For those worried about irrevocable changes, sometimes a good plan is all the output.

Claude Code is very good at `doc = f(doc, incremental_input)` where doc is a code file. It's no different if doc is a _prompt file_ designed to encapsulate best practices.

Hand it a set of unstructured SOP documents, give it access to an MCP for your email, and have it gradually grow a set of skills that you can then bring together as a knowledge base auto-responder instruction-set.

Then, unlike many opaque "knowledge-base AI" products, you can inspect exactly how over-fitted those instructions are, and ask it to iterate.

What I haven't tried is whether Cowork will auto-compact as it goes through that data set, and/or take max-context-sized chunks and give them to a sub-agent who clears its memory between each chunk. Assuming it does, it could be immensely powerful for many use cases.