Comment by tcwd

Thanks! Quite a few factors, here's a detailed post on the architecture: https://blog.withmeka.com/introducing-meka-an-open-source-fr...

IMO, the combination of having an "evaluator model" at the end to verify if the intent of the task was complete, and using multiple models that look over each other's work in every step was helpful - lots of human organization analogies there, like "trust but verify" and pair programming. Memory management was also very key.