Prompts should be called Intern Assignments

I absolutely love the metaphor for AI that Benedict Evans uses; that AI gives you the power of infinite interns.

And while I’m still astounded at how few people are using generative AI in their daily lives, I think more metaphors like this will help people wrap their heads around how to use these new capabilities.

So I’m going to try reframing “prompts” as “intern assignments” and see if it helps people.

When you give an intern an assignment, you’re essentially asking them to complete a task based on their understanding and interpretation of your instructions. The same concept applies to AI prompts. You’re giving the AI a task to complete based on the instructions you provide. The more specific and detailed your instructions, the better the AI can perform the task.

For example, if you were to tell an intern, “Write a report on the latest market trends,” they might come back with a general overview. But if you said, “Write a report on the latest market trends in the tech industry, focusing on AI advancements in the last quarter,” they would return with a much more focused and useful report. The same goes for AI. The more specific your prompt, the more targeted and useful the output.

So, think of AI prompts as intern assignments. Be clear, be specific, and you’ll get the results you’re looking for.