CSE Roadmap

Core tier · about 8 hours · 16 parts

Part 7 of 16 · 1 min read

What competes for the window

Seven kinds of item, who writes them, and how each should be treated.

An agent's window holds items of different kinds, and they do not deserve equal treatment.

Kind Example Written by Treat as
Rules "Never delete the backup bucket." developer pinned: always in, always first
Tool definitions names, arguments, descriptions developer pinned, or chosen per step
History earlier user and assistant turns user, model candidates: recent ones usually matter most
Tool results logs, search results, file contents outside world candidates, often long, mostly noise, untrusted
Retrieved text passages found by search store candidates, untrusted
Notes what the agent wrote to itself earlier the agent candidates, trusted more than tool results
The question the current goal or message user always in, last

Two things follow. First, the rules must not compete. If a rule can be pushed out by a long log, the agent will break it exactly when the logs are long, which is when it is working hardest. Second, trust differs by kind. Text a tool returned can say anything. So the assembler must wrap it in a way that cannot be mistaken for a rule, as Part 4 showed.