The loop

One tool press is not yet an agent. What makes an agent is doing it in a loop.

The cycle has three beats. Observe: the model reads everything on the board so far, the task, and whatever results have come back. Decide: it judges whether it can answer now, or whether it needs to act first. Act: if it needs more, it asks for a tool, and the result lands back on the board. Then it loops: observe the new board, decide again, act again.

That is the whole engine. Observe, decide, act, observe, around and around, until the model judges the task done.

And it can go around many times. A single request like "research this and write me a summary" might spin the loop a dozen times: search, read a result, search again to check it, open a document, pull a figure, cross-check it elsewhere, then finally write. Each lap feeds the next. This is what lifts an agent above a single reply: it can follow a thread through the world, gathering and testing as it goes, instead of answering in one breath from frozen memory.

But look closely at that loop and you can already see the danger built into it. Every lap is a fresh chance to go wrong, and worse, a wrong turn early does not stay put. The result of a bad step lands on the board, and the next lap builds on it as if it were true. A small slip at step three can quietly steer every step after it. And unless someone deliberately puts a human in the loop, nobody is checking between the laps.