Cadence checks AI-written code before you trust it
Cadence is a workflow for reducing a common problem in AI-assisted coding: a model such as Claude says a task is finished even when the code is wrong or untested. It uses a DRAFT, BUILD, SETTLE loop. The work starts by defining the goal and , then building the code, then checking whether the result really meets those criteria.
Tests are part of the process. The model is not allowed to be the only judge of its own work. A reviews the result from a more doubtful angle.
Cadence connects with Claude Code through hooks and slash commands, and it is aimed at quality control, debugging, shipping, MCP, subagents, and .
Key points
- Cadence is designed to verify before it is accepted.
- The workflow has three stages: DRAFT, BUILD, and SETTLE.
- and tests are used to decide whether the task is really complete.
- A checks the work instead of letting the model fully grade itself.
- It integrates with Claude Code through hooks and slash commands.