cleandataengineering.aiAgent Harness, drawn simply
You are here: End to end › State & memory › This turn

Agent Harness Tutorial · End to end · Zoom level 2

This turn, in memory

While the loop runs, the harness holds the full working picture in memory. When the turn ends, almost all of it is thrown away on purpose.

During the turnmessages so fartool callsraw tool resultsend of turnOpen: KeptKeptRohan's words + the replyzoom in ›Thrown awaytool calls and results→ saved in the checkpoint→ re-read fresh next time
Only text is saved. Facts from tools are always fetched again, fresh.

Why throw the tool results away? Because they go stale. A claim that was "registered" ten minutes ago may be "under assessment" now. Saving it would tempt the model to answer from memory. Instead, rows read earlier are read again at the start of the next turn.

It also keeps the saved conversation small: four messages come to about 1.9 KB.