Learn AI Agents
Agents choose tools or steps toward a goal. Adaptive behaviour needs explicit permissions and limits.
Read each short explanation, work through the example, then answer a pop quiz. Every answer explains the reasoning. Incorrect answers unlock a fresh question on the same idea; the full lesson contains ten questions.
01Understand the basics
Ready to learnAn AI agent chooses steps or tools toward a goal. This can help when the path varies, but each extra choice creates opportunities for mistakes and loops. The surrounding system must enforce tool permissions and stopping rules independently of the model.
02Set enforceable budgets
Ready to learnBound iterations, elapsed time and cost. Stop when a limit is reached, record what happened and provide an escalation path. A prompt asking the model to stop is weaker than a system-enforced limit.
Try a different value
03Treat observations as data
Ready to learnRetrieved pages and tool results may contain instructions from untrusted sources. They must not grant permissions or override the user task. Give each tool only the access required.
You’ve practised all three sections.
First-attempt understanding and later practice are shown separately. Keep practising with the related tools or continue through the suggested path.
Put it to work
Apply what you’ve learned using the related tools.