Memory for agents
Comes up in: AI engineering, AI system design
This concept is being written. It gets the full five steps — explanation, predict, interview angle, practice with tests, and review cards. Here is exactly what it will cover, so you can study it elsewhere in the meantime.
What it covers
- short-term (conversation) vs long-term memory
- summaries/compaction
- retrieval-based memory
- memory tools
- privacy and user control (view/delete)
- stale or wrong memories
Words you will know
What you will practise
- user-preference memory with a delete UI
Interview questions this answers
- How would you give an assistant long-term memory? What can go wrong?