Lesson 5 · Generative AI
AI Agents & Automation
9 min
You'll be able to
- Define an AI agent and its loop
- Understand tools and tool calling
- See how agents compose into workflows
An AI agent is a system that uses a model to reason, decides which action to take, calls tools to act, observes the result, and repeats — closing a loop until a goal is reached.
The agent loop
- Reason — interpret the user's goal and current state.
- Plan — choose the next action.
- Act — call a tool (search, run code, call an API).
- Observe — see the outcome and feed it back in.
- Repeat — until the goal is satisfied.
Tool use is what turns a language model into an agent: the model decides to call a function, the system executes it, and the result returns to the model. This is how assistants look up the weather, run calculations, and take real actions.
Challenge
Design an agent
Describe an agent that helps plan a trip: what tools it needs, what loop it runs, and one safety guardrail you would add.
Knowledge Check
AI agents
What makes a language model an 'agent'?
Agents can only produce text; they cannot interact with external systems.
Answer all questions to submit.