AI Roadmaps
← All roadmaps
IntermediateRoadmap 06 · 14 steps · 4h 56m of video

AI Agents & MCP

Agents that call tools, use MCP servers, plan, and coordinate, and how to tell if they work.

Before this: AI Engineering.

  1. 12 min
    Step 1

    What are AI agents?

    The core loop: reason, act, observe.

    What are AI Agents?

    IBM Technology

  2. 15 min
    Step 2

    How Anthropic builds effective agents

    When to build an agent, and when a workflow is better.

    How We Build Effective Agents: Barry Zhang, Anthropic

    AI Engineer

  3. 5 min
    Step 3

    Tool calling

    How a model decides to call your function.

    What is Tool Calling? Connecting LLMs to Your Data

    IBM Technology

  4. 6 min
    Step 4

    ReAct: reasoning plus acting

    The pattern behind most agents.

    ReAct AI Agents, clearly explained!

    Akshay Pachaar

  5. 34 min
    Step 5

    Build an agent from scratch

    A working agent in Python in about 30 minutes.

    Build an AI Agent From Scratch in Python - Tutorial for Beginners

    Tech With Tim

    microsoft/ai-agents-for-beginners★ 80.6k
  6. 4 min
    Step 6

    What is MCP?

    The USB-C port for connecting AI to tools and data.

    What is MCP? Integrate AI Agents with Databases & APIs

    IBM Technology

  7. 8 min
    Step 7

    How MCP works

    Hosts, clients, servers, and the messages between them.

    How Model Context Protocol (MCP) actually works

    Google Cloud Tech

  8. 26 min
    Step 8

    Build an MCP server

    Expose your own tools to Claude, Cursor, and others.

    Build Anything With a CUSTOM MCP Server - Python Tutorial

    Tech With Tim

    modelcontextprotocol/python-sdk★ 24.9k
  9. 1h 13m
    Step 9

    MCP, the full course

    Servers, resources, prompts, and deployment.

    Intro to MCP Servers – Model Context Protocol with Python Course

    freeCodeCamp.org

    modelcontextprotocol/servers★ 92.1k
  10. 10 min
    Step 10

    Context engineering for agents

    Four ways agents fail because of what's in their context.

    Context Engineering for AI Agents: 4 Failure Modes to Avoid

    IBM Technology

  11. 16 min
    Step 11

    Skills instead of agents

    Package expertise as files an agent loads only when needed.

    Don't Build Agents, Build Skills Instead – Barry Zhang & Mahesh Murag, Anthropic

    AI Engineer

  12. 18 min
    Step 12

    Multi-agent systems

    When splitting work across agents helps, and when it hurts.

    Multi-agent Systems Explained in 17 Minutes

    Shaw Talebi

    openai/openai-agents-python★ 30.8k
  13. 58 min
    Step 13

    Agents with Hugging Face

    Kick-off for a free, hands-on agents course.

    Welcome To The Agents Course! Introduction to the Course and Q&A

    Hugging Face

    huggingface/agents-course★ 35.2k
  14. 11 min
    Step 14

    Evaluate agents

    Measure trajectories and outcomes, not vibes.

    How to evaluate agents in practice

    Google Cloud Tech

    SWE-agent/mini-swe-agent★ 9.9k

Build it

Watching isn't learning. Pick one and put it on GitHub.

Next roadmap