Learn AI Agents.

New to the lingo? An agent is an AI that does not just answer but takes actions: it uses tool calling to run steps, returns structured outputs your code can trust, and plugs into tools over MCP. Hover any underlined word for a quick definition, or click to learn more.

1. 1✓ ReadHow to build an AI agent What actually turns a chatbot into an agent: a model plus tools plus a loop plus memory plus a stop. The five parts, the agent loop, the security you cannot skip, and a builder that writes your agent's spec.
2. 2✓ ReadWhat is tool calling (function calling)? How a model decides to call a function, returns structured arguments, and your code runs it, the basis of agents.
3. 3✓ Trytool call visualizer Step through the function-calling loop.
4. 4✓ ReadWhat are structured outputs? Making a model return JSON that matches a schema every time, vs JSON mode, and why it powers extraction and tool calls.
5. 5✓ ReadStructured Output Builder Define fields once; generate the schema for OpenAI, Anthropic, Gemini, and plain JSON Schema.
6. 6✓ ReadAI Patterns Library Reflection, Router, Judge, Verification, Human-in-the-loop.
7. 7✓ Tryai pattern builder Compose an agent flow, export scaffolding.
8. 8✓ ReadWhat is agent memory? Why an assistant 'remembers' or 'forgets', context vs short-term vs long-term memory, and how persistence is faked.
9. 9✓ Tryagent memory simulator See how AI memory keeps or loses facts.
10. 10✓ ReadWhat is MCP (Model Context Protocol)? The open standard for connecting AI apps to tools and data, the 'USB-C for AI tools.'
11. 11✓ ReadWhat are MCP servers? The servers you actually plug in: files, databases, GitHub, the web, browsers. The categories that matter, real examples, and how to connect one.
12. 12✓ Trymcp config generator Build & validate an MCP server config.
13. 13✓ Tryai architecture generator Describe an app, get an architecture (BYO key).

More routes: all learning paths, the skill tree, or the knowledge map.