Skip to content

AI Memory

What an assistant remembers, for how long, and what can go wrong.

conversation historyshort-term memorylong-term memorysemantic memorysummariesprivacystale memories

Lessons

  1. 27.1Short-term and long-term memory for assistantsAI models forget everything between calls. Here's how an assistant still remembers your name today and your dog next year. 30 min Agent memory manager
  2. 27.2Memory risks: privacy, staleness, poisoning and deletionEvery memory an assistant keeps can leak, go stale, be wrong, or be planted by an attacker. Here's how to keep memory safe by default. 30 min Agent memory manager

On the job: try it on your own project

Look at an AI feature in your product or a tool your team uses that remembers things. Ask Claude Code to explain what is stored, where, for how long, and who can see it. Check for stale or sensitive data. Write a short memory policy: what to remember, what to forget, how users can delete it, and how stale memories get fixed.

Can you do this now?

0/4. Anything you can't tick yet: reopen that lesson's practice ladder.