--- title: "How to write a good AI prompt: a step-by-step guide" canonical_url: "https://tryiro.com/blog/how-to-write-a-prompt" site: "Iro AI" site_url: "https://tryiro.com" app_store: "https://apps.apple.com/app/id6759628066" language: en-US keywords: ["how to write a prompt", "how to write a good AI prompt", "how to write ChatGPT prompts", "prompt writing guide", "how to prompt AI"] date_published: "2026-06-05" date_modified: "2026-06-05" reading_time_minutes: 7 author: "Alex Furukawa" license: "© 2026 Iro AI" canonical_llm_reference: "https://tryiro.com/llms-full.txt" pillar: "prompt-engineering" --- # How to write a good AI prompt: a step-by-step guide > A good prompt has four parts: context, role, task, and format. Add those, then refine the first answer. Here's the simple recipe, with before-and-after examples you can copy. **Canonical:** https://tryiro.com/blog/how-to-write-a-prompt **Published:** 2026-06-05 **Reading time:** ~7 min **Author:** Alex Furukawa — Founder of Iro AI ## Key takeaways - A good prompt has four parts: context (background), role (who the AI should act as), task (what to do), and format (how you want the answer). - The biggest upgrade to a weak answer is usually more context and a specific format — not a 'magic' phrase. - Treat the first answer as a draft and refine it; iteration is part of prompting. - The same recipe works across ChatGPT, Claude, Gemini, and Perplexity. ## How do you write a good AI prompt? **A good prompt gives the AI four things: context, a role, a clear task, and the output format you want.** Most weak answers come from skipping these — the model has to guess what you mean. Add them and you'll get sharp, useful results from ChatGPT, Claude, Gemini, or any other tool. Then treat the first answer as a draft and refine it. ## The four parts of a great prompt - **Context** — the background the AI needs: who it's for, what you've tried, any constraints. _"I'm emailing a client who missed a deadline; tone should stay warm."_ - **Role** — who the AI should act as: _"You are an experienced customer-success manager."_ - **Task** — the specific thing to do: _"Write a 3-sentence reply that asks for a new date without blaming them."_ - **Format** — how you want it: length, structure, tone. _"Under 80 words, friendly, no jargon."_ You won't need all four every time, but the more ambiguous the task, the more they help. This is the heart of [prompt engineering](/blog/what-is-prompt-engineering). ## Before and after: a weak prompt vs a good one **Weak:** `write a post about our new feature` You'll get something generic, because the AI is guessing the audience, tone, length, and the feature itself. **Good:** `You are a product marketer. Write a LinkedIn post (under 120 words, confident but not hypey) announcing our new AI feedback feature for our app that helps people learn AI. Audience: busy professionals. End with a question to drive comments.` Same model, dramatically better output — because it now has context, a role, a task, and a format. For more reusable structures, see [the 7 prompt patterns that work everywhere](/blog/prompt-engineering-patterns). ## How to refine the first answer The first answer is a draft, not the deliverable. Improve it with quick follow-ups: - **Adjust:** "Make it shorter / more formal / more specific." - **Add an example:** show one sample of "good" and ask it to match. - **Ask for options:** "Give me three versions, ranked." - **Push back:** "That intro is generic — try a sharper hook." Two or three rounds of this beats hunting for a perfect one-shot prompt. ## Common prompting mistakes **Being vague.** "Make it better" gives the model nothing to aim at — say what "better" means. **Skipping context.** The AI can't read your mind about audience or constraints. **Accepting the first draft.** Iterating is where the quality comes from. **Chasing magic words.** There aren't any — clarity beats tricks. If your prompts keep underperforming, see [why your AI prompts aren't working](/blog/why-your-ai-prompts-arent-working), and practice hands-on in the [Prompt Lab](/prompt-engineering-app). ## FAQ **How do you write a good AI prompt?** Give the AI four things: context (the background), a role (who it should act as), a clear task (what to do), and the format you want (length, structure, tone). Then treat the first answer as a draft and refine it with quick follow-ups. **What is the formula for a good prompt?** A reliable formula is Context + Role + Task + Format: tell the AI the situation, who to be, exactly what to do, and how you want the answer. The more ambiguous the task, the more these matter. **Why are my prompts not working?** Usually the prompt is too vague or missing context and a clear format. Add who it's for, the constraints, and exactly what 'good' looks like, then iterate on the first answer instead of starting over. **Does the same prompt work on ChatGPT, Claude, and Gemini?** Mostly yes. The context-role-task-format structure works across all major AI tools. You tune small details per model, but the core recipe transfers. ## Read next - [The 7 prompt patterns that work everywhere](https://tryiro.com/blog/prompt-engineering-patterns) - [15 ChatGPT prompts for beginners](https://tryiro.com/blog/chatgpt-prompts-for-beginners) - [Why your AI prompts aren't working](https://tryiro.com/blog/why-your-ai-prompts-arent-working) - [Take the free AI IQ test](https://tryiro.com/quiz) ## About the author Alex Furukawa — Founder of Iro AI. Alex Furukawa is the founder of Iro AI, the gamified app for learning to use AI well. He writes about practical AI fluency — prompting, AI tools, and the daily habits that turn AI from a novelty into real leverage.