Intermediate Free 90 min total

AI Agents and
Agentic Systems

Agents are AI systems that do not just answer questions. They plan, use tools, call APIs, remember context, and work with other agents to complete real tasks. This course shows you exactly how they work and how to build one yourself.

Start Module 1 → Talk to Arjun
Is this course for you?
This IS for you if
  • You already use AI tools and want to understand how agents actually work
  • You are a product manager, engineer, or executive evaluating agentic AI
  • You want to build a simple agent or understand what the vendors are selling
  • You have completed the Prompt Engineering course and are ready for the next level
This is NOT for you if
  • You have never used an AI tool before (start with Prompt Engineering first)
  • You want deep reinforcement learning theory
  • You need a production-grade multi-agent framework tutorial with code
ⓘ
Prerequisites: basic AI familiarity. You should know what a prompt is and have used an AI assistant at least a few times. If you want to start from zero, take Prompt Engineering Fundamentals first. No coding required for this course.
What you will be able to do
✓Explain what makes an AI agent different from a chatbot
✓Describe how agents use tools and call functions to take action
✓Explain the ReAct reasoning loop and why it works
✓Describe how agents store and retrieve memory across steps
✓Identify the common failure modes of agentic systems
✓Build a simple agent loop and know when to use multi-agent architectures

The Six Modules

01
What Is an AI Agent?
The four things that make an agent different from a chatbot: perception, reasoning, action, and feedback. Why agents matter now and what they can actually do.
15 min
→ 02
Tool Use and Function Calling
How agents call external tools, APIs, and functions. The Toolformer approach to self-supervised tool learning, and how modern frameworks implement it.
15 min
→ 03
Memory and Context Management
The four types of memory an agent can use: in-context, external retrieval, episodic, and procedural. Why context windows run out and how agents work around it.
15 min
→ 04
Multi-Agent Systems
How multiple agents collaborate: orchestrator and worker patterns, peer-to-peer coordination, and when splitting work across agents actually helps versus hurts.
15 min
→ 05
Agentic Failure Modes
Why agents go wrong: reasoning errors, tool misuse, infinite loops, compounding mistakes, and the safety issues unique to systems that take real-world action.
15 min
→ 06
Building Your First Agent
A practical walkthrough: picking a task, defining tools, writing the system prompt, testing the reasoning loop, and knowing when to hand off to a human.
15 min
→

Supporting Blog Series

Six articles covering every angle of agentic AI. Read any one independently or work through them alongside the course.

01 What is an AI agent? 02 How AI agents use tools 03 AI agent memory explained 04 Multi-agent systems explained 05 AI agent failure modes 06 How to build an AI agent

Related Courses

Beginner
Prompt Engineering Fundamentals
Beginner
Model Development Fundamentals
All Courses
AJ University: 90 Free AI Courses

Ready? Start with Module 1.

No account. No paywall. No credit card. Just start learning.

Begin Module 1 →