Skip to content

AI Agents

When a model is allowed to act, not just answer.

LLM vs agentagentic systemsreasoningplanningtoolsmemoryloopshuman approval

Lessons

  1. 24.1LLM vs AI agent vs agentic systemPeople use these three words as if they meant the same thing. They don't, and picking the wrong one can be very expensive. 30 min LLM → agent → agentic system
  2. 24.2Planning, loops and knowing when to stopAn agent is a loop around a model. The hard part isn't starting the loop, it's planning well and knowing when to stop. 30 min LLM → agent → agentic system
  3. 24.3Human in the loop: approvals, thresholds and escalationAgents that act in the real world need people at the right moments, not at every step. Here's how to choose those moments. 30 min Pick the tools
  4. 24.4Design a hotel booking agent end to endPut it all together: design a real hotel booking agent where the AI is one part among many, and most of the safety lives around it. 30 min Agent memory manager AI cost simulator

On the job: try it on your own project

Pick one repetitive multi-step task at work, such as triaging tickets or preparing a report. Write the steps a human follows, the tools they use and the decisions that need approval. Ask Claude Code to critique it as an agent design. Write a one-page agent brief: plain LLM call or agent, the loop, the tools, and where a human must approve.

Can you do this now?

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