AI can feel overwhelming, but this hands-on course makes it practical, approachable, and fun. You will start with AI fundamentals and model mechanics like transformers and tokens, before moving into the architecture of tools, workflows, and true agents. You will build and experiment with four distinct agents, seeing firsthand how single agents evolve into a multi-agent system. Finally, you will learn how OpenClaw woks to gain the confidence needed to design, build, test, and deploy real-world AI agents.

Course resources: https://kode.wiki/3SrN8GO

Course created by @KodeKloud

❤️ Support for this channel comes from our friends at Scrimba – the coding platform that's reinvented interactive learning: https://scrimba.com/freecodecamp

Chapters
Section 1 & 2: LLM & Core Concepts
- 00:00:00 Course Welcome & Architecture Fundamentals
- 00:07:54 Hallucinations, Model Evolution, & Competitors
- 00:15:23 Developer Fundamentals & Working with APIs
- 00:17:54 Token Economics & Managing Context Windows
- 00:31:13 API Message Roles & Prompt Engineering Nuances

Section 3 & 4: Code Setup & Tool Architecture
- 00:38:29 Hands-On Lab: Practice Labs & First API Call
- 00:45:01 Multi-Turn History, API Costs, & Trade-offs
- 00:51:08 Architecture Overview: Tool Schemas & Execution Loops
- 00:58:20 Predefined AI Workflows vs. Autonomous Agents

Section 5: Building Agents from Scratch
- 01:08:16 The Core Loop: Perceive, Reason, Act
- 01:13:15 Hands-On Lab: Engineering the Standard `While` Loop
- 01:21:13 Planning Limits, Brittle Logic, & Mitigation Guardrails
- 01:26:19 Memory Managers: Sliding Windows & Vector DBs
- 01:33:56 Multi-Agent Frameworks & Inter-Agent Communication
- 01:43:08 Deconstructing Production Failures & Error Handling
- 01:52:20 Grounding Data & Prepackaged Frameworks (LangChain, Mastra)
- 02:00:25 Hands-On Lab: Building a Production Personal Assistant

Section 6: Deep Case Study (OpenClaw)
- 02:09:25 OpenClaw Codebase Tour & File Architecture
- 02:14:39 Custom Layouts, Terminal Interfaces, & Concurrency Locks
- 02:30:44 Testing Non-Deterministic Agents & LLM-as-a-Judge Evals
- 02:39:30 Observability, Tracking Performance Metrics, & Optimization Levers
- 02:51:55 Agent Security, Advanced Prompt Assemblies, & Wrap-up

🎉 Thanks to our Champion and Sponsor supporters:
👾 @omerhattapoglu1158
👾 @goddardtan
👾 @akihayashi6629
👾 @kikilogsin
👾 @anthonycampbell2148
👾 @tobymiller7790
👾 @rajibdassharma497
👾 @CloudVirtualizationEnthusiast
👾 @adilsoncarlosvianacarlos
👾 @martinmacchia1564
👾 @ulisesmoralez4160
👾 @_Oscar_
👾 @jedi-or-sith2728
👾 @justinhual1290

--

Learn to code for free and get a developer job: https://www.freecodecamp.org

Read hundreds of articles on programming: https://freecodecamp.org/news