Module 2 of 3

Memory and Identity

Breaking the illusion of the "Persistent Entity."

Agents feel like they have a persistent identity. They don't. In this module, we help you construct 'memory' from scratch using context, episodic logs, and semantic search.

How AI Agents Work
  • ~75 mins
  • 3 lessons
  • foundation
Get this course

What you'll learn

  • Evaluate trade-offs between short-term context and long-term semantic memory.
  • Move past the hype of "infinite memory" to the logical reality of embeddings and vector search.

Lessons in the Module

1 Why Agents Are Not Entities 20–25 min
2 Memory Architecture 25–30 min
3 Single-Process vs. Distributed Multi-Agent 25–30 min
Back to course overview

Further Reading

Safety

Constraint Architecture for Autonomous Agents

10 min read

Technical

The LLM-as-Judge Problem Nobody Is Talking About

7 min read

Governance

The Inference Audit Trail: Making Every AI Decision Accountable

8 min read
All insights