Learn · Track
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.
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.
Fixed workflows and model-driven agents compared: cost, control and testability, the common patterns between them, and how to mix both in one graph.
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.
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.
Why long MCP tool lists hurt agents (context, wrong picks, cost), and practical fixes: shortlisting, toolsets, per-agent servers and rules that hide tools.
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.
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