Prompt Engineering 101

The Art of Talking to AI

The quality of AI output depends heavily on how you ask. A vague prompt gets a vague answer. A specific, well-structured prompt gets a useful, targeted response. This skill is called prompt engineering — and it’s one of the most practical AI skills you can learn.

Prompt Lab

Compare a bad prompt with a good prompt. Click the one you think produces better results.

Bad Prompt

“Write about a water bottle”

A water bottle is a container used to hold water. It can be made of plastic, metal, or glass. People use water bottles to drink water.

Good Prompt

“Write a 50-word product description for a stainless steel insulated water bottle targeting fitness enthusiasts. Highlight: keeps drinks cold 24hr, BPA-free, comes in 5 colors. Tone: energetic and motivational.”

Crush your workout goals with our premium stainless steel bottle. Keeps your drinks ice-cold for 24 hours, BPA-free, and available in 5 vibrant colors. Built for athletes who refuse to slow down.

5 Rules for Better Prompts

1. Be specific — Instead of “write about dogs”, say “write a 200-word blog post about training golden retrievers for first-time owners.”

2. Provide context — Tell the AI who the audience is, what tone to use, and what format you want.

3. Set constraints — Specify length, style, language, or format (“in bullet points”, “as a table”).

4. Give examples — Show the AI what good output looks like by including a sample.

5. Iterate — Your first prompt rarely produces the best result. Refine and try again.

Think of AI as an Intern

AI is eager to help but needs clear instructions. The more context and specifics you provide, the better the output. You wouldn’t tell an intern “do the thing” — don’t do it to AI either.

Check Your Understanding

1. What is prompt engineering?

2. Which prompt is better?

3. Why should you iterate on prompts?

4. What does ‘providing context’ mean in prompting?

Answer all questions. You need 70% to pass.