Project 42Start learning
Module 6 of 16 · 15 min

Prompt with Purpose

Turn a vague request into a task an AI system can execute and you can evaluate.

Core concept

By the end

You will be able to

  • Write prompts with a goal, context, constraints, and output contract.
  • Separate trusted instructions from untrusted input.
  • Define a useful stopping condition.
01

A prompt is a working contract

Strong prompts say what outcome is needed, why it matters, what information is trustworthy, what boundaries apply, and what a successful response looks like.

The model should not have to guess the audience, format, source of truth, or definition of done.

Reusable prompt shape
text
Goal: [OUTCOME]
Context: [TRUSTED FACTS]
Constraints: [BOUNDARIES]
Deliverable: [FORMAT]
Verify: [CHECKS]
02

Inspect, correct, and reuse

Prompting is iterative. Inspect the result, identify the missing constraint or context, and improve the reusable instruction instead of repeatedly requesting a vague improvement.

Evidence

Sources and verification

Knowledge check

Make it stick.

Pass at 80%

Choose the strongest answer for each question. Your attempts become part of your device-local transcript.

01Which addition most improves an ambiguous request?
02Why separate trusted context from untrusted content?