--- title: "Prompt Engineering Part 2 - From Bad to Excellent: How to Transform Your AI Prompts" description: "Title tag: From Bad to Excellent Prompts: A Simple Upgrade Path for AI\nMeta description: Learn how to move from vague AI prompts to excellent, structured briefs that deliver useful, publishable results. The difference between bad and excellent AI prompts is not magic. It is structure, context, and iteration." image: https://www.augmentednewsroom.org/hubfs/BAF%20GOOD%20EXCELLENT-1.png --- ![27 Outline Logo](https://443642032.fs1.hubspotusercontent-ap1.net/hubfs/443642032/27%20Outline%20Logo.svg) - [Home](https://www.augmentednewsroom.org) - [Case Studies](https://www.augmentednewsroom.org/case-studies) - [About](https://www.augmentednewsroom.org/about-augmented-newsroom) - [Founder](https://www.augmentednewsroom.org/founder-augmented-newsroom) [contact us](mailto:malito:alib@augmentednewsroom.org) ## Prompt Engineering Part 2 - **From Bad to Excellent:** How to Transform Your AI Prompts ![](//443642032.fs1.hubspotusercontent-ap1.net/hubfs/443642032/raw_assets/public/@marketplace/if_else_agency/Aesthetics/assets/images/icons/arrow-down.svg) ![](https://443642032.fs1.hubspotusercontent-ap1.net/hubfs/443642032/BAF%20GOOD%20EXCELLENT-1.png) Your AI isn't the problem. Your prompt is. Two people can type the same request into the same tool and get completely different results. One walks away with generic fluff. The other gets a sharp, usable output they can build on. The gap between them isn't the type of AI agent they use. It's the difference between bad, normal, good and excellent prompts. See the difference on one real journalism task: summarising local council meeting documents. Bad vs Normal vs Good vs Excellent (same task, four levels) --- Before we start, remember: **Always treat the first output as a draft, not the final result you will use.** Edit and refine it until it meets your needs. Once you have a prompt that consistently produces the result you want, save it as a reusable template. ---   Task: Research local council meeting documents and provide a summary. Bad prompt: "Summarise these council meeting documents." - No focus, no audience, no constraints. - Output: generic overview with no clear news angle. Normal prompt: "Summarise these local council meeting documents in one paragraph." - Clear task, but still no topic focus or intended use. - Output: slightly tighter, but still broad and not story-ready. Good prompt: "Summarise these local council meeting documents in one paragraph to be used in a local news newsletter. Focus on decisions about council spending and any new flood early warning systems. Use active voice, keep it under 120 words, and avoid jargon." - Adds audience (newsletter readers), topic focus (spending, flood warnings), and constraints (length, style). - Output: more targeted, closer to publishable. Excellent prompt: "You are an experienced local government reporter. Summarise the attached council meeting documents in one paragraph to be used in a local news newsletter aimed at residents. Prioritise: (1) any decisions or debates about council spending, especially large or controversial items; (2) any updates on flood early warning systems, including timelines, costs, and responsible departments. Use active voice, third person, under 120 words, no jargon. If the documents mention specific dollar figures, suburbs, or deadlines, include them. If they do not mention spending or flood warnings, say that clearly instead of guessing. Treat this as a first draft for an editor to refine. Don't invent or fabricate anything. Give me a confidence score of how accurate the result is." - Full brief: role, audience, priorities, constraints, and explicit handling of missing information. - Output: focused, factual, and ready to edit into a story or newsletter item. ### The Anatomy of a Great AI Prompt To create a great prompt, follow these steps:  - State the task clearly, mentioning the priorities.  - Ask AI to use the supplied material if any.  - Tell it to flag missing information rather than guess. - Define the audience and intended use (internal vs external use). - Set tone and style (active voice, third person, etc). - Request a specific format (number of words or paragraphs). - Tell the AI agent what to avoid, such as emojis or unsupported additions. Add instructions to avoid fabrication and hallucinations. **Always treat the first output as a draft, not the final result you will use.** Edit and refine it until it meets your needs, then verify it before use. Once you have a prompt that consistently produces the result you want, save it as a reusable template. [**Ali Bahnasawy with AI Support**](https://www.augmentednewsroom.org/case-studies/author/ali-bahnasawy-with-ai-support) #### My awesome resource Vivamus suscipit tortor eget felis porttitor volutpat. Curabitur arcu erat, accumsan id imperdiet et, porttitor at sem.  Discover ## Related **blog posts** ![](https://443642032.fs1.hubspotusercontent-ap1.net/hubfs/443642032/pexels-mizunokozuki-12899156.jpg) **Prompt Engineering for Media Professionals - Part 1** Most people get mediocre results from AI because they treat prompts like casual questions and accept the first answer... Read more ![](https://443642032.fs1.hubspotusercontent-ap1.net/hubfs/443642032/WP%20Images-1.png) **Ask The Post AI: Grounding Chatbot Answers in Verified Reporting** At a Glance Organization: The Washington Post Country: United States AI tool: Ask The Post AI — a generative AI... Read more ![](https://443642032.fs1.hubspotusercontent-ap1.net/hubfs/443642032/chatgpt%20desktop2.jpg) **From 3 Weeks to 2 Days: AI in Data Journalism** At a Glance Organization: Independent journalist Jacopo Ottaviani; original 2012 project published on the Guardian... Read more ![Grey Augmented Newsroom](https://443642032.fs1.hubspotusercontent-ap1.net/hubfs/443642032/Grey%20Augmented%20Newsroom.svg) Augmented Newsroom helps journalists and newsrooms use AI responsibly — faster reporting without sacrificing accuracy or editorial standards. - [Home](https://www.augmentednewsroom.org) - [Case Studies](https://www.augmentednewsroom.org/case-studies) - [About](https://www.augmentednewsroom.org/about-augmented-newsroom) - [Founder](https://www.augmentednewsroom.org/founder-augmented-newsroom) ```json { "@context" : "https://schema.org", "@type" : "BlogPosting", "author" : { "@type" : "Person", "name" : "Ali Bahnasawy with AI Support", "url" : "https://www.augmentednewsroom.org/case-studies/author/ali-bahnasawy-with-ai-support" }, "dateModified" : "2026-09-15T03:15:10.216Z", "datePublished" : "2026-09-14T07:06:33.000Z", "headline" : "Prompt Engineering Part 2 - From Bad to Excellent: How to Transform Your AI Prompts", "image" : [ "https://www.augmentednewsroom.org/hubfs/BAF%20GOOD%20EXCELLENT-1.png" ], "mainEntityOfPage" : { "@id" : "https://www.augmentednewsroom.org/case-studies/from-bad-to-excellent-how-small-changes-transform-your-ai-prompts", "@type" : "WebPage" }, "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject" } } } ```