Skip to content
Klay

Agents and tools

Let a model do things, and know how that fails.

  1. What an AI agent actually is Separate an agent from a chatbot and from a workflow.
  2. Tool calling Give a model a function and let it decide when to call it.
  3. The agent loop Trace think → act → observe → repeat, and where to stop it.
  4. MCP: giving agents a standard set of tools Explain what MCP standardises and why that matters.
  5. How agents fail, and guardrails Predict the common failure modes and bound them before shipping.

Ends with a graded checkpoint: 8 questions, pass mark 70%.