5-Week Bootcamp · Python-first · Ages 15+ · 10 hours

Agentic AI

You already know a model can talk. Now you make it act. In five 2-hour sessions you’ll build LLM agents that reason in a loop, call real tools, remember, retrieve from your own documents, coordinate as a crew, and ship a guard-railed agent you demo in public.

Start Week 1 → 📘 New here? Start with the Intro
First time with agents, APIs & MCP? The Intro explains them with pictures, then Build It walks you through making all three. New to Python and neural nets? Do AI Trailblazers first.
How this works

Screens for code. This site for thinking.

Every week you write real Python in Google Colab, calling live LLM APIs (Claude, GPT, Gemini) through LangChain, CrewAI, and LangGraph. This interactive handbook is the other half of the lab — the mental models, the checkpoints, and the receipts — so nothing about agents feels like magic. Work in pairs (driver + navigator, swap at every checkpoint); your capstone agent is yours alone.

The one rule that makes you an engineer: AI assistants may explain an error — never write your lab solution. An agent that fails loudly is teaching you the loop. Read the last line of the traceback out loud before you raise a hand.
The Build

Five weeks, one real AI agent

The 5-week journey: Week 1 Loop, Week 2 Memory, Week 3 RAG, Week 4 Crew, Week 5 Ship
Five weeks, one real agent — from the loop to a shipped project.
0PRE-WORK

Get an API key + “Hello, model” (at home)

“My code just talked to a live LLM.”
covered in Wk1 →
1WEEK

From Chatbot to Agent

“My agent decided which tool to use — and used it.”
Start →
2WEEK

Memory & Tools

“It remembered what I said and reached for the right hand.”
Open →
3WEEK

Agents That Read (RAG)

“It answered from MY documents, with a citation.”
Open →
4WEEK

Many Minds (Multi-Agent)

“A crew of agents split the job and finished it.”
Open →
5WEEK

Guardrails & Ship It

“I evaluated it, guarded it, demoed it — it’s on my resume.”
Open →
The Vocabulary Contract

Learn four words and every agent is understandable

Goal
what the agent is trying to achieve
Loop
reason → act → observe → repeat
Tool
a function the agent can call
Memory
what it carries between steps
Anatomy of an agent: a central AGENT node connected to GOAL, LOOP, TOOL, and MEMORY
The four parts of every agent — goal, loop, tool, memory.

Every agent you meet — a coding copilot, a research crew, a customer-service bot — is some arrangement of these four. An agent is just an LLM wrapped in a loop that can call tools and keep memory. Say the four words out loud.

The Five Laws

One law per week. Earn them.

Law #1 · Week 1
The magic is the loop, not the model.

An agent is a plain LLM given the power to act, observe the result, and try again.

Law #2 · Week 2
An agent is only as capable as its tools.

Give it hands and a memory, not just a mouth. Clear tool descriptions are the whole game.

Law #3 · Week 3
An agent that can’t look it up will make it up.

Retrieval beats hallucination. Ground answers in real documents — and cite them.

Law #4 · Week 4
Many small agents beat one giant prompt.

Split the job, define the roles, let them hand work off. Specialists coordinate; generalists drown.

Law #5 · Week 5
An agent you can’t observe, you can’t trust.

Log every step, evaluate on real cases, guard the edges. Then — and only then — ship.

Badges — no participation trophies

Earn one a week. All five = Agentic Architect.

🛠️

Tool User

Wk 1 — built a ReAct agent that read a question, picked the right tool, and used it in code.

🧠

Memory Keeper

Wk 2 — gave an agent working memory and two tools; it stayed coherent across a multi-turn task.

📚

Retriever

Wk 3 — built a RAG agent over your own documents that answers with a real citation.

🎭

Orchestrator

Wk 4 — ran a 2-agent crew with defined roles that handed work off and produced one result.

🚀

Shipped-It

Wk 5 — added a guardrail, ran an eval, and gave a public 4-beat demo with a shown artifact.

🏆

Agentic Architect

All 5 badges + all 5 missions. Announced at the Showcase.

Your Toolkit

Real tools professionals ship with

📓

Google Colab / Jupyter

Where you write and run every Python notebook — no install.

🤖

Claude / GPT / Gemini APIs

The LLM engines your agents reason with (free/low-cost tiers).

🔗

LangChain + LCEL

Wire prompts, tools, and models into an agent you can run.

🧩

FAISS / Chroma

Vector databases that let an agent search your documents by meaning.

🎭

CrewAI + LangGraph

Give agents roles and a graph to coordinate multi-step work.

🔭

LangSmith + Rebuff

See every step your agent takes — and block prompt-injection attacks.

Begin the Build → Week 1