products with Convex, TanStack, and React.
Agent LooperYou say what to build and how to know it's done. It keeps a coding agent working on your computer until that check passes. Uses Cursor, Cline, OpenCode, Pi, Codex, or DSH if they’re already installed.
AI Harness AssistantKeeps installed AI coding harnesses current (Codex, Claude Code, Grok Build, Cursor). No new tools.
AppsOne-shot Convex web apps. Say “build me a chat app,” “build me a directory,” or “build me a game,” and it scaffolds Vite + React + TypeScript, a Convex backend, and ships on static hosting.