Haha, I just started doing this on my own. Found it helps the agents preserve state better. I typically ask them to design a DAG first based on a set of specifications and then execute it (each step stores something in a SQLite DB). Iteration is pretty simple then because I just ask for a tweak to one or two steps of the DAG, and then to re-run.

Funny how people are independently converging on similar patterns of "what works" here. Still feels like we're in the wild west with all these ad-hoc patterns of agent orchestration that people are coming up with.

Same. The prompt was essentially, every checkbox in this PLAN.md should be task in SQLite.