--- title: "Why AI answers come back vague" url: https://aiguideson.com/courses/prompting-for-beginners/why-answers-come-back-vague/ course: "Prompting for beginners" lesson: "1 of 5" minutes: 8 published: 2026-10-03 updated: 2026-10-03 author: "Jack Stovell" publisher: "Adapt Progress Evolve Limited" language: "en-GB" --- # Why AI answers come back vague Lesson 1 of 5 in [Prompting for beginners](https://aiguideson.com/courses/prompting-for-beginners/) · 8 minutes When an AI reply comes back vague or generic, it’s usually because the prompt left gaps and the AI filled them with guesses. In this lesson you’ll send the same job twice, once in one line and once with the details, and see exactly what it guessed. ## You need - A free ChatGPT or Claude account - About ten minutes A narrated walkthrough of this lesson is coming. The steps below cover everything in it. ## Steps ### Step 1: Send a one-line prompt Start a new chat and send the one-line prompt below. It’s the kind of thing most people type first. Our example is a home bakery replying to a customer who asked about a gluten-free cake. The prompt (works in ChatGPT, Claude or any AI chat tool): ```text Write a reply to a customer asking about a gluten-free cake. ``` - This is deliberately vague: it says what to write, but nothing about who you are or what you want to say. (Screenshot to come.) Checkpoint: You’ve got a reply to a one-line prompt. ### Step 2: See what it guessed Our one-line prompt got a long reply full of guesses. It said yes, the bakery could make a gluten-free cake, which wasn’t true. It left gaps in square brackets for flavours, sizes and prices, used dollars, and offered two different kitchen notes to choose from. It wasn’t being careless. It just had nothing else to go on. ![Our two prompts and the two replies side by side. On the left, the one-line prompt and a long reply that says yes to a gluten-free cake, with gaps to fill and prices in dollars. On the right, the specific prompt with five rules and a short reply that politely says no, signed by Jo.](https://aiguideson.com/courses/prompting-for-beginners/l1-vague-vs-specific.png) (screenshot captured 3 October 2026) 1. Vague: one line, no details 2. It guessed: says yes, you can make one 3. Gaps to fill in, and prices in dollars 4. Specific: who, what to say, length, sign-off 5. It said what you asked it to say 6. Still check: it promised something on someone else's behalf Checkpoint: You can point to at least three things in your reply that it guessed. ### Step 3: Send a specific prompt Start a new chat and send the specific version below. It says who we are, what the customer asked, what we want to say, how long it should be and who signs it. The prompt (works in ChatGPT, Claude or any AI chat tool): ```text I run Brook Lane Bakes, a small home bakery. A customer called Priya has emailed to ask if I can make a gluten-free birthday cake for her daughter's party. Write my reply email. - I can't make gluten-free cakes: I use wheat flour in my kitchen every day, so I can't rule out traces - I'd still like to help, so suggest she looks for a specialist gluten-free baker - Keep it warm and short: under 120 words - Sign it from Jo at Brook Lane Bakes - Don't promise anything I haven't said here ``` - It says who you are and who the customer is. - It says what to say, including the reason, so the AI doesn’t invent one. - It sets a length, a sign-off and a rule against promising anything else. (Screenshot to come.) Checkpoint: You’ve got a reply to the specific prompt. ### Step 4: Compare the two, then check the good one too The specific prompt got a short, warm reply that said what we wanted. But read it closely, because it also said a specialist baker "will be able to guarantee a safe bake". We never said that, and we can’t promise it for someone else. A better prompt means fewer guesses, not none. (Screenshot to come.) Checkpoint: You’ve read the good reply line by line and found anything you didn’t say. ### Step 5: The rule for the rest of this course AI fills every gap you leave, so the more you tell it, the less it guesses. Anthropic, which makes Claude, puts it this way: show your prompt to a colleague who knows nothing about the job. If they’d be confused, the AI will be too. (Screenshot to come.) Checkpoint: You can explain why a vague prompt gets a vague answer. ## Common problems ### Your vague reply looks fine Look again for anything it assumed: prices, what you offer, your name, your tone. A reply can read well and still be built on guesses. ### The reply uses American spelling or dollars It doesn’t know where you are unless you say. Add "UK English" and "prices in pounds" if those matter. The screenshot is our own page showing the two prompts and replies word for word, captured by tools/capture/prompting-for-beginners.mjs; it is not the chat screen. The chat screens themselves need a signed-in account, so they have no screenshot yet. ## Sources - [Claude Platform Docs: Prompting best practices](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices) (checked 2026-10-03) - [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)