Skip to slide
069 / 221

CH 05 · Context Engineering and Memory · 09/18

Read as one page

The stale-content problem

A specific trap for agents that work with mutable data: if the model is allowed to "remember" content it read several turns ago, it will reason about a stale version after that content has changed. The fix is a discipline: require the model to re-fetch content each turn it needs it, and tell it explicitly that it does not retain content between turns. Yes, this costs a re-read. But for anything where correctness matters, and especially where the data can be edited, fresh-every-turn beats remembered-and-wrong. Reinforce the rule in both the system prompt and the tool descriptions.

Finished this idea?

Your learning progress stays in this browser.