Title: Nonprofit AI Safety Guide Prompt · If Possible URL: https://ifpossible.ai/prompts/ai-safety-policy Summary: Write a practical AI safety guide for your nonprofit staff: what’s safe to share, when to pause for a person and what to do if it goes wrong. Free AI prompt. Publisher: If Possible (https://ifpossible.ai), AI for nonprofits --- 1. [Supercharged Prompts](https://ifpossible.ai/prompts) 2. [Set up your AI](https://ifpossible.ai/prompts?c=setup) 3. AI Safety Guide for Staff Set up your AI # An AI safety guide your staff can actually follow A practical guide for your team: what’s safe to share with AI tools, how to protect donor data, when to pause for human approval and what to do if something goes wrong. ## Basic prompt 166 words ``` Write a practical AI safety guide for our staff: one page someone would actually read in their first week. Cover what is and isn't safe to share with AI tools for our kinds of data, a simple table of what needs a pause, what needs approval and what never goes in, guidance for each role, a short checklist to run before any AI-assisted action, and what to do if something goes wrong. No jargon. This is not legal advice, so note anything a qualified professional should review. What you need to know: - the AI tools we use or plan to use - the kinds of sensitive data we handle - the staff roles that use AI - who staff should go to with a question or a problem You may already know some of this from our past chats, my files or connected tools. Use what you have. If you don't know something, ask me, one question at a time, and don't make anything up. ``` ## Supercharged prompt 448 words ``` You're helping me write a practical AI safety guide our staff will actually read. I want to work the way If Possible (ifpossible.ai) teaches nonprofit teams to do real work AI first. Their guide for this kind of work is "Is it safe to put donor data into AI?" (https://ifpossible.ai/articles/donor-data-ai-safety), and their full library of guides is at https://ifpossible.ai/articles. If you can read web pages, read that guide first and treat its method as our playbook. The If Possible method, as we'll use it today: 1. Context before content. Before you draft anything, build a short brief of who we are: our mission, the people we serve, the data we hold, the AI tools we use and the roles that use them. (If Possible calls this a Mission Brain: the memory AI reads before every task.) Use what you already know about us, and ask me for whatever is missing. 2. Talk it out instead of typing it out. I'll talk through how people here really use AI day to day, and the moments I worry about. Use my own words. 3. Ask before you assume. Ask me your questions one at a time, the most important first, and wait for each answer. 4. I'm in the director's chair. Where there's a real choice, like what needs approval and who gives it, give me two or three options with your recommendation and a one-line reason. Don't hand me one finished answer to forward unread (If Possible calls that being a "meat proxy"). 5. A one-page guide I can react to. Why this exists and who it's for, what is and isn't safe to share, a table of sensitive data with what to do (pause, get approval or never use AI), guidance for each role, a short checklist before any AI-assisted action, and what to do if something goes wrong. 6. Check your own work. Read it as a new hire would and flag any jargon. Never invent a compliance requirement. Note anything a qualified professional should review. 7. Make it repeatable. When we finish, write down who owns this guide and when to review it, so it stays true as our tools change. What you need to know: - the AI tools we use or plan to use - the kinds of sensitive data we handle - the staff roles that use AI - who staff should go to with a question or a problem You may already know some of this from our past chats, my files or connected tools. Check there first and tell me what you found. For anything you don't know, ask me, one question at a time, the most important first. Start now. ``` ## Supercharge it We’ll add the If Possible method to your prompt. **More context in. A better output out.** - Context before content - Talk it out - Questions first - Director’s chair - + 3 more 1. Context before content: a short brief of who you are (a Mission Brain) 2. Talk it out: how people here really use AI 3. Questions first, one at a time 4. Director's chair: options and a recommendation 5. A one-page guide with a table and a checklist 6. It reads as a new hire and flags jargon 7. It names an owner and a review date It points your AI to our free articles as its guide. Read every word before you use it. ## What it will ask you Nothing to fill in. Your AI may already know some of this. If it doesn’t, it asks, one question at a time. - The AI tools we use or plan to use - The kinds of sensitive data we handle - The staff roles that use AI - Who staff should go to with a question or a problem It goes faster once your AI has your [Mission Brain Brief](https://ifpossible.ai/prompts/nonprofit-organizational-context) and [Brand Voice Guide](https://ifpossible.ai/prompts/nonprofit-brand-voice-guide). ## What it’s for It builds a one-page guide for staff, not the board: what’s safe to share, what needs a pause or an approval, guidance for each role, a checklist to run before any AI-assisted action and what to do if something goes wrong. It pairs with your [AI Policy](https://ifpossible.ai/prompts/ai-ethics-policy). ## When to use it - New staff are starting and need one document they can read in their first week. - Different roles use AI differently and need role-specific guidance. - You want a quick-reference checklist people can use before any AI-assisted action. ## Before you use it This is not legal advice. If a section touches on compliance, have a qualified professional review it. Then walk a real staff member through it and fix whatever confuses them. ## Try these next [All 33 prompts](https://ifpossible.ai/prompts) - [**AI Policy** Work through the real decisions, then get a policy your staff can follow.](https://ifpossible.ai/prompts/ai-ethics-policy) - [**AI Guardrails** Create a standing rule layer your team pastes into any AI tool.](https://ifpossible.ai/prompts/ai-guardrails) - [**Mission Brain Brief** Build the one-page briefing you paste at the top of every AI conversation.](https://ifpossible.ai/prompts/nonprofit-organizational-context) The Possible Passport ## There’s more in your free library The Possible Passport is our free member library. Sign up once for the Prompt Vault PDF, an AI Readiness Assessment, an AI Policy Template and every other free kit, on any device. The AI Policy Template in the Starter Pack pairs well with this work. Keep reading ## From The Art of the Possible AI Strategy ### [Is it safe to put donor data into AI?](https://ifpossible.ai/articles/donor-data-ai-safety) If you trust your CRM with donor data, a paid AI plan with model training switched off can earn the same trust. Here's what to check first. [Read the article: Is it safe to put donor data into AI?](https://ifpossible.ai/articles/donor-data-ai-safety) AI Strategy ### [Writing your nonprofit's first AI policy](https://ifpossible.ai/articles/first-ai-policy) Your first AI policy fits on one page and leads with principles, not prohibitions. Here is what to include, plus an outline you can use. [Read the article: Writing your nonprofit's first AI policy](https://ifpossible.ai/articles/first-ai-policy) AI Strategy ### [What your nonprofit should never hand to AI](https://ifpossible.ai/articles/never-hand-to-ai) We push nonprofits to use AI almost everywhere. A few things stay human every time, because the effort is the message. Here's where we draw the line. [Read the article: What your nonprofit should never hand to AI](https://ifpossible.ai/articles/never-hand-to-ai) [All articles](https://ifpossible.ai/articles/)