Course 2 · Understand
Get better answers from your AI assistant.
Five practical lessons for when your assistant is nearly right: what to check when it goes wrong, how to write its instructions, what to give it to read, and how to tell whether it's actually working.
FreeBeginner5 lessons · 41 minWorks in any AI tool
Start lesson 1No signup to read.
Written by Joe LeungCTO and co-founder, LaunchLemonade
5 lessons · about 41 minutes
Course outline
Best in order, but every lesson stands on its own. Jump to the one you need.
- 1When it goes wrong: seven fixes to try firstYour assistant was great on Monday and odd by Friday. Seven setup fixes to try before you blame the model, and how to tell which one you need.8 min
- 2Write a system prompt that worksThe instructions your assistant reads before every chat: role, context, format, constraints and examples, with a before and after you can copy.8 min
- 3Instructions that hold up in real workWhat your instructions should say when documents disagree, when something is sensitive, and when the assistant is stuck, with weak and strong versions side by side.8 min
- 4Teach it your business"Training it on our business" usually means giving it the right documents at the moment it answers: a short list, an owner for each, written to stand on its own.9 min
- 5Is it actually working?"It feels faster" isn't a number. A baseline, an honest count of time saved, a test set of real tasks, and a decision: expand, improve, pause or retire.8 min
After this course
Build your first assistant
Make an assistant that does one job your way: your instructions, your documents, the model you choose. No code.