INTERMEDIATE · 8 MODULES · 64 LESSONS
Agent Memory and State
Give your agent a memory that survives the end of a session, so it remembers each user, updates what changed, and forgets when asked.
- For you if
- You've built an agent with tools, and every new session it forgets everything.
- By the end
- You'll know what to store, how to retrieve what's relevant when a session opens, and when you need semantic search.
- You need
- Basic Python and SQL, and an agent with tool calling under your belt. No API key needed.

Curriculum
01Why agents forget between sessions
02Types of memory (working, episodic, semantic)
04What to save (extracting facts, not transcripts)
- Module 4: What to save (extracting facts, not transcripts)
- Why NOT the raw transcript
- Extracting facts from `tool_result`
- The `extract_facts` function
- Episodes vs. facts: what's worth persisting
- Writing Ana's session 1 to the store
- Deterministic extraction vs. LLM extraction
- Mini-project: persist a complete session
06Updating, expiring, and forgetting memory
07Injecting memory into a new session
- Module 7: Injecting memory into a new session
- The write-at-end, read-at-start cycle
- `format_memory_block`: giving the text its shape
- Injecting into the `system`
- Injecting into the initial `messages`
- The full cycle: from session 1 to session 2
- The boundary with `context-engineering-guide`
- Mini-project: a memory-aware Reservo agent
08Project: a Reservo agent with member memory
Reviews
What students say
These reviews are from enrolled students who completed at least 50% of the course. We moderate reviews only on content grounds (spam, offensive language, personal data), never for being critical or negative.
No approved reviews yet.
Be the first to share your experience!