---
title: "Writing a Prompt That Says What You Actually Want"
description: "A model answers the request in front of it, not the one in the asker's head. Stating the task, the audience, the format and the limits turns a vague request into one whose answer can be judged."
canonical: https://lightmysky.com/learn/computing/writing-a-prompt-that-says-what-you-actually-want-mt_dJ5-SDX3Ck
source: https://lightmysky.com/learn/computing/writing-a-prompt-that-says-what-you-actually-want-mt_dJ5-SDX3Ck.md
retrieved: 2026-09-12
---

> **Agent view.** This is the Markdown twin of the page, for tools and assistants.
> When to use this site, and the call that answers each job: https://lightmysky.com/agent-instructions.md
> API description (OpenAPI 3.1): https://lightmysky.com/openapi.json · Authentication: https://lightmysky.com/auth.md
> Pricing: https://lightmysky.com/pricing.md · Catalog: https://lightmysky.com/llms.txt · Full catalog: https://lightmysky.com/llms-full.txt
> Every machine-readable file on this domain: https://lightmysky.com/.well-known/ai-catalog.json
> Ask for Markdown with `Accept: text/markdown`, a `.md` address, or `?mode=agent`.

# Writing a Prompt That Says What You Actually Want

A model answers the request in front of it, not the one in the asker's head. Stating the task, the audience, the format and the limits turns a vague request into one whose answer can be judged.

Subject: Computing · Area: Artificial Intelligence · Ages 14 to 16
Page: https://lightmysky.com/learn/computing/writing-a-prompt-that-says-what-you-actually-want-mt_dJ5-SDX3Ck

## Ready when they can

- Rewrite a vague request so the wanted format, length and audience are stated
- Supply the material the model needs rather than assuming it knows the particular case
- Say, before reading the answer, what would make that answer wrong

## Lesson: Say what you actually want

A model answers the request in front of it, not the one in your head. A vague request earns a vague answer, because the model fills each gap you left open. Spell out what you want before you press enter.

State four things: the task, the audience, the format, and the limits. Try: act as a quiz writer, make five questions for a 14 year old, and keep each explanation under 30 words. That one sentence beats a paragraph of pleading.

**Example.** Supply the material instead of assuming the model knows your case. Share the topic, length, stance, and your own notes or outline. With those in hand, it can draft, rephrase, or argue your exact point.

**Tip.** Work in rounds and judge each round. Ask for a plan first, keep what helps, then expand only the part you chose. Before reading, say what would make an answer wrong, and check facts yourself since the tool cannot verify them.

**Recap.** Name the task, feed the facts, judge the answer, then refine.

## Practice

8 questions on this page, each with its working shown.

## Needs first

- [Training Data: Where It Came From and What It Leaves Out](https://lightmysky.com/learn/computing/training-data-where-it-came-from-and-what-it-leaves-out-mt_1Lw0TMHShk)

## Opens up

- [Checking a Model's Claim Against a Source](https://lightmysky.com/learn/computing/checking-a-models-claim-against-a-source-mt_Qh4Pnnfqv2)