AI slop happens when AI sits in the director's chair
Every nonprofit can now make more content than it can read. The teams that sound like themselves keep one job for people: deciding.
This prompt bridges the gap between what your programs track and what your donors need to hear.
Turn our program data into the narrative section of a donor impact report. Open with a story, not a statistic. Weave the numbers in naturally, show what donors made possible and close with a look ahead. This is stewardship, not a solicitation, so no ask. Use exact numbers, and put the people we serve at the center, not our organization. What you need to know: - the time period and the programs to cover - who this report is for - our raw numbers by program - a true story or quote from someone we serve 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.
You're helping me turn our program data into the narrative of a donor impact report. 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 "AI slop happens when AI sits in the director's chair" (https://ifpossible.ai/articles/ai-slop-directors-chair), 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 programs in this report, who's reading it and our voice. (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 what these numbers meant for real people. If I have a transcript of program staff describing it, I'll give it to you. Pull the story out of their 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. Give me two or three ways to open, each built on a different story or result, 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. An outline, then a narrative I can react to. Open with a story, weave in the numbers by program, show what donors made possible and close with a look ahead. No ask. 6. Check your own work. Use exact data and never inflate. List every figure so I can match it to our records, and tell me whether each section centers the people we serve or our organization. 7. Make it repeatable. When we finish, write down the steps and the numbers we needed, so the next report starts here. What you need to know: - the time period and the programs to cover - who this report is for - our raw numbers by program - a true story or quote from someone we serve 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.
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 program data into a compelling impact narrative for donor stewardship reports. It opens with a story, not a statistic, weaves your data in naturally, shows what donor investment made possible and closes with a forward-looking statement. This is stewardship, not a solicitation, so there’s no ask.
Match every figure to your source. The prompt says to use exact data and not inflate. Then check whose story it tells: the people you serve should be at the center, not the org.
Every nonprofit can now make more content than it can read. The teams that sound like themselves keep one job for people: deciding.
AI knows almost everything and still gets your facts wrong. Here's how we hunt for errors, stop the flattery, and teach AI not to repeat a mistake.
Speed of gratitude drives second gifts. Here is a donor thank-you system that gets a personal note out within a day of every gift, with a person on the part that matters.