Introduction to AI Agents

Introduction to AI Agents

Duration: 2 Days

Description

An agent is what you get when a language model stops just answering questions and starts deciding what to do next — reasoning through a task, calling tools, and taking action toward a goal instead of producing a single response. This course introduces that shift properly: how an agent decides what step comes next, how tool use and function calling actually work under the hood, and the guardrails that keep an agent focused on the task instead of wandering off or taking an unsafe action. Hands-on exercises have participants build working agents from the ground up, so the concepts are demonstrated rather than described.
Class time is divided between instructor-led explanation (40 percent) and hands-on development (60 percent).

Audience

This course is for developers who can already build LLM-powered features (calling a model’s API, working with prompts) and want to move into agent development specifically. It’s the right starting point before reaching for a heavier agent framework like LangGraph — understanding the underlying loop makes the framework’s abstractions make sense instead of feeling arbitrary.

Objectives

  • Explain what AI agents are and how they differ from simple LLM calls
  • Describe the reason-act loop and how agents make decisions
  • Implement tool use and function calling
  • Give agents access to data and external actions safely
  • Keep agents reliable, bounded, and observable
  • Build a simple working agent

Prerequisites

Participants should be comfortable building basic LLM features. The following will help:

  • Working knowledge of Python (see Python Foundations)
  • Experience calling AI model APIs (see AI for Developers)
  • Familiarity with LLM application patterns (see Building LLM Applications)

Related AI Courses

See the full AI training roadmap and course directory for how this fits into a broader learning path.

New to a quick, guided first agent build first? See Beginner’s Guide to Agentic AI Micro-Credential. Ready to go further? Continue with Advanced AI Agents for multi-agent and production-grade systems, or LangChain & LangGraph to build agents with a full orchestration framework.

Course Outline

  • Module 1 – Course Introduction
    • Welcome and objectives
    • What is an AI agent?
    • Agents versus chatbots versus workflows
  • Module 2 – How Agents Work
    • The reason-act loop
    • Planning and decision-making
    • Memory and context for agents
    • Where agents succeed and where they struggle
  • Module 3 – Tools and Function Calling
    • Giving agents tools
    • Function calling fundamentals
    • Designing good tool interfaces
    • Hands-on exercise: an agent that uses a tool
  • Module 4 – Data and Actions
    • Connecting agents to data sources
    • Taking real-world actions safely
    • Permissions and guardrails
    • Confirming and validating agent actions
  • Module 5 – Reliability and Observability
    • Keeping agents on task
    • Handling failures and loops
    • Logging and tracing agent behavior
    • Cost and latency considerations
  • Module 6 – Building an Agent
    • Designing a simple agent end to end
    • Hands-on exercise: build and test an agent
  • Module 7 – Course Wrap-Up
    • Key takeaways
    • Resources for continued learning
    • Next steps toward advanced agents