Skip to content

Learn · Track

How AI agents work

What an agent is, how its loop runs, when a fixed workflow is the better choice, how a supervisor splits work across worker agents, what an agent should remember, how to keep its tool list short, and where a person should approve its actions. No prior knowledge of agents needed; knowing what a language model is helps.

Guides in this track

Beginner6 guides, in reading order

  1. What is an AI agent?

    An AI agent is a model in a loop that calls tools until it can answer. See the loop step by step, where it fails, and run one locally with no API key.

    8 min read

  2. Workflows vs agents

    Fixed workflows and model-driven agents compared: cost, control and testability, the common patterns between them, and how to mix both in one graph.

    9 min read

  3. Supervisor and workers

    How a supervisor agent delegates to worker agents exposed as tools: when it helps, what it costs, how to test it, and a sample that runs with no API key.

    8 min read

  4. Agent memory

    Short-term history, session memory and cached tool results: what each is for, how much to keep, and how agent memory meets retention and erasure.

    9 min read

  5. Too many tools

    Why long MCP tool lists hurt agents (context, wrong picks, cost), and practical fixes: shortlisting, toolsets, per-agent servers and rules that hide tools.

    9 min read

  6. Human in the loop

    Where a person belongs in an agent's path: before risky tool calls, on a draft, or as a question. Which actions need it, timeouts, and approval fatigue.

    10 min read

Before and after

Prerequisites: none. The first guide in MCP fundamentals explains where an agent's tools come from.

After this track: Prompt injection starts the agent security track. To build one, import a working agent from the recipes, or read the agent loop reference for every setting.

This website (not the L2M product) uses Google Analytics, only after you accept cookies. Cookie settings