AI agents and MCP

Stage 1 · Lesson 1 of 6

What an agent is

How agents work

An AI is a program where a language model decides the next step, runs it through a tool and looks at the result before deciding again. The model on its own only produces text. Your code gives it tools (functions it may ask you to run), (fetching relevant documents) and memory (facts carried between calls).

This combination is sometimes called an augmented . The agent is the loop around it: call the model, run what it asks, feed back the result, repeat until the task is done. Everything in this roadmap, from frameworks to servers, is a way of building, connecting or controlling that loop.

Common trapthinking the model is the agent, when most of an agent's quality comes from the tools, context and limits your code provides.

A question to check yourself, an AI practice session and 2 cheat sheet entries come with the full roadmap. Unlock

Resources for this stage

Start with· follow one of these

  • CoursePaid
    Grokking Modern AI Fundamentals

    Design Gurus · Beginner · $72 one-time

    Chapter 8, Agentic AI, covers reasoning, planning and memory in agents and ends with a small agent project

  • CourseFree
    Hugging Face AI Agents Course

    Hugging Face · Beginner

    Free: Unit 1 explains the thought, action, observation cycle and builds a first agent step by step

Practise

Keep handy

  • The clearest description of workflows versus agents and the common patterns; reread it at every stage

  • A one-page map of agent topics, useful to see where each stage of this roadmap fits

Also worth your time

Mark this stage as not done?