1:1 mentoring with Big Tech AI engineers
Q27Premium

The agent remembered something wrong about the user. How does that get corrected?

Memory & State

MemoryData QualityPersonalizationProduction

Asked at OpenAI · Meta · Sierra

How to Answer

“First I’d ask how it got there, because most bad memories are an inference written as a fact. The user asked about vegetarian restaurants once, and the agent stored ‘user is vegetarian’. That is a guess promoted to a permanent record, and no correction path fixes a write policy that does that.

For correction itself: memories have to be updatable and supersedable, not merely appendable. When the user says ‘I’m not vegetarian’, that has to supersede the old row — otherwise retrieval returns both and the model picks whichever ranked higher.

So I want three fields on every memory: where it came from, when, and whether it was stated or inferred. Then correction is a real operation — find the conflicting rows, mark them superseded, write the new one.

And the user needs to be able to see and delete what the agent thinks it knows. That’s a trust feature, and in a lot of jurisdictions it’s also a legal requirement.”

The deep dive — diagrams, tradeoff tables, and the follow-up trap

Loading…