Skip to content
Agent Builder
Join
CurriculumPricingGlossaryFAQSign inAccount
Theme

Pricing

Simple pricing. Lifetime access.

One payment unlocks every lesson, prompt, exercise, and capstone — plus all future updates. Not sure yet? Read the 7 free lessons first, no account needed.

65
Lessons
12
Modules
~11h
Reading

Complete course

Lifetime access
$149USD, one-time

Pay once. No subscription. Keep it forever.

  • All 65 lessons across 12 modules
  • Hundreds of copy-paste prompts and templates
  • A hands-on exercise in every lesson
  • Four 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.

What's inside

The full curriculum, module by module.

00Start HereYour on-ramp to working with AI agents

Get oriented, set up your tools, and complete a real task with an AI agent in your first 15 minutes. No experience required. Module overview →

  1. 0.1Welcome: What You'll Be Able to DoFree5 min
  2. 0.2What Is an AI Agent, Really?Free9 min
  3. 0.3Setting Up Your Agent ToolkitFree11 min
  4. 0.4Your First Agent Task in 15 MinutesFree8 min
  5. 0.5The Agent Builder MindsetFree8 min
01How Agents WorkThe mental model behind every agent

Understand what's happening under the hood: language models, the agent loop, tool calling, context windows, and how to pick the right model for a job. Module overview →

  1. 1.1LLMs in Plain EnglishFree9 min
  2. 1.2The Agent Loop: Think, Act, Observe9 min
  3. 1.3Tools and Function Calling11 min
  4. 1.4Context Windows, Tokens, and Cost9 min
  5. 1.5Choosing the Right Model for the Job8 min
  6. 1.6Agents vs. Workflows: When to Use Which9 min
02Working with Coding AgentsShip software with an AI pair that does the typing

Use Claude Code, Codex, Cursor, and similar tools to build real software. Write tasks agents can finish, review their work, and run them safely with git. Module overview →

  1. 2.1The Coding Agent LandscapeFree10 min
  2. 2.2Writing Tasks an Agent Can Actually Finish9 min
  3. 2.3Project Instructions: CLAUDE.md and AGENTS.md9 min
  4. 2.4Plan First, Then Execute8 min
  5. 2.5Reviewing Agent-Written Code8 min
  6. 2.6Git, Branches, and Worktrees for Agent Work8 min
  7. 2.7Building a Full App Agentically, Start to Finish16 min
03Prompting & Context EngineeringGive agents exactly what they need — nothing more

Move beyond clever prompts to deliberate context design: system prompts, specs, examples, long-context management, memory, and reusable skills. Module overview →

  1. 3.1From Prompt Engineering to Context Engineering9 min
  2. 3.2Writing System Prompts That Hold Up10 min
  3. 3.3Specs, Examples, and Constraints10 min
  4. 3.4Managing Long Context9 min
  5. 3.5Giving Agents Memory9 min
  6. 3.6Skills and Reusable Instructions9 min
04Tools & the Model Context ProtocolConnect agents to everything

Design tools agents use correctly, understand MCP, connect existing MCP servers, and build your own server to give agents new superpowers. Module overview →

  1. 4.1Designing Tools Agents Love to Use10 min
  2. 4.2What Is MCP and Why It Matters10 min
  3. 4.3Connecting MCP Servers to Your Agents12 min
  4. 4.4Building Your First MCP Server15 min
  5. 4.5Permissions, Approvals, and Tool Safety12 min
05Build Your First Agent from ScratchWrite the loop yourself and truly understand it

Build a working agent in code: API setup, a minimal agent loop, real tools, streaming, error handling — then level up with an agent SDK. Module overview →

  1. 5.1Project Setup: SDKs, Keys, and Your First API Call10 min
  2. 5.2A Minimal Agent Loop in 60 Lines11 min
  3. 5.3Adding Real Tools: Files, Web, and APIs14 min
  4. 5.4Streaming and a Better User Experience12 min
  5. 5.5Error Handling, Retries, and Stop Conditions16 min
  6. 5.6Leveling Up with an Agent SDK12 min
06Multi-Agent SystemsCoordinate teams of agents

Learn when multiple agents beat one, and how to build orchestrator–worker systems, subagents, parallel runs, and clean handoffs. Module overview →

  1. 6.1When (and When Not) to Go Multi-Agent8 min
  2. 6.2The Orchestrator–Worker Pattern10 min
  3. 6.3Subagents and Delegation10 min
  4. 6.4Running Agents in Parallel13 min
  5. 6.5Handoffs and Shared State11 min
07Agents for Everyday WorkPut agents to work beyond code

Practical playbooks for research, busywork automation, data analysis, writing, and scheduled background agents — no engineering degree required. Module overview →

  1. 7.1Research Agents: From Question to Report9 min
  2. 7.2Automating Repetitive Busywork8 min
  3. 7.3Data Analysis with Agents7 min
  4. 7.4Writing and Content Workflows7 min
  5. 7.5Scheduled and Background Agents9 min
08Evals, Testing & ReliabilityKnow your agent works — with evidence

Stop guessing. Build eval sets, grade with code and LLM judges, trace every run, and systematically debug agent failures. Module overview →

  1. 8.1Why Evals Are Your Superpower8 min
  2. 8.2Building Your First Eval Set13 min
  3. 8.3LLM-as-Judge: Grading at Scale12 min
  4. 8.4Tracing and Observability12 min
  5. 8.5Debugging Agent Failures11 min
09Safety, Security & GuardrailsPowerful agents, safely

Understand the agent threat model, defend against prompt injection, sandbox execution, protect secrets and data, and design human-in-the-loop controls. Module overview →

  1. 9.1The Agent Threat Model8 min
  2. 9.2Prompt Injection and How to Defend Against It10 min
  3. 9.3Sandboxing and Least Privilege10 min
  4. 9.4Secrets, PII, and Data Handling9 min
  5. 9.5Human-in-the-Loop Design10 min
10Shipping Agents to ProductionFrom prototype to product

Architect, deploy, monitor, and scale agents for real users — and turn what you build into a product people pay for. Module overview →

  1. 10.1Architecture for Production Agents11 min
  2. 10.2Controlling Cost and Latency10 min
  3. 10.3Deploying Your Agent13 min
  4. 10.4Monitoring and Improving in Production9 min
  5. 10.5Turning Agents into Products9 min
11Capstone ProjectsBuild four real agents end to end

Put it all together with four guided builds: a research assistant, a support agent, an autonomous coding pipeline, and a personal ops agent. Module overview →

  1. 11.1Capstone 1: A Deep Research Assistant17 min
  2. 11.2Capstone 2: A Customer Support Agent15 min
  3. 11.3Capstone 3: An Autonomous Coding Pipeline15 min
  4. 11.4Capstone 4: Your Personal Ops Agent14 min
  5. 11.5Where to Go Next8 min

Frequently asked questions

Do I need to know how to code?

No. The first half of the course — setup, how agents work, coding agents, context engineering, and everyday-work playbooks — is written for non-programmers. The build-from-scratch modules use TypeScript, but they're written so 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 65 lessons across 12 modules (about 11 hours of focused reading), hundreds of copy-paste prompts, hands-on exercises, four full capstone builds, progress tracking, and every future update to the course.

Is this a subscription?

No. It's a single one-time payment of $149. No recurring charges, ever.

Can I try it before buying?

Yes. 7 lessons are completely free, including the entire Start Here module, the first lesson on how LLMs work, and the coding-agent landscape. No account required.

Which AI tools does the course use?

The principles work with any modern agent. Examples use popular tools such as Claude Code, OpenAI Codex, Cursor, and the Claude and ChatGPT apps, plus the Anthropic API and the Model Context Protocol (MCP) for building. Where we show a specific product, we focus 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 plan for a coding agent or a small amount of API credit — a few dollars covers every build exercise in the course if you follow the cost tips we teach.

How is this different from free YouTube videos and blog posts?

It's a complete, ordered path instead of scattered tips: each lesson builds on the last, every concept comes with a practical exercise, and the advanced modules (evals, safety, production) cover the things most tutorials skip — the parts that make agents reliable enough to trust.

How long does it take?

Most people finish the core modules in two to three weeks at 30–45 minutes a day. Every lesson stands on its own, so you can also jump straight to what you need.

Is the course kept up to date?

Yes. Agent tooling moves fast, and lessons are revised as tools change. Updates are included in your one-time purchase.

What if it's not for me?

If the course isn't right for you, email support@agentbuildercourse.com within 30 days of purchase for a full refund.

How do I sign in after buying?

You're signed in automatically after checkout. On any other device, enter the email you purchased with on the sign-in page and we'll send you a one-click sign-in link — no password to remember.

Can I buy for my team?

Yes — email support@agentbuildercourse.com with the number of seats and we'll set you up with team access and an invoice.