← All drills

Test Your Prompts Like Code

What you'll be able to do

Change a prompt in a production LLM feature with evidence, not intuition, and stop a regression before it ships.

⌁ Any product with a prompt in it: support triage, document extraction, question answering over policies, and agent system prompts.
Start this internship
Create an account to unlock the 11 sections, the workbench, and askThili.
Begin

Sections

1. Test Your Prompts Like Code
🔒 locked
2. A prompt is a program you can test
🔒 locked
3. Graders: code that decides if a reply is right
🔒 locked
4. The harness, and your first honest numbers
🔒 locked
5. Clarity and format: say it, then enforce it
🔒 locked
6. Role, constraints, and the refusal
🔒 locked
7. Worked examples
🔒 locked
8. Asking the model to reason
🔒 locked
9. Right once is not right every time
🔒 locked
10. Letting a loop rewrite the prompt
🔒 locked
11. Prompts under attack, and shipping changes safely
🔒 locked

Dig deeper

🔗Groq documentation (the API used in this drill)
docs
🔗thilillm, the reference implementation you check your code against
code

Part of these learning paths

I'm a student and I want to get my first AI/ML job
View path →
I want to build an app that answers from my own documents
View path →