---
id: copilot-iterating
lang: en
track: copilot
title: "Iterating"
seoTitle: "Iterating: refine a Copilot answer"
description: "Turn a fair Copilot answer into a strong one with short, targeted follow-ups, one change at a time, and know when to stop steering and start a fresh chat."
part: prompting
partTitle: "Prompting"
partOrder: 3
order: 3
level: Intermediate
durationMinutes: 3
outcome: "Turn a fair Copilot answer into a strong one with short, targeted follow-ups."
summary: "You rarely get the best answer first: read the reply, then steer the next one with one small change at a time, like shorter, sharper, or a different tone."
draft: false
updated: "2026-10-14"
furtherReading:
  - title: "Get better Copilot responses with great prompting"
    url: "https://support.microsoft.com/en-us/microsoft-365-copilot/get-better-copilot-responses-with-great-prompting"
    note: "Microsoft's tips for getting more useful answers from Copilot."
  - title: "Copilot tutorial: quick tips for better prompts"
    url: "https://support.microsoft.com/en-us/microsoft-365-copilot/copilot-tutorial-quick-tips-for-better-prompts"
    note: "A short Microsoft tutorial with quick prompting tips."
  - title: "Prompt Gallery"
    url: "https://adoption.microsoft.com/en-us/copilot/prompt-gallery/"
    note: "Ready-made prompts from Microsoft to copy and adapt."
keywords:
  - Copilot prompt iteration
  - refine a Copilot answer
  - Copilot follow-up prompts
  - steer Copilot
  - start a fresh chat
  - one change at a time
quiz:
  intro: "Four quick questions. Ace them all and the next lesson unlocks."
  passScore: 4
  questions:
    - q: "The first answer is only okay. What's the best next move?"
      options:
        - "Start over in a new chat straight away"
        - "Ask it to \"do better\""
        - "Use it as it is, first answers don't improve"
        - "Tell Copilot what to keep and what to change, in one specific follow-up"
      answer: 3
      explain: "Tell Copilot what to keep and what to change, in one specific follow-up, rather than starting over or asking it to \"do better.\" The first answer is a draft to react to."
    - q: "Which follow-up will actually move the answer?"
      options:
        - "\"That's not quite right.\""
        - "\"Cut it to three sentences and drop the last paragraph.\""
        - "\"Make it better.\""
        - "\"Try again.\""
      answer: 1
      explain: "\"Cut it to three sentences and drop the last paragraph.\" Specific and concrete beats a vague note like \"that's not quite right.\""
    - q: "When is it smarter to start fresh than to keep steering?"
      options:
        - "After exactly three follow-ups, whatever happens"
        - "As soon as the first answer is a bit off"
        - "When the chat has drifted far off track and each fix makes it worse"
      answer: 2
      explain: "When the chat has drifted far off track and each fix makes it worse, not after any fixed number of follow-ups. Then open a new chat with one strong prompt that folds in what you learned."
    - q: "Why change one thing at a time instead of ten?"
      options:
        - "So you can see what each change did and keep what works"
        - "Because Copilot can only follow one instruction per message"
        - "Because ten changes take too long to type"
      answer: 0
      explain: "So you can see what each change did and keep what works, instead of guessing again. It feels slower, but it's faster."
  pass:
    badge: "Perfect score"
    title: "You can coach the reply now."
    body: "Full marks. You know how to read a first draft, steer it one change at a time, and when to start fresh. Next up: advanced prompt patterns for writing, analysis, research, and coding."
  retry: "Check the marked answers and give it another go. You've got this."
---

> **Level:** Intermediate · **Reading time:** ~3 min
>
> **What you'll be able to do:** turn a fair Copilot answer into a strong one with short, targeted follow-ups.

Here's a habit worth breaking: you send a prompt, the answer comes back a bit off, and you either sigh and use it anyway or wipe the slate and start over. Both waste the best thing Copilot gives you, which is a first draft you can react to.

The first answer is rarely the finished one. It's a starting point. The skill is reading it, spotting the one or two things that are off, and steering the next version. This is where a lot of the real quality lives. You already wrote a solid prompt in the [last lesson](/learn/copilot/prompting/how-to-write-a-great-prompt). Now you learn to coach the reply.

## Read the first answer for what to fix

Before you type anything, actually read what came back and ask three quick questions. Is it the right length? Is the tone right? Is anything wrong or missing?

Most first drafts are close on one, off on another. Maybe the facts are right but it reads like a brochure. Maybe the tone is spot on but it's twice as long as you need. Naming the gap is half the work, because once you can name it, you can ask for the fix.

## Steer with small, specific follow-ups

You don't need to rewrite the prompt. Just tell Copilot what to keep and what to change. The trick is being concrete.

Vague steering gets you nowhere:

*Make it better.*

Better how? It'll shuffle a few words and hand you back much the same thing. Specific steering works:

*Good, but two fixes. Cut it to three sentences, and lose the "we're excited to" opening. Get straight to the ask.*

That, Copilot can do. "Three sentences" is a number. "Lose the opening" is a clear target. The more precise the instruction, the closer the next version lands. Think of it as pointing, not hoping.

## Watch it work

Say you asked Copilot in Teams for a note declining a meeting and got back something warm but far too long.

Your first follow-up:

*Right idea, too long. Half the length, and keep it friendly.*

Shorter now, but it dropped the reason you're saying no. Second follow-up:

*Better. Add one line: I'm out because I'm heads-down on the launch this week.*

Now it's short, friendly, and honest. Two small nudges, thirty seconds, and a fair draft became one you'd actually send. Notice you changed one thing each time. That's on purpose.

<figure class="lesson-svg" aria-labelledby="p33-en-t">
<svg viewBox="0 0 640 214" width="100%" height="auto" role="img" aria-labelledby="p33-en-t p33-en-d" xmlns="http://www.w3.org/2000/svg" font-family="Inter, system-ui, sans-serif"><title id="p33-en-t">Steer one change at a time</title><desc id="p33-en-d">Three connected steps. First draft, too long and generic. Steer: shorter and friendlier. Steer again: add the one line it dropped. Result: a short, honest draft, ready to send.</desc><defs><marker id="arrow-teal" viewBox="0 0 10 10" refX="8" refY="5" markerWidth="7" markerHeight="7" orient="auto-start-reverse"><path d="M0,0 L10,5 L0,10 z" fill="var(--part,#1FA98C)"></path></marker></defs><text x="0" y="26" fill="var(--ink,#1F2328)" text-anchor="start" style="font-size:20px;font-weight:800;">Steer one change at a time</text><rect x="0.0" y="56" width="146.5" height="110" rx="10" ry="10" fill="#fff" stroke="var(--line,#E7E9EC)" stroke-width="1.5"></rect><circle cx="20.0" cy="78" r="12" fill="var(--med-gray,#5B6169)"></circle><text x="20.0" y="83" fill="#fff" text-anchor="middle" style="font-size:11.5px;font-weight:800;">1</text><text x="38.0" y="83" fill="var(--ink,#1F2328)" text-anchor="start" style="font-size:12px;font-weight:800;">First draft</text><text x="14.0" y="108" fill="var(--med-gray,#5B6169)" text-anchor="start" style="font-size:11px;font-weight:normal;">Warm, but far too long.</text><path d="M148.5,111.0 L162.5,111.0" stroke="var(--part,#1FA98C)" stroke-width="2" fill="none" marker-end="url(#arrow-teal)"></path><rect x="164.5" y="56" width="146.5" height="110" rx="10" ry="10" fill="#fff" stroke="var(--line,#E7E9EC)" stroke-width="1.5"></rect><circle cx="184.5" cy="78" r="12" fill="var(--med-gray,#5B6169)"></circle><text x="184.5" y="83" fill="#fff" text-anchor="middle" style="font-size:11.5px;font-weight:800;">2</text><text x="202.5" y="83" fill="var(--ink,#1F2328)" text-anchor="start" style="font-size:12px;font-weight:800;">Steer #1</text><text x="178.5" y="108" fill="var(--med-gray,#5B6169)" text-anchor="start" style="font-size:11px;font-weight:normal;">“Half the length, keep</text><text x="178.5" y="124" fill="var(--med-gray,#5B6169)" text-anchor="start" style="font-size:11px;font-weight:normal;">it friendly.”</text><path d="M313.0,111.0 L327.0,111.0" stroke="var(--part,#1FA98C)" stroke-width="2" fill="none" marker-end="url(#arrow-teal)"></path><rect x="329.0" y="56" width="146.5" height="110" rx="10" ry="10" fill="#fff" stroke="var(--line,#E7E9EC)" stroke-width="1.5"></rect><circle cx="349.0" cy="78" r="12" fill="var(--med-gray,#5B6169)"></circle><text x="349.0" y="83" fill="#fff" text-anchor="middle" style="font-size:11.5px;font-weight:800;">3</text><text x="367.0" y="83" fill="var(--ink,#1F2328)" text-anchor="start" style="font-size:12px;font-weight:800;">Steer #2</text><text x="343.0" y="108" fill="var(--med-gray,#5B6169)" text-anchor="start" style="font-size:11px;font-weight:normal;">“Add one line: why I'm</text><text x="343.0" y="124" fill="var(--med-gray,#5B6169)" text-anchor="start" style="font-size:11px;font-weight:normal;">out.”</text><path d="M477.5,111.0 L491.5,111.0" stroke="var(--part,#1FA98C)" stroke-width="2" fill="none" marker-end="url(#arrow-teal)"></path><rect x="493.5" y="56" width="146.5" height="110" rx="10" ry="10" fill="var(--part-tint,#E9F7F3)" stroke="var(--part,#1FA98C)" stroke-width="2"></rect><circle cx="513.5" cy="78" r="12" fill="var(--part,#1FA98C)"></circle><text x="513.5" y="83" fill="#fff" text-anchor="middle" style="font-size:11.5px;font-weight:800;">4</text><text x="531.5" y="83" fill="var(--part-ink,#16806A)" text-anchor="start" style="font-size:12px;font-weight:800;">Ready to send</text><text x="507.5" y="108" fill="var(--med-gray,#5B6169)" text-anchor="start" style="font-size:11px;font-weight:normal;">Short, friendly,</text><text x="507.5" y="124" fill="var(--med-gray,#5B6169)" text-anchor="start" style="font-size:11px;font-weight:normal;">honest.</text><text x="0" y="204" fill="var(--med-gray,#5B6169)" text-anchor="start" style="font-size:11.5px;font-weight:normal;font-style:italic;">One change per step, so you always know what fixed it.</text></svg>
</figure>

## One change at a time

It's tempting to fire off "shorter, warmer, add the numbers, fix the ending, and make it funny" all at once. Resist it. When you change five things together and the result is worse, you've no idea which change did the damage.

Change one thing, see what it did, keep it or undo it, then change the next. It feels slower. It's faster, because you're learning what works instead of rolling the dice again.

## When to steer and when to start fresh

Steering has a limit. Sometimes a chat drifts so far that every fix drags in the baggage of the wrong turns before it, and you spend more effort fighting the thread than doing the task.

That's your cue to start clean. Open a new chat and write one strong opening prompt that folds in everything you've learned from the messy one. You're not throwing away the work, you're using what the failed attempt taught you. Knowing when to steer and when to restart is its own small skill, and it comes fast with practice.

## Try it

Take a so-so answer you have lying around, or generate one on purpose with a lazy prompt. Improve it in exactly three follow-ups, changing one thing each time: first the length, then the tone, then one specific fix.

Read the final version against the first. Three small nudges, one at a time, and watch how far a middling draft can travel.

## Key terms

[Prompt](/glossary#prompt), [Iteration](/glossary#iteration), [Context](/glossary#context), [Copilot](/glossary#copilot)
