AI Fluency & Building · Prompt Engineering
Own it end to end. Bigger projects you design, run and present like a professional.
Task 1 of 2
Automatically test prompts across two models.
What to do
Build a Python harness that runs your prompt library against test cases on two AI models, scores the outputs, and flags any drop in quality whenever a prompt changes.
You’ll make
Done looks like
A Python harness on GitHub that scores outputs and flags regressions.
Task 2 of 2
Turn messy product info into structured data reliably.
What to do
Design a prompt that turns messy product information (supplier notes, photos' text, spreadsheets) into strict JSON for a website catalogue: name, price, sizes, features, description. Add schema validation and automatic retry, and document failure cases.
You’ll make
Done looks like
A working prompt with schema validation, retries and documented failure cases.
Learn before you build
Free course
A free open-source prompting course from basics to advanced.
Free course
A free 1.5-hour course by DeepLearning.AI and OpenAI.
Free tool
Open-source tool to test prompts and AI apps against test cases.
Code repo
Hands-on notebooks that take you from basics to advanced techniques.
Article guide
Official techniques: clarity, examples, XML tags, chaining and more.
Article guide
The most complete open guide to prompting techniques and research.