Every few months a new word arrives for the same idea. "Copilot", "assistant", "agent". Underneath, the agents that actually work in production share a surprisingly small shape: a loop around a model that can call tools.

The core loop

The model never "does" anything. It proposes. Your runtime decides whether to execute, feeds the result back, and asks again.

yesnoUser goalPlan / reasonNeed a tool?Call toolObserve resultAnswer

That's it. Everything else — memory, guardrails, multi-agent setups — is decoration on this loop.

The four parts that matter

Part What it does Where it goes wrong
Model Reasons, picks the next step Overconfident on missing context
Tools Touch the real world (APIs, files, DBs) Vague descriptions, giant outputs
Memory Carries facts across turns and sessions Stale or contradictory notes
Control Budgets, approvals, stop conditions Infinite loops, silent writes

Tools are the product

The single biggest lever I've found isn't the model — it's tool design. A good tool:

When an agent misbehaves, I read the tool descriptions before I touch the prompt. Nine times out of ten, that's where the ambiguity lives.

Where humans stay in the loop

propose write (publish, send, pay)ask for approvalapproveresultAgentRuntimeHumanAgentRuntimeHuman

Reads can be automatic. Writes that are hard to undo should pause for a person. That one rule removes most of the fear from shipping agents.

An agent is only as trustworthy as its least-guarded tool.

Takeaway

Don't start with frameworks. Start with the loop, three well-designed tools and a clear stop condition. You'll be surprised how far that gets you.