LLMs can't justify their answers–this CLI forces them to
w heat is a decision-making framework that runs inside Claude Code. You research, prototype, stress-test, and compile your findings into a decision brief. A compiler validates everything — you can't ship a recommendation built on contradictions.
Works with Claude Code , Cursor , Copilot , or standalone. Node.js 20+.
w heat is a structured way to answer technical questions. You start with a question — "Should we migrate to GraphQL?" — and use slash commands to research, prototype, and challenge your findings. Every finding is tracked as a typed claim with an evidence grade.
When you're ready, a compiler validates everything: catches contradictions, flags weak evidence, and blocks output until issues are resolved. The result is a decision brief you can send to your team. It all runs inside Claude Code — no new UI to learn.
One command. Zero prompts. Sprint ready in under 3 seconds.