Learn to work with AI agents —
and build your own.
The practical course for professionals and developers. Delegate real work to agents, ship software with coding agents, and build reliable agents that run in production.
Save $70 · One-time payment · Lifetime access · 30-day money-back guarantee
- 130
- lessons
- 14
- modules
- ~26h
- of reading
- 7
- capstone builds
Examples use the tools teams rely on
- Claude Code
- OpenAI Codex
- Cursor
- GitHub Copilot
- Model Context Protocol
- Claude Agent SDK
- Anthropic API
Why this course
Most AI tutorials stop at the demo. This one goes to production.
A complete, ordered path that covers the parts most courses skip: verification, safety, evals, cost, and deployment.
Understand how agents really work
The model, the loop, tools, context, and cost — explained clearly enough that you can predict when an agent will succeed and why it fails.
Get real work done with agents
Write tasks agents can finish, use coding agents like Claude Code and Codex with confidence, and automate research, analysis, and busywork.
Build and ship your own
Write the agent loop from scratch, connect tools with MCP, coordinate multiple agents, and run them safely in production with evals and guardrails.
Curriculum
14 modules. 130 lessons. One complete path.
Start at the beginning or jump to the module you need — every lesson stands on its own.
Start Here
Your on-ramp to working with AI agents
- Welcome: What You'll Be Able to Do
- What Is an AI Agent, Really?
- A Tour of What Agents Can Do Today
- + 3 more
How Agents Work
The mental model behind every agent
- LLMs in Plain English
- Reasoning Models and Extended Thinking
- The Agent Loop: Think, Act, Observe
- + 7 more
Working with Coding Agents
Ship software with an AI pair that does the typing
- The Coding Agent Landscape
- Writing Tasks an Agent Can Actually Finish
- Project Instructions: CLAUDE.md and AGENTS.md
- + 10 more
Prompting & Context Engineering
Give agents exactly what they need — nothing more
- From Prompt Engineering to Context Engineering
- Writing System Prompts That Hold Up
- Specs, Examples, and Constraints
- + 8 more
Tools & the Model Context Protocol
Connect agents to your data, APIs, and apps
- Designing Tools Agents Love to Use
- Connecting Agents to Databases and APIs
- What Is MCP and Why It Matters
- + 6 more
Build Your First Agent from Scratch
Write the loop yourself and truly understand it
- Project Setup: SDKs, Keys, and Your First API Call
- A Minimal Agent Loop in 60 Lines
- Adding Real Tools: Files, Web, and APIs
- + 8 more
Multi-Agent Systems
Coordinate teams of agents
- When (and When Not) to Go Multi-Agent
- The Orchestrator–Worker Pattern
- Subagents and Delegation
- + 6 more
Beyond Text: Vision, Browser & Voice Agents
Agents that see, click, and talk
- Vision Agents: Images, Screenshots, and PDFs
- Document Processing Pipelines
- Browser Agents: Automating the Web
- + 3 more
Agents for Everyday Work
Put agents to work beyond code
- Research Agents: From Question to Report
- Automating Repetitive Busywork
- Agents for Email and Calendar
- + 8 more
Evals, Testing & Reliability
Know your agent works — with evidence
- Why Evals Are Your Superpower
- Building Your First Eval Set
- LLM-as-Judge: Grading at Scale
- + 6 more
Safety, Security & Guardrails
Let agents act without losing control
- The Agent Threat Model
- Prompt Injection and How to Defend Against It
- Tool Poisoning and Supply-Chain Security
- + 6 more
Shipping Agents to Production
From prototype to product
- Architecture for Production Agents
- Durable Execution for Long-Running Agents
- Controlling Cost and Latency
- + 8 more
Agents in Organizations
Make agents work for a whole team
- Finding High-Value Agent Use Cases
- Rolling Out Agents to a Team
- Training Your Team to Work with Agents
- + 4 more
Capstone Projects
Build seven real agents end to end
- Capstone 1: A Deep Research Assistant
- Capstone 2: A Customer Support Agent
- Capstone 3: An Autonomous Coding Pipeline
- + 5 more
Inside every lesson
Designed to be used, not just read.
Focused lessons, most under 15 minutes, with worked examples, before-and-after comparisons, and the exact prompts to try.
- Copy-ready prompts
- More than 200 prompts and templates, each one click to copy.
- Code that runs
- Complete TypeScript examples, with Python versions for most of Module 5.
- An exercise in every lesson
- Apply each idea right away, usually to your own work.
- Search in a keystroke
- Press ⌘K or Ctrl+K to find any lesson, section, or term in the 109-term glossary.
Who it's for
A path for wherever you're starting.
Professionals & founders
Take real work off your plate — research, reports, analysis, operations — without learning to code first.
Recommended modules
Developers
Ship faster with coding agents and add agent features to the products you build.
Recommended modules
Builders
Turn agents into products, and make them reliable, safe, and affordable to run.
Recommended modules
Try it free
8 complete lessons. No signup.
Read all of Module 0 plus the first lessons of Modules 1 and 2, and have an agent finish its first real task for you today.
- 0.1Welcome: What You'll Be Able to DoHow this course is structured, who it's for, and the concrete skills you'll walk away with — from delegating work to agents to building your own.6 min
- 0.2What Is an AI Agent, Really?A no-hype definition of AI agents: a model, a loop, and tools. Learn how agents differ from chatbots and why they suddenly got useful.9 min
- 0.3A Tour of What Agents Can Do TodayA guided tour of the agents you can use right now — chat assistants, coding agents, research agents, browser agents, and scheduled agents — and what each is genuinely good at.10 min
- 0.4Setting Up Your Agent ToolkitInstall and check everything the course uses — a chat assistant, a terminal, git, Node.js, a coding agent, and an Anthropic API key — in one sitting.11 min
- 0.5Your First Agent Task in 15 MinutesHands-on: have an agent clean up a messy expense spreadsheet, prove its work with a test, and write up the results — without typing a line of code.9 min
- 0.6The Agent Builder MindsetThe mental shifts that separate people who get great results from agents from those who get frustrated: delegation, verification, and iteration.8 min
- 1.1LLMs in Plain EnglishHow large language models work — tokens, prediction, training, and context — explained without math, so you can predict when they'll shine, slip, or make things up.9 min
- 2.1The Coding Agent LandscapeA tour of terminal agents, IDE agents, and cloud agents — Claude Code, Codex, Cursor, and more — and how to choose between them.11 min
Launch offer · 47% off
The complete course for $79 — for the first 100 students.
Normally $149. When the 100 launch seats are gone, the price goes back up. No subscription, tiers, or upsells.
- Instant access after checkout
- Sign in anywhere with a one-click email link
- Team licenses available on request
- Secure checkout with Stripe
Complete course
Lifetime accessYou save $70. Launch price for the first 100 students only.
- All 130 lessons across 14 modules
- More than 200 copy-paste prompts and templates
- A hands-on exercise in every lesson
- 7 complete capstone builds with code
- Progress tracking across devices
- Every future update, included
30-day money-back guarantee. If it's not for you, email us for a full refund.
Do I need to know how to code?
No. Start Here, Agents for Everyday Work, and Agents in Organizations need no code at all, and How Agents Work and Prompting & Context Engineering explain every idea in plain language before showing any code. The build modules use TypeScript, but you can follow along by having a coding agent do the typing while you learn to direct and review it.
What exactly do I get?
Lifetime access to all 130 lessons across 14 modules (about 26 hours of reading), more than 200 copy-paste prompts, a hands-on exercise in every lesson, 7 complete capstone builds, progress tracking, and every future update to the course.
Is this a subscription?
No. It's a single one-time payment with lifetime access and no recurring charges.
Is the launch price really limited?
Yes. The $79 launch price applies only to the first 100 students. The seat counter on the site counts real, paid purchases. When the seats are gone, the price returns to $149 automatically.
Can I try it before buying?
Yes. 8 lessons are completely free, including the entire Start Here module, LLMs in Plain English, and The Coding Agent Landscape. No account required.
Which AI tools does the course use?
The principles work with any modern agent. Examples use widely used tools such as Claude Code, OpenAI Codex, Cursor, and the Claude and ChatGPT apps, plus the Anthropic API, the Claude Agent SDK, and the Model Context Protocol (MCP) for building. Where a lesson shows a specific product, it focuses on the skills that transfer.
Will I need to pay for AI tools too?
Many exercises work on free tiers. For the coding-agent and build modules you'll want a paid coding-agent plan or some prepaid API credit. The build exercises make small, short runs, and the course shows you how to measure what each run costs and set a spend limit before you start.
How is this different from free YouTube videos and blog posts?
It's a complete, ordered path instead of scattered tips: lessons build on each other, every lesson has a hands-on exercise, and the advanced modules (evals, safety, production) cover what most tutorials skip — the parts that make agents reliable enough to trust.
Built the way it teaches
This site, its checkout, search, and all 130 lessons were planned, written, reviewed, and shipped by AI agents — directed by one person who decided what to build and checked the results. That's the skill set this course teaches.
Launch offer · 47% off · 100 seats left
Get the whole course for $79.
The launch price is only for the first 100 students. After that it goes back to $149.