--- title: "Fix an answer you don’t like" url: https://aiguideson.com/courses/prompting-for-beginners/fix-an-answer/ course: "Prompting for beginners" lesson: "4 of 5" minutes: 10 published: 2026-10-03 updated: 2026-10-03 author: "Jack Stovell" publisher: "Adapt Progress Evolve Limited" language: "en-GB" --- # Fix an answer you don’t like Lesson 4 of 5 in [Prompting for beginners](https://aiguideson.com/courses/prompting-for-beginners/) · 10 minutes The first reply is only a first draft. In this lesson you’ll learn four ways to get a better one: say what’s wrong in the same chat, let the AI ask you questions first, give it permission to say it doesn’t know, and know when to start again. ## You need - A free ChatGPT or Claude account - A reply you weren’t happy with (or the one from lesson 1) A narrated walkthrough of this lesson is coming. The steps below cover everything in it. ## Steps ### Step 1: Say what’s wrong, in the same chat Reply in the same chat and say plainly what you want different. You don’t need to repeat the whole job. We told it the lesson 1 reply was a bit formal and asked for under 80 words. It came back shorter and more relaxed. It also noticed, without being asked, that the earlier version had promised something on someone else’s behalf, and took that line out. The prompt (works in ChatGPT, Claude or any AI chat tool): ```text That's a bit formal. Make it sound more like I'd talk to a neighbour, and keep it under 80 words. ``` - Say what’s wrong (too formal) and what you want instead (like talking to a neighbour). - Give a limit it can check: under 80 words. (Screenshot to come.) Checkpoint: The new reply fixes what you asked about. ### Step 2: Change one thing at a time If several things are wrong, fix the most important first and check the result before you ask for more. OpenAI suggests breaking bigger jobs into smaller prompts and treating prompting as a conversation: you refine your request based on the answers you get. ![OpenAI’s help page "How do I create a good prompt for an AI model?", showing the tips to right-size and prioritise requests and to work iteratively, treating prompting as a conversation.](https://aiguideson.com/courses/prompting-for-beginners/l4-openai-iterate.png) (screenshot captured 3 October 2026) 1. Break big jobs into smaller prompts 2. Treat it as a conversation and refine Checkpoint: You’ve fixed the biggest problem before moving on to the next. ### Step 3: Let it ask you questions first When you’re not sure what details it needs, ask it to ask you. We wanted a short "About me" section for the bakery’s website and asked for up to five questions before it wrote anything. It asked who’s behind the bakery, what makes it different, where it is, what tone to use and how long it should be. Fair questions, all of them. The prompt (works in ChatGPT, Claude or any AI chat tool): ```text I want to write a short "About me" section for my bakery's website. Before you write anything, ask me up to five questions you need answered. Ask them all at once, numbered. ``` - "Before you write anything" stops it guessing a first draft. - "Up to five" and "all at once, numbered" keep the questions short and easy to answer. (Screenshot to come.) Checkpoint: You have a numbered list of questions from the AI. ### Step 4: Answer them, then read the result Answer each question by number, in your own words. They don’t need to be polished. Ours came back at about 60 words, built from our answers. It left a gap for the email address, because we hadn’t given one, and said so. The prompt (works in ChatGPT, Claude or any AI chat tool): ```text 1. I'm Jo. I started baking sourdough at home about five years ago, and began taking orders from friends and neighbours. 2. Slow-risen sourdough loaves and celebration cakes, made to order. Everything is baked in my own kitchen. 3. A home bakery in a small town. Collection only, on Friday and Saturday, 8am to 1pm. 4. Warm and personal, written as "I". 5. About 60 words, ending with an invitation to order by email. ``` - Numbering your answers to match its questions means nothing gets missed. (Screenshot to come.) Checkpoint: You have a draft built only from your answers. ### Step 5: Tell it that it can say "I don’t know" AI tools tend to give an answer even when they’re unsure. Anthropic’s advice is to give Claude permission to admit uncertainty, which it says can greatly reduce false information. Add a line like "If something isn’t clear, tell me rather than guessing." You’ll use this line in your prompt kit. ![Anthropic’s guide "Reduce hallucinations", at the first strategy: allow Claude to say "I don’t know" by explicitly giving it permission to admit uncertainty.](https://aiguideson.com/courses/prompting-for-beginners/l4-claude-dont-know.png) (screenshot captured 3 October 2026) 1. Give it permission to say "I don't know" Checkpoint: You have a line you can add to any prompt where accuracy matters. ### Step 6: Know when to start again If a chat has gone round in circles, stop. Start a new chat and write a better first prompt, using the four parts from lesson 2 and what you’ve learned from the replies so far. It can feel like giving up. It isn’t. (Screenshot to come.) Checkpoint: You know when a fresh start beats another follow-up. ## Common problems ### Every fix makes something else worse Start a new chat with one clear prompt that includes everything you’ve learned. Long chats can drift. ### It keeps adding things you didn’t ask for Add a rule to your prompt: "Don’t add any details I haven’t given you." ### It agrees with everything you say, even when you’re wrong Ask it to check your facts rather than agree: "Tell me if anything I’ve said is wrong." Then check the important parts yourself. Steps 2 and 5 are the makers’ public guidance pages, captured by tools/capture/prompting-for-beginners.mjs. Steps 1, 3 and 4 happen in a signed-in chat, so they have no screenshot yet; the prompts and replies are in outputs/. ## Sources - [OpenAI Help Center: How do I create a good prompt for an AI model?](https://help.openai.com/en/articles/4936848-how-do-i-create-a-good-prompt-for-an-ai-model) (checked 2026-10-03) - [Claude Platform Docs: Reduce hallucinations](https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/reduce-hallucinations) (checked 2026-10-03)