Talking to AI · 06

Treat wrong answers as data

Outcome

By the end, you'll be able to use an unsatisfying reply as the raw material for a better follow-up — instead of starting over or giving up.

Concept

Nobody writes the perfect prompt on the first try — including people who do this for a living. The skill isn't getting it right immediately; it's noticing exactly what's missing or off in a reply, and using that to write a sharper follow-up. Each round narrows the gap between what you asked and what you actually wanted.

Weak prompt vs. strong prompt

The ask

Tell me about Python.

What comes back

Python is a high-level, interpreted programming language known for its simplicity and readability. It was created by Guido van Rossum and first released in 1991. Python supports multiple programming paradigms, including procedural, object-oriented, and functional programming. It has a large standard library and an active community, making it popular across many fields such as web development, data science, automation, artificial intelligence, and more. Its clean syntax makes it a common choice for beginners.

Try it

Open claude.ai and run this chain, one message at a time:

Prompt

1) "Tell me about Python." 2) Then: "What is Python used for in web development specifically?" 3) Then: "Give me 3 real Python web frameworks and one sentence on when to use each."

What to look for: After each reply, ask yourself: what's still missing? Use that answer to write the next message. Notice how each round gets noticeably more useful than the last.

Takeaway

A vague or unhelpful reply isn't a dead end — it's information about what to ask next.

Practice

Practice with Claude

Try what this tutorial teaches. Conversations aren't saved.

Ask a question about working with AI, or paste a prompt to try — Claude will reply and point out where it could be sharper.


Tell it what "done" looks likeIt's not a database