Learning roadmap

Learn in the order real systems demand.

Start with solid Python, ship a small application, automate a real task, then add agent behavior where it earns its complexity.

02

Turn code into a working application

Build a small API or data workflow. Add inputs, outputs, logs, tests, and one repeatable deployment command.

Explore FastAPI →

03

Automate a real workflow

Choose one repeatable task, define its failure boundaries, and make every run observable and safe to retry.

Browse automation resources →

04

Add an agent only where judgment is needed

Learn the model-tool loop, structured output, state, guardrails, evaluation, and human review before adding orchestration.

Open the agent roadmap →

Featured guide

Run and test the agent loop before the framework.

A no-key troubleshooting agent with bounded tools, an action trace, a hard step limit, and three unit tests.

Guide 01Python 3.12+3 automated tests

Build a testable Python agent loop

Create two files, run a deterministic troubleshooting agent, and verify both success and failure paths with unittest.

Read the complete guide →