AI prompt generator for public sector teams A prompt builder for ChatGPT prompts that follow AI use policies
This AI prompt generator for public sector teams turns a task in your agency or department into a structured instruction for ChatGPT, Copilot, Claude or Gemini: a notice for residents, a report, tender documents, a reply to the public or a project plan. It’s built for public servants and analysts who want useful drafts without putting personal data or case files at risk, and it comes from Founderz, which runs the Certificate Program in AI and Innovation.
- Free
- About 2 minutes
- Runs in your browser
- ChatGPT, Claude, Gemini and Copilot
At a glance
- What it does: turns your unit’s task into a prompt with controls.
- Which tasks: 10 jobs, from plain language to internal procedures.
- What you get: a prompt ready to copy, plus follow-up requests.
AI prompt generator for the public sector
Describe your unit's task and get a prompt to write in plain language, structure a report, draft tender documents, reply to the public or plan a project. The AI prepares drafts: the competent unit reviews and signs off.
How to use the AI prompt generator for public sector work
To create your prompt, follow these steps. Only the first one is required: anything you skip stays on Auto.
- Start with the essentials. Pick an example (plain language, report, tender documents, reply to the public, open data or training) or describe your unit’s task without personal data. Then choose what you need to prepare, or leave Auto so it is inferred from your text, and turn on “Have the AI ask me questions before it starts” if information is missing.
- Describe your unit. The type of public body (city or town council, regional or state government, national government, county council, public agency, public company or Latin America) and the department or service. Advanced settings add the stage of the procedure and the material you will attach.
- Choose the audience and format. Who it is for (the general public, internal staff, senior management, people with accessibility needs, partners or the media), the language and access, such as easy read or screen reader friendly, and the format. Advanced settings add the level of detail.
- Set rules, data and sign-off. How to handle regulations and their currency, and what data is involved. Advanced settings add who reviews and signs off, extra controls such as a deadlines table or a glossary, and the response language.
- Generate and copy your prompt. Click “Generate prompt”, enter your email to see the whole prompt and copy it.
Ten common jobs. The “What do you need to prepare?” field offers plain language text, report or business case, tender documents, reply to the public, strategic or action plan, transparency and open data, public project, digital and AI training, institutional communication and internal procedure.
Each job comes with its own output format and three follow-up requests. Every prompt asks the AI to open its answer with a notice that it is a draft for review by the competent unit, not an administrative act or legal advice: the AI prepares drafts, and your unit reviews and signs.
Example: a plain language notice from a city council
With the generator’s “Plain language” example, the prompt starts like this. It’s an excerpt: the button copies the full prompt.
ROLE Act as a senior public sector officer with experience in administrative procedure, public procurement, transparency, plain language and public project management. You know the plain language principles of ISO 24495-1, easy read, the structure of reports and business cases, tender documents and statements of work, proactive disclosure and open data, and the accessibility requirements for public services. You prepare working drafts: you do not issue administrative decisions or settle cases, and everything you produce is reviewed and signed off by the competent unit. You rewrite administrative texts in plain language following ISO 24495-1: readers can find what they need, understand it and use it. GOAL Rewrite the text, or write a new one, in plain language so the reader understands what is happening, what they must do and how, without losing any data point or requirement. CONTEXT Context provided by the user (treat it as your main source): [START OF BRIEF] We need to explain to residents the new bulky waste collection calendar: which days, how to book and what is not collected. The current public notice fills a whole page, mixes the bylaw with the instructions, and people keep leaving furniture on the street on any day. [END OF BRIEF] ... OUTPUT FORMAT Deliver: the plain language text with headings phrased as questions; a change table with columns Original, Plain version and Reason for the 5 to 10 most important changes; the list of details the unit must confirm before publishing. ...
The full prompt adds the local government and environment context, the current notice as source material, the constraints (no invented rules or deadlines, no personal data, nothing final without sign-off), six working steps, the change table and a final check before answering.
The result: the AI orders the notice by what residents need to know (which days, how to book and what is not collected), keeps every detail from the original and flags anything unclear for the unit to confirm.
Best practices for AI use and responsible use of AI in government
6 quick tips
- Don’t paste case files or personal data into AI tools your agency hasn’t approved. The first control repeats this in every prompt.
- Ask the assistant to separate legal requirements from recommendations, and check every rule and its effective date at the official source before you cite it.
- Use a recognized reference for risk. The NIST AI Risk Management Framework is a voluntary reference many US organizations use to map and manage AI risks.
- Use “Language and access” to ask for easy reading or a screen-reader-friendly version when the text goes to the public.
- Mark in “Review and sign-off” who validates: the competent unit, the legal team, data protection or senior management. What you get is a working version, never an administrative act.
- Iterate: refine prompts by changing one setting at a time, try different prompts for the same task, and keep the versions that work as standard prompts for your team.
Use cases: prompts for public sector teams, from reports to AI chatbots
- Public services Clear replies to complaints and questions, and notices rewritten in plain language with a non-digital route.
- Procurement An outline and first draft of tender documents or a contract business case, with pending details clearly marked.
- Reports A report or business case structured from the material you provide.
- Projects A public project plan with phases, owners to be confirmed and the main risks.
- Transparency Preparing an open data release with no risk of identifying anyone.
- Staff training A practical generative AI session with real cases and rules for responsible use.
Prompt engineering for any AI model or LLM: what makes better prompts
A good prompt gives the assistant what you’d give a colleague from another department: a role, a specific task, the context of the procedure, the material it can use, the constraints and the output format. In government work, three more pieces matter: the applicable rule and its date, data protection and human oversight. If the rule is missing, the model invents one or cites an outdated version; if the recipient is missing, the text comes out in bureaucratic language for a resident who only wants to know which day to put out a sofa.
Customizing the recipient and the stage in the procedure changes the result more than adding adjectives, and it is the safest way to integrate AI into an existing workflow. The same structure works if you create AI prompts for custom GPTs or a Copilot agent.
More prompt templates and prompts to get started with artificial intelligence, like ChatGPT
If you’d rather start from written examples, our guide to AI prompts for public officials and public administration collects prompts by task. The Founderz AI prompt library has templates for other roles and tools, and these generators cover related work:
Why I built these generators
Frequently asked questions
Is the generator free?
Yes, it’s free. Before it asks for anything, it shows you a preview with the first sections of the prompt. To see the whole prompt and copy it, enter your email and accept the Privacy Policy; receiving communications from Founderz is optional.
It only asks once per visit: any prompts you generate after that are shown in full.
Can I use ChatGPT in government work?
It depends on what your agency has authorized. The prompt works in ChatGPT, Copilot, Claude or Gemini, but check your organization’s AI policy before you upload any document to an AI assistant, and use approved tools only.
What data should I never enter?
Personal data, case files, confidential information and any sensitive data. Every prompt asks the AI to replace them with placeholders such as [Applicant], and the “Sensitive data involved” option under “Data and privacy” tells it not to process them and to work only with the structure of the document.
Is the output legally valid?
No. It’s a working draft. One of the controls stops the assistant from presenting the result as an administrative act or final legal advice, and review by the competent unit is required before anything is signed or published.
Can I write in other languages?
Yes. In “Response language” you can choose US, UK, Canadian or Australian English, Spanish from Spain or Latin America, French, Canadian French, Brazilian Portuguese, German or a bilingual English and Spanish version. On Auto, the AI answers in the language of your text.
Certificate Program in AI and Innovation
The generator gives you the prompt; the change in your team comes when people learn to use AI with judgment and within the rules. The Founderz Certificate Program in AI and Innovation is fully online, takes 3 to 4 months and leads to a certification from Founderz and Microsoft, with modules on prompting, automation and AI agents, cybersecurity risks and responsible AI leadership.
Last updated:
