Index Ai Academy
Free courses · 25 lessons · about 17 hours

Free AI agents course

Learn how to build AI agents by building one: tools, the agent loop, MCP, permissions, context management and evals, ending with a coding agent that stops when its tests pass.

Create a free account Read the start of the first lesson

Already have an account? Sign in

What you'll be able to do

  • Give a model tools, and run the full round trip from question to final answer
  • Turn that into a loop with a turn limit, approval for risky tools and a log of steps
  • Choose between workflows and agents, and between routing, orchestrator-workers and other patterns
  • Explain what MCP solves, and judge whether a server is safe to connect
  • Decide each tool call with allow, ask and deny rules, and defend against prompt injection
  • Treat the context window as a budget: clear old tool results and compact long conversations
  • Evaluate an agent by the end state it produces, across repeated runs
  • Build a coding agent whose harness, not the model, decides when the work is done

Who it's for

For developers who have called a model from code and want to know what an agent is made of. You'll write the loop, the tools and the guardrails yourself, so no framework is a black box.

Before you start

Some lessons here build on earlier ones in the academy. The placement test can mark off what you already know, and you can open any of them first:

New to Python? Start with the free Python for AI course.

The 25 lessons

One is free with no account, and a free account opens the rest.

  1. Structured outputGet reliable JSON back that your code can use.
  2. Tool useLet the model call your functions (function calling).
  3. Conversations and memoryAPIs are stateless: how chat history and memory really work.
  4. The agent loopModel → tool → result → model, until the task is done.
  5. Model Context ProtocolA standard way to plug tools and data into any AI app.
  6. Agent design patternsRouting, orchestrator-workers and when not to build an agent.
  7. Prompt injection and securityHow untrusted text hijacks models, and how to limit the damage.
  8. EvalsMeasure output quality with test sets instead of vibes.
  9. LLM-as-judgeGrade open-ended output with rubrics and a second model.
  10. Multi-agent systemsCoordinating many agents on one large job.
  11. Evaluating agentsMeasure multi-step, tool-using behavior.
  12. What an agent harness is FreeThe software around a model that turns it into an agent.
  13. The core loop, built properlyStop reasons, parallel tool calls, errors and turn budgets.
  14. A tool registry for agentsSchemas from functions, validation, output limits and helpful errors.
  15. File and search toolsRead, write, edit by exact replacement, glob and grep inside one folder.
  16. Running code safelyExecution tools, step limits, output caps and real sandboxes.
  17. Permissions and approvalsRules, modes and approval prompts that keep a person in control.
  18. Hooks and skillsExtend a harness at lifecycle events, and load know-how on demand.
  19. Managing the context windowBudgets, clearing old tool results, compaction and a cacheable prefix.
  20. Memory, plans and long tasksTo-do lists, progress notes, memory files and checkpoints.
  21. SubagentsHand a focused task to a fresh context with fewer tools.
  22. Streaming, interrupts and sessionsLive output, stopping safely, and saving and resuming transcripts.
  23. Evaluation harnessesRun agents on tasks in fresh environments and grade what they leave behind.
  24. Tracing, budgets and guardrailsSee what an agent did, cap what it spends, and stop it when it loops.
  25. Capstone: build a coding agentA harness that edits a project, runs its tests and stops when they pass.

When you finish

Finish every lesson, or show you know it in the placement test, and you earn a certificate of completion, "AI agents course", with its own link you can share or add to LinkedIn.

Questions

Is it really free?
Yes. There's nothing to pay, here or anywhere in the academy. A free account saves your progress and issues your certificate.
Do I need to install anything?
No. The Python in these lessons runs in your browser.
How long does it take?
About 17 hours in all, at your own pace. Your progress stays where you left it.
What does the certificate show?
That your account recorded every lesson as finished or known. It's a certificate of completion from Index Ai Academy, not an accredited qualification.

Start the course

A free account saves your progress across devices and issues your certificate when you finish.

Create a free account