AI Fluency & Building · Agentic AI Developer
Start here. Short, guided tasks that build the basics and give you your first piece of proof.
Task 1 of 3
Let an AI call one function and explain the loop.
What to do
Build a simple script where an AI model can call one function (for example, look up a product's price in a local file). Explain each step of the tool-use loop in your README.
You’ll make
Done looks like
A working script on GitHub with a README explaining each tool-use step.
Task 2 of 3
Summarise industry news for a brand every day.
What to do
Build an agent that reads 5 RSS feeds or news sources for an industry you choose (fashion, food, tech, fitness) and writes a daily 5-bullet digest with ideas a brand could post about.
You’ll make
Done looks like
A working agent that outputs a daily 5-bullet digest with source links and post ideas.
Task 3 of 3
When a fixed pipeline beats a free-running agent.
What to do
Write a short design doc comparing fixed workflows and AI agents: when should a simple step-by-step automation beat a free-running agent? Use 3 business examples.
You’ll make
Done looks like
A short design doc with 3 examples and a clear recommendation for each.
Learn before you build
Free course
A free hands-on agents course with a certificate.
Free course
Free courses on building stateful, multi-step agents.
Free course
Dozens of free 1–2 hour courses on agents, RAG and evaluation.
Code repo
Free notebooks on the API, tool use and evaluations.
Article guide
Read this first: when to use agents, and the patterns that work.
Article guide
A lightweight open-source framework for multi-agent workflows.