Agent Memory

Thu, 20 Aug 2026 01:04:50 +0545

There is an external database that stores the relevant information. It must support querying, and curating.

Some must be never forgotten, some must be forgotten.

The important/interesting thing is how curation happens.

Quite interesting to realize that evals must take into account probably a dynamic memory.

Agent Evals

Thu, 20 Aug 2026 00:54:58 +0545

notes from this short video.

We want agents to be reliable. Reliability = Observability + Evals

Observability means we can see what agent did. What the model response was, what the tool response was.

LLM response desired properties:

Relevance: Answer relevance to the user’s query
Groundedness (relates to hallucination as well): uses the particular context provided (as opposed to the generic response)
Tool Sequence Accuracy: does not do wasteful tool calls, and follows correct sequence of tool calls