Learn to build
AI agents.
From scratch. For real.
Hands-on courses on orchestration, tool use, MCP, and production agent systems. Powered by Ollama. No vendor lock-in. No frameworks until you understand what they abstract.
4
tracks
20
modules
67
lessons
100%
free
# Your first agent - built from scratch, no frameworks
import ollama
def run_agent(goal, tools, max_iterations=10):
state = {"messages": [], "goal": goal}
for i in range(max_iterations):
# Reason about the next action
response = ollama.chat(
model="llama3",
messages=state["messages"],
tools=tools,
)
# Check if the agent is done
if response.done:
return response.content
# Execute the tool and observe results
result = execute_tool(response.tool_call)
state["messages"].append(result)Curriculum
Four tracks to mastery
Each track builds on the previous. Start with fundamentals and work your way to deploying production agent systems.
Agent fundamentals
The orchestration loop, tool use, ReAct, memory, context engineering, and agentic RAG.
Orchestration patterns
Multi-agent systems, topologies, state machines, safety controls, and metacognition.
Building with MCP
Protocol fundamentals, building servers, building clients, and production MCP.
Production agents
Reliability, evaluation, observability, deployment, and scaling.
What makes this different
Built by an engineer shipping agents at scale
Not another LangChain tutorial. Learn the concepts, then choose your tools.
Build from scratch
No frameworks until you understand what they abstract. Every concept implemented in plain Python first.
Interactive sandboxes
Write and run agent code directly in your browser. Pyodide for logic exercises, Ollama for real agent execution.
No vendor lock-in
Ollama-powered, provider-agnostic. Switch to any model or API. Your agents, your infrastructure.
Production-tested patterns
Orchestration loops, MCP servers, observability dashboards. Patterns used in real systems with 200+ engineers.
Progressive depth
Start with a 30-line agent, end with a production multi-agent system. Each track builds naturally on the last.
Zero cost to learn
Free platform, free models with Ollama, free exercises. No API keys required to get started.
Prerequisites
You'll need three things to get started.
Python basics
Functions, classes, and comfortable with pip.
Command line
Navigate directories, run scripts, install packages.
Ollama installed
ollama.com — one install, then ollama pull llama3.
Ready to build your first agent?
Start with Track 1 and have a working agent in 30 minutes. No sign-up required to browse the curriculum.