> your prompt is confusing, unfocused, and doesn't work right on any LLM

You are assuming the entirety of the prompt is human prose, but it could be sets of data so the agent doesn't have to collect it every time, like program interfaces, commands, views, databases, tables, data models etc...

I could see this scale to multiple kiltobytes of metadata in the prompt easily.

▲

DiabloD3 28 minutes ago | parent [-]

That usually ends up being a poor use of LLMs, and is an unsolved problem with LLMs.

RAG was supposed to be the way out on that, and ended up being mostly abandoned.

	▲	gchamonlive 14 minutes ago \| parent [-]
		That doesn't make much sense to me because this is in nature much like how harnesses operate: launch a bunch of exploratory subagents to search and retrieve evidence to use in the actual prompt. Think of it as caching this end result so you don't have to re-fetch in the codebase.