Agent Basics
Core concepts, the agent loop, foundations for newcomers.
24 posts · showing 21–24
-
Reading Your First Agent Trace: Wrong Tool, Wrong Argument, or Wrong Plan?
Four buckets, checked in order, and most agent failures resolve before you get to the interesting one. The trick is finding the first wrong turn and reading the raw array — not the pretty rendering.
-
Prompt, Tool, or Code? Where Each Piece of Logic Belongs
A rule the agent keeps breaking usually isn't a prompting failure — it's deterministic logic filed under "advice." Two questions place any behavior in the right one of three homes.
-
Why Your Agent Stops Too Early: The Missing Termination Signal
"Done" in most agent loops means the model stopped asking for tools — indistinguishable from stuck, confused, or bored. Making completion an explicit, validated claim takes about twenty lines.
-
Your Agent Isn't Thinking, It's Looping — Read One Turn of the Trace
There's no reasoning engine and no memory — just a while-loop, a stateless model, and an array that grows. Unroll one turn of it and most agent mysteries stop being mysteries.