Is it safe to put donor data into AI?
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.
Give it your giving data and get back which segments are at risk, why, and three things you can do this week.
Analyze our donor giving data and show me where we're losing people. If I give you a file, run the numbers on the file and show your work. Tell me which segments are most at risk and why, the early warning signs, three things we can do this week, three changes to our stewardship and what to track from now on. Name segments and timelines, and mark anything you inferred. You don't need donor names for this, so tell me if a file holds more than you need. What you need to know: - our organization's name - our giving data: an export or a summary by segment - what worries me most: overall retention, major donors, recurring donors or first-time donors - how we define a lapsed donor - what stewardship we do now 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, the most important first: one question mark, one fact, no recap. If I don't have it, mark the gap and move on. When I say go, stop asking and write the draft. Don't make anything up. Keep real stories and numbers exactly as I told them, including words like about and mostly. Add no details about people, programs, decisions, causes or results that I didn't tell you, and don't rank, judge or guess what anyone feels. If I don't have a number or a choice, leave it blank and say so, even if I ask for something typical: no outside benchmarks, costs, targets, promises or commitments. Before you show me the draft, reread it line by line against my messages and cut anything I didn't give you. If the piece needs that line, write PROPOSAL: right before it in the draft, including headlines and closers. Joining my facts in a plain sentence is fine. State a word count only if you counted. After the draft, list what you assumed and every proposal.
You're helping me find where we're losing donors and what to do about it this week. Work the way If Possible (ifpossible.ai) teaches nonprofit teams. If you can read web pages, read their guide first and use it as our playbook: "Is it safe to put donor data into AI?" (https://ifpossible.ai/articles/donor-data-ai-safety). 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, how we define our donor segments, what stewardship we do now and what we've already tried. Keep it in your head, and show it only if I ask. (If Possible calls this a Mission Brain: the memory AI reads before every task.) 2. Talk it out instead of typing it out. I'll talk through what I'm seeing and what worries me. Use my own words to decide where to look first. 3. Ask before you assume. Ask only what would change the work. Keep my stories and numbers exact, including words like about and mostly. Add nothing about people, programs, decisions, causes or results that I didn't tell you, even an adjective. Don't rank, judge or guess feelings. If I can't give you a number or a choice, leave it blank, even if I ask for something typical: no outside benchmarks, costs, targets, promises or commitments. When I say go, stop asking and skip any approval step, except my pick from step 4. Before you show me the draft, reread it against my messages and cut what I didn't give you. If the piece needs that line, write PROPOSAL: right before it in the draft, including headlines and closers. Joining my facts in a plain sentence is fine. State a word count only if you counted. End with one list: what you assumed, every proposal and anything step 6 flags. 4. I'm in the director's chair. Give me two or three places to focus first, 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 scan I can react to. Which segments are at highest risk and why, early warning signs, three things to do this week, three changes to our stewardship and what to track from now on. 6. Check your own work. Run the numbers on the data and show your work. Mark anything you inferred, and tell me if the file holds more personal detail than this job needs. 7. Make it repeatable. With the draft, write down the steps and the metrics, so we can run this scan again. What you need to know: - our organization's name - our giving data: an export or a summary by segment - what worries me most: overall retention, major donors, recurring donors or first-time donors - how we define a lapsed donor - what stewardship we do now You may already know some of this from our past chats, my files or connected tools. Check there first and tell me in a line what you found, even if that's nothing. Don't repeat this plan or my answers back to me. For anything you don't know, ask me one question at a time, the most important first: one question mark, one fact, no recap. If I don't have it, mark the gap and move on. Start now.
We’ll add the If Possible method to your prompt. More context in. A better output out.
Same job. Here’s what changed. More context in. A better output out.
It points your AI to our free articles as its guide. Read every word before you use it.
It turns raw giving data into a retention action plan with five parts: a risk assessment by segment, early warning signs, three immediate actions, three changes to your stewardship and what to track going forward. Give it a file and it runs the numbers.
Before donor data goes in, check three things: your AI plan’s training opt-out, its SOC 2 Type 2 certification and your own AI policy. Treat anything marked inferred as a question to test, not a fact.
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.
Most nonprofits only give their biggest donor the personal treatment. AI can find who else deserves it and help you prepare for every one of those conversations.
Five nonprofit email templates AI can tailor to each donor, with personalization slots that turn one good draft into hundreds that read one-to-one.