Lesson 1 of 7 · Why Intelligence Doesn't Compound

Stop prompting — start building memory

From Agents That Remember: Context Engineering & Memory: Build agents that remember. An agent's memory is just plain markdown files it reads, searches and updates for itself. Set that up and the agent gets better at your work every time it runs. You will keep deep detail out of the context window with progressive disclosure. You will stop two agents overwriting each other, using hashing and versioning. And you will decide what stays read-only and what an agent may rewrite. Predict, drag and decide your way through.

Start here

Stop prompting. Start building memory.

Context engineering is how an agent keeps its own memory — notes it writes, reads and updates itself. Build that, and the agent gets better at your work every time. Predict, drag and decide your way through.

Based on: Lamis Mukta's AI DevCon talk (Anthropic)
Time: ~25 min
Style: Interactive — predict & decide

A raw model is brilliant but forgetful. Give it a memory it manages itself, and its intelligence stops being a one-off — it starts to compound.

How agent memory grew up

One year, four eras — tap each to see the leap

1 · CLAUDE.md
2 · Memory tools
3 · Skills
4 · File-system memory

How this course works

Each lesson hands you something to do — predict an outcome, drag things into place, or sort what belongs where. You'll need to engage to continue. That's the point: you remember what you commit to.

Topics: ai, agents, context-engineering, memory, anthropic, interactive