The Anatomy of a Prompt
A free lesson from Swipe AI · Prompt Engineering, level 1 · updated October 2026
By the Swipe team, founded by Colin · how we make lessons
A well-built prompt is really made of several separate parts, each doing its own job: the role (who or what perspective the tool should adopt), the task (the actual instruction — what to do), the context (background information it needs to do the task well), the format (how the output should be structured), and the constraints (limits — length, tone, what to avoid).
You already used pieces of this — giving a tool a role and a format — back in the basics of using AI tools well. Prompt engineering just formalizes it: naming each part lets you improve one at a time instead of rewriting a whole prompt from scratch every time something's slightly off.
Role: "You are a patient tutor explaining this to a total beginner." Task: "Explain what compound interest is." Context: "The reader has never taken a finance or math class." Format: "Two short paragraphs, no bullet points." Constraints: "Do not use any formulas or jargon."
Not every prompt needs all five parts spelled out explicitly — a simple, low-stakes request doesn't need a role or heavy constraints. But for anything you'll reuse, or anything where the output really needs to land a specific way, deliberately filling in each part is what separates a reliable prompt from a vague one.
In the anatomy of a prompt, what does the 'constraints' part actually specify?
The part of a prompt that specifies who or what perspective the AI tool should adopt is called the ____.
Every single prompt needs its role, task, context, format, and constraints spelled out explicitly to be effective.
Free ai tools
Keep your streak going in Swipe AI
Swipe through every level of Prompt Engineering on your iPhone — with XP, stars, streaks, a personal advisor and the full track beyond these free levels.
Get the Swipe apps →