Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Video course · 15 chapters · 59 min · certificate

Build AI Agents That Actually Work: Full Guide

Build AI agents that actually work: agents versus chat, the agent loop, harnesses and permissions, onboarding agents like employees, agents.md and memory, MCP tools, stacking tasks, skills as SOPs, and choosing a platform.

Become a memberAlready a member? Sign in

What you'll learn

  • Explain the difference between agents and chat
  • Describe the agent loop and harnesses
  • Onboard an agent like a real employee
  • Set up agents.md and compounding memory
  • Connect tools with MCP and stack tasks
  • Create and chain skills

Chapters

15 chapters · 58:55
  1. 3:22 01Intro Members Agents versus chat Cutting through confusing terms: what agents are compared to chat.
  2. 2:24 02Loop Members The agent loop Inside every agent step is the agent loop.
  3. 4:57 03Harness Members Harnesses, demos and permissions Harnesses like Claude Code, Codex and Antigravity, and security permissions.
  4. 5:09 04Setup Members Comparing platforms and folders Comparing results across platforms, a startup idea example, and department-based agent folders.
  5. 3:42 05Onboarding Members Onboard agents like employees Onboarding agents like real hires, using voice-to-text, and chat versus agent memory.
  6. 4:55 06Context Members agents.md and context engineering Building agents.md and why context engineering beats prompt engineering.
  7. 5:58 07Memory Members Compounding memory Memory builds up and reduces repeated errors.
  8. 4:22 08Tools Members Memory size and MCP How big memory can get, and connecting tools with MCP.
  9. 2:20 09AI OS Members High-value work in Claude Code Everyone will have an AI operating system for high-value tasks.
  10. 2:55 10Value Members Stacking, not summarizing The real value comes from stacking tasks end to end, not just summarizing.
  11. 3:04 11Skills Members What are skills? Skills as SOPs for AI.
  12. 5:28 12Skills Members Creating skills Using the built-in skill creator, e.g. for writing viral hooks.
  13. 4:58 13Examples Members Real-world skills An ads analyst skill that turns 4 hours into minutes, chaining skills, and an automated car search.
  14. 2:54 14Platforms Members Autonomous platforms and where to start Migrating agents to more autonomous platforms and which to start with.
  15. 2:27 15Scope Members Global versus project-level When to put skills, context and MCPs globally versus per project.

Jobs this course suits

Our AI checked this course against 500 jobs; these get the most out of it. Each job links to its learning path.

Software EngineersAI EngineersIT ConsultantsAutomation EngineersNo-Code DevelopersSystems AnalystsSoftware DevelopersIndependent ConsultantsFull-Stack DevelopersIT SpecialistsSystems EngineersMobile App Developers