Skip to content
Agent Builder
Join
CurriculumPricingGlossaryFAQSign inAccount
Theme

Curriculum

The complete AI agents course

12 modules, 65 lessons, about 11 hours of reading. Start at the beginning or jump to what you need — every lesson stands on its own.

00

Start Here

Beginner

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

5 lessons · 41 min

  1. 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.5 minFree
  2. 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 minFree
  3. 3Setting Up Your Agent ToolkitInstall and configure the essentials — a chat assistant, a coding agent, a terminal, and an API key — so you're ready for every lesson.11 minFree
  4. 4Your First Agent Task in 15 MinutesHands-on: hand an agent a real multi-step task, watch it plan, use tools, and verify its own work — then learn what just happened.8 minFree
  5. 5The Agent Builder MindsetThe mental shifts that separate people who get great results from agents from those who get frustrated: delegation, verification, and iteration.8 minFree
01

How Agents Work

Beginner

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.

6 lessons · 55 min

  1. 1LLMs in Plain EnglishHow large language models actually work — tokens, prediction, training, and reasoning — explained without math so you can predict their behavior.9 minFree
  2. 2The Agent Loop: Think, Act, ObserveThe simple loop at the heart of every agent. Trace a real agent run step by step and learn where things go right and wrong.9 min
  3. 3Tools and Function CallingHow models call tools: schemas, tool calls, tool results, and why well-described tools make or break an agent.11 min
  4. 4Context Windows, Tokens, and CostWhat fits in an agent's working memory, how tokens translate to dollars, and how to keep long-running agents sharp and affordable.9 min
  5. 5Choosing the Right Model for the JobFrontier vs. fast models, reasoning effort, cost/latency trade-offs, and a practical decision framework for picking a model per task.8 min
  6. 6Agents vs. Workflows: When to Use WhichNot everything should be an agent. Learn the spectrum from single prompts to chains to autonomous agents and how to choose.9 min
02

Working with Coding Agents

Beginner

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.

7 lessons · 68 min

  1. 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.10 minFree
  2. 2Writing Tasks an Agent Can Actually FinishThe anatomy of a great agent task: goal, context, constraints, and a definition of done. Includes before/after rewrites of real prompts.9 min
  3. 3Project Instructions: CLAUDE.md and AGENTS.mdTeach an agent your codebase once. What to put in project instruction files, what to leave out, and templates you can copy.9 min
  4. 4Plan First, Then ExecuteWhy planning mode prevents most agent disasters, how to review a plan, and how to break large features into agent-sized steps.8 min
  5. 5Reviewing Agent-Written CodeA fast, reliable review process for code you didn't type: tests first, diff reading strategies, and red flags to catch.8 min
  6. 6Git, Branches, and Worktrees for Agent WorkUse git as your safety net: small commits, branches per task, worktrees for parallel agents, and easy rollbacks.8 min
  7. 7Building a Full App Agentically, Start to FinishA complete walkthrough of building and deploying a real web app with a coding agent — from blank folder to live URL.16 min
03

Prompting & Context Engineering

Intermediate

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

6 lessons · 56 min

  1. 1From Prompt Engineering to Context EngineeringWhy the best results come from curating everything the model sees — not from magic phrases — and a framework for doing it.9 min
  2. 2Writing System Prompts That Hold UpStructure, tone, priorities, and edge cases: how to write system prompts that behave consistently over thousands of runs.10 min
  3. 3Specs, Examples, and ConstraintsTurn fuzzy requests into precise specs. When to use examples, how to phrase constraints, and how to get structured output reliably.10 min
  4. 4Managing Long ContextCompaction, summaries, scratchpads, and just-in-time retrieval: techniques that keep long-running agents focused and accurate.9 min
  5. 5Giving Agents MemoryShort-term vs. long-term memory, file-based memory, retrieval, and how to design memory that helps instead of polluting context.9 min
  6. 6Skills and Reusable InstructionsPackage your best workflows into skills, commands, and templates that any agent can load on demand.9 min
04

Tools & the Model Context Protocol

Intermediate

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

5 lessons · 59 min

  1. 1Designing Tools Agents Love to UseNaming, descriptions, parameters, and error messages: the craft of designing tools that models call correctly on the first try.10 min
  2. 2What Is MCP and Why It MattersThe Model Context Protocol explained: hosts, clients, servers, tools, resources, and prompts — and why it became the standard.10 min
  3. 3Connecting MCP Servers to Your AgentsInstall and configure MCP servers in popular agents, choose trustworthy servers, and troubleshoot connections.12 min
  4. 4Building Your First MCP ServerStep by step: build, test, and connect a working MCP server in TypeScript that exposes your own tools to any agent.15 min
  5. 5Permissions, Approvals, and Tool SafetyDecide which tools run automatically and which need a human. Permission modes, allowlists, and designing safe destructive actions.12 min
05

Build Your First Agent from Scratch

Intermediate

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

6 lessons · 75 min

  1. 1Project Setup: SDKs, Keys, and Your First API CallSet up a TypeScript project, store your API key safely, and make your first model call — with a Python equivalent for every step.10 min
  2. 2A Minimal Agent Loop in 60 LinesWrite a complete tool-using agent loop from scratch and see exactly how messages, tool calls, and results flow.11 min
  3. 3Adding Real Tools: Files, Web, and APIsGive your agent useful abilities — reading and writing files, fetching web pages, and calling APIs — with safe implementations.14 min
  4. 4Streaming and a Better User ExperienceStream tokens and tool activity to users so your agent feels fast and trustworthy, in a CLI and a web UI.12 min
  5. 5Error Handling, Retries, and Stop ConditionsMake your agent robust: tool errors the model can recover from, API retries, iteration limits, and budgets.16 min
  6. 6Leveling Up with an Agent SDKWhen to stop hand-rolling the loop. Rebuild your agent with an agent SDK and get context management, permissions, and subagents for free.12 min
06

Multi-Agent Systems

Advanced

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

5 lessons · 52 min

  1. 1When (and When Not) to Go Multi-AgentThe real costs and benefits of multi-agent systems, and a checklist for deciding if your problem needs more than one agent.8 min
  2. 2The Orchestrator–Worker PatternBuild a lead agent that breaks work into subtasks, dispatches workers, and synthesizes results — the most useful multi-agent pattern.10 min
  3. 3Subagents and DelegationUse subagents to protect your main context, specialize behavior, and delegate well — with briefs that actually work.10 min
  4. 4Running Agents in ParallelFan out work across many agents at once without conflicts: isolation, merging results, and controlling cost.13 min
  5. 5Handoffs and Shared StatePass work between agents reliably using artifacts, structured handoff notes, and shared files instead of giant transcripts.11 min
07

Agents for Everyday Work

Beginner

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

5 lessons · 40 min

  1. 1Research Agents: From Question to ReportRun deep research with agents: scoping questions, verifying sources, and producing reports you can trust.9 min
  2. 2Automating Repetitive BusyworkFind the tasks worth automating and hand them to agents: inbox triage, file cleanup, form filling, and recurring reports.8 min
  3. 3Data Analysis with AgentsLet agents clean spreadsheets, run analyses, and build charts — while you stay in control of the conclusions.7 min
  4. 4Writing and Content WorkflowsUse agents as researchers, editors, and producers in a content pipeline without losing your voice or your credibility.7 min
  5. 5Scheduled and Background AgentsAgents that work while you sleep: scheduled runs, triggers, notifications, and keeping unattended agents safe.9 min
08

Evals, Testing & Reliability

Advanced

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

5 lessons · 56 min

  1. 1Why Evals Are Your SuperpowerEvals turn 'it seems better' into numbers. Learn the types of evals and the minimum viable eval for any agent.8 min
  2. 2Building Your First Eval SetCollect realistic test cases, define success criteria, and write a small eval harness that runs in minutes.13 min
  3. 3LLM-as-Judge: Grading at ScaleUse models to grade open-ended outputs with rubrics — and calibrate the judge so you can trust its scores.12 min
  4. 4Tracing and ObservabilityCapture every model call, tool call, and decision so you can see exactly what your agent did and why.12 min
  5. 5Debugging Agent FailuresA systematic playbook for the most common agent failures: loops, wrong tools, hallucinated facts, and premature stops.11 min
09

Safety, Security & Guardrails

Advanced

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

5 lessons · 47 min

  1. 1The Agent Threat ModelWhat can go wrong when software can act on its own — and the 'lethal trifecta' of risks to design around.8 min
  2. 2Prompt Injection and How to Defend Against ItHow hidden instructions in web pages, emails, and files hijack agents, and layered defenses that actually reduce risk.10 min
  3. 3Sandboxing and Least PrivilegeContainers, VMs, scoped credentials, and network rules: limit the blast radius of any agent mistake.10 min
  4. 4Secrets, PII, and Data HandlingKeep API keys out of prompts and logs, handle personal data responsibly, and understand what data leaves your machine.9 min
  5. 5Human-in-the-Loop DesignPut humans in the right places — approvals, reviews, and escalations — without turning your agent into a nag.10 min
10

Shipping Agents to Production

Advanced

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

5 lessons · 52 min

  1. 1Architecture for Production AgentsQueues, durable execution, state, and sessions: the architecture that keeps long-running agents reliable.11 min
  2. 2Controlling Cost and LatencyPrompt caching, model routing, batching, and budgets — the levers that cut agent costs by an order of magnitude.10 min
  3. 3Deploying Your AgentShip your agent as an API and a web app: environment config, secrets, background jobs, and a deploy you can repeat.13 min
  4. 4Monitoring and Improving in ProductionDashboards, alerts, feedback loops, and turning production failures into new evals.9 min
  5. 5Turning Agents into ProductsFind problems worth solving, price agent products, and design UX that earns user trust.9 min
11

Capstone Projects

Advanced

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

5 lessons · 69 min

  1. 1Capstone 1: A Deep Research AssistantBuild a research agent that plans queries, reads sources, tracks citations, and writes a sourced report.17 min
  2. 2Capstone 2: A Customer Support AgentBuild a support agent with a knowledge base, account lookup tools, escalation rules, and an eval suite.15 min
  3. 3Capstone 3: An Autonomous Coding PipelineWire up a pipeline where agents pick up issues, implement changes in isolated branches, run tests, and open pull requests for review.15 min
  4. 4Capstone 4: Your Personal Ops AgentBuild a scheduled agent that triages your inbox, summarizes your day, and drafts replies — with you in control.14 min
  5. 5Where to Go NextHow to keep your skills current as models and tools evolve, plus a roadmap of next projects to build.8 min