It's a durable orchestration loop for implementing code with LLMs that forces review and verification gates until the code matches exactly what you asked for.
It's complementary to any existing harness or tools you use, you investigate and plan your work and simply have your agent hand off the implementation to the engine.
You can have Opus 4.8 implementing, GPT 5.5 and DeepSeek reviewing in different roles etc, mix and match however you like.
It also supports sandboxing out of the box, starting with the YC backed Microsandbox.
It's a durable orchestration loop for implementing code with LLMs that forces review and verification gates until the code matches exactly what you asked for.
It's complementary to any existing harness or tools you use, you investigate and plan your work and simply have your agent hand off the implementation to the engine.
You can have Opus 4.8 implementing, GPT 5.5 and DeepSeek reviewing in different roles etc, mix and match however you like.
It also supports sandboxing out of the box, starting with the YC backed Microsandbox.