Prompt

how you instruct and guide ai to achieve what you want

A prompt is how you tell an AI tool what you want, and the result often depends on how clearly you ask. This card looks at how a team writes, refines, and reuses prompts in daily work. It treats prompting as a practical skill, not a trick, and a place where small habits change the output.

Questions to explore

// use these as prompts in a workshop or on your own. There are no right answers.

What makes the difference between a prompt that works and one that does not in your experience?
How do you give a tool enough context without feeding it sensitive material?
Which prompts would be worth saving and sharing across your team?
How do you check whether the output actually answered what you asked?
When a result is wrong, how do you tell if the prompt or the tool is at fault?

Expert voices

// notes from the journalists and AI experts who helped shape this kit

“Teach prompting as a transferable skill, not as tricks for one specific tool.”

Bahia Albrecht, DW Akademie

“Prompting is an editorial skill, not a technical trick. Good prompts sharpen thinking and challenge weak ideas; poor prompts quietly steer AI toward generic, biased outputs that feel authoritative.”

Paul McNally, Develop AI

Things to consider

Clear, specific prompts tend to give more useful results.
Be careful what source material you paste into a prompt.
A shared library of prompts saves the team from starting over each time.

using this card

Pull Prompt when it is relevant and set it aside when it is not. Pair it with the other AI Conversations cards, lay them out on a table, and use the questions above to get everyone on the same page. Capture what you discuss on sticky notes or in a shared doc.