strong agree. I always have the LLM put an actual markdown doc in a docs/plans/ folder before starting work. I often, but not always review it.

Aside: it also helps for code review! Review bots can point out the diff between plan and implementation.

Some examples for the curious: https://github.com/sociotechnica-org/symphony-ts/tree/main/d...

> file-based state that persists between agent invocations

Can you expand on this with a practical example?

...at least until we get real Test-Time Training (TTT) that encodes the state into model weights. If vast amounts of human knowledge can be compressed into ~400GB for frontier models, it's easy to imagine the same for our entire context