☕ Learning path

Learn AI Agents.

From a model that can only talk to a system that can act: tools, structured calls, patterns, memory, and how to architect it.

⏱ ~55 min· 6 concepts· 5 hands-on tools· free, no account
0 of 11 steps
  1. 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.
  2. Trytool call visualizer Step through the function-calling loop.
  3. 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.
  4. ReadStructured Output Builder Define fields once; generate the schema for OpenAI, Anthropic, Gemini, and plain JSON Schema.
  5. ReadAI Patterns Library Reflection, Router, Judge, Verification, Human-in-the-loop.
  6. Tryai pattern builder Compose an agent flow, export scaffolding.
  7. ReadWhat is agent memory? Why an assistant 'remembers' or 'forgets', context vs short-term vs long-term memory, and how persistence is faked.
  8. Tryagent memory simulator See how AI memory keeps or loses facts.
  9. ReadWhat is MCP (Model Context Protocol)? The open standard for connecting AI apps to tools and data, the 'USB-C for AI tools.'
  10. Trymcp config generator Build & validate an MCP server config.
  11. Tryai architecture generator Describe an app, get an architecture (BYO key).

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