Prompt
The full instruction you give an AI model. Not just a question. A prompt is the complete package: task, context, format, and constraints. The model works only with what you hand it, so the quality of what comes back is almost entirely a function of the quality of what goes in.
What it is
A prompt is everything you type into a chat window before you hit send. The word sounds like it means "a question," but a complete prompt has four parts. The task is what you want the model to do. The context is what the model needs to know to do it well (your business, the situation, the background). The format is what the output should look like (email, bullet list, under 150 words). The constraints are what you don't want (no legal language, don't mention the pricing dispute, formal tone only).
Most prompts that underperform are missing context and format. The model fills the gaps with whatever is most plausible, which is usually generic.
Why it matters
A large language model predicts the most plausible next word from the input you give it. More specific input, tighter output. Vague input, generic output. The model isn't more capable when you prompt it well; you're just wasting less of what it can already do. Per Anthropic's prompting guidance, context is the single biggest lever most users leave unpulled.
Related
Put this term to work.
The Desk Theory guides turn definitions like this into running workflows. Two operator manuals, $99 each, or the bundle for $149.
Browse the books →The signal in your inbox, every Thursday
Three workflows that put you in the top 1% of CEOs. Free, 90-second read.
Get the newsletter →