Discussion about this post

User's avatar
hohoda's avatar

Most people optimizing their agent are still in the execution layer — shaving tokens, tuning prompts, but context loading is a different problem. Someone has to decide what gets loaded: you, RAG, or the agent itself, that choice doesn't disappear just because the window is 200k.

Jonatan's avatar

Thanks Pawel. This described some experiments I’ve been building without framing them expressly as agents. Claude Code, Obsidian vault, instruction files with autonomy tiers, scheduled monitors, memory as markdown. I’m about to go deeper with an old Mac Mini that’s currently just sitting idle. Was thinking of trying OpenClaw on it but maybe I’ll build something from scratch for the full learning experience.

6 more comments...

No posts

Ready for more?