Ai Ml · advanced
AI Agents & Agentic Frameworks
A deep technical course on building production-grade AI agents. You will learn the theory behind agentic systems — the ReAct pattern, tool use, planning, and memory — then implement real agents using LangGraph, LangChain, and AutoGen. Topics include StateGraph construction with conditional routing and checkpointing, multi-agent orchestration with supervisor and handoff patterns, long-term memory with vector stores, and deploying observable, cost-controlled agents to production. Every concept is paired with runnable Python code drawn from the LangGraph, Anthropic, and AutoGen documentation.
- 12 hours
- 24 lessons
- 6 modules
- updated May 2026
Try it before you sign up
Read a full lesson and answer 3 questions from the Module 1 quiz. No account needed.
Agents, ReAct, and the Anthropic Agent Taxonomy
6 modules, 24 lessons
Module 1 is free — lessons, hands-on walkthrough and quiz.
- readAgents, ReAct, and the Anthropic Agent Taxonomy45 min
- quizQuiz: Agent Foundations15 min
- hands-onCLI: Your First ReAct Agent with the Anthropic SDK30 min
- videoVideo: What are AI Agents?15 min
Built by the CloudaQube team
No celebrity instructor — here is exactly what goes into the course instead.
- 01 6 guided hands-on walkthroughs you run in a real environment.
- 02 6 module quizzes — every answer comes with an explanation.
- 03 Last updated May 2026.
- 04 Any module can become a hands-on lab in Labs Studio.
What you'll be able to do
- 01 Explain the ReAct pattern and distinguish it from fixed pipelines
- 02 Implement tool use with the OpenAI and Anthropic function-calling specifications
- 03 Build stateful agents with LangGraph StateGraph including conditional edges and checkpointing
- 04 Integrate short-term and long-term memory into agent loops using vector stores
- 05 Design multi-agent systems using orchestrator, subagent, and supervisor patterns
- 06 Add human-in-the-loop interrupts and streaming output to LangGraph agents
- 07 Instrument agents with LangSmith, apply token budgets, and write agent behaviour tests
- — Comfortable writing Python (functions, classes, async/await)
- — Familiarity with large language model APIs (OpenAI or Anthropic)
- — Basic understanding of prompting and chat completion formats
Before you start
How long does it take?
About 12 hours of lessons, videos and hands-on walkthroughs across 6 modules.
What’s free?
Module 1 in full — lessons, hands-on walkthrough and quiz — with no card required. Any paid plan (from $8.99/mo) unlocks all 6 modules, and starts with a 14-day free trial.
Start the course with Module 1 free.
No card required. Unlock every module from $8.99/mo when you’re ready.