What is a Mission Brain? The AI memory every nonprofit needs
Your AI forgets you the moment a chat ends. A Mission Brain is the long-term memory it reads first, so every task starts from who you really are.
Upload your grant history, funder feedback, donor transcripts and campaign retrospectives, then ask them questions in plain English.
I'm going to give you our development files: grant applications, funder feedback, donor conversation transcripts and campaign retrospectives. Read what you have, tell me what's there and what's missing, then help me answer one of three questions. One: what patterns do you see in our funder relationships? Two: which donor relationships and know-how live with one person and are at risk if they leave? Three: which campaign approaches worked, and which didn't? Point to the document behind every finding. If you can't see any files, say so in your first reply, then work only from what I tell you and label each finding as my words, not a document. What you need to know: - our organization's name - which files you can see, or which ones I should upload - which of the three questions I want answered - who will use the answer - what decision it's for 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 turn our development files into something we can ask questions of. 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: "What is a Mission Brain? The AI memory every nonprofit needs" (https://ifpossible.ai/articles/what-is-a-mission-brain). 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, our funders, our campaigns and who holds which relationships. 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. Before you read, I'll tell you what I think we'd find and what I'm worried we've lost. Use that to decide where to look. 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 questions worth asking these files first, with your recommendation and a one-line reason that uses only what I've told you. Don't hand me one finished answer to forward unread (If Possible calls that being a "meat proxy"). 5. Findings I can react to. For the question I pick, give me the patterns you found, the document behind each one and what you'd do next. Keep it to one page. 6. Check your own work. Point to the document behind every finding. If you can't see any files, say so in your first reply, then work only from what I tell you and label each finding as my words, not a document. Say plainly what the files don't show, and never fill a gap with a guess. Warn me before you repeat anything sensitive. 7. Make it repeatable. With the draft, tell me what to add to our Mission Brain, and what to record from now on so this knowledge stops living in one person's head. What you need to know: - our organization's name - which files you can see, or which ones I should upload - which of the three questions I want answered - who will use the answer - what decision it's for 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 reads your grant applications, funder feedback, donor transcripts and campaign retrospectives, tells you what’s there and what’s missing, then answers one of three questions: what patterns show up with funders, which relationships and know-how are at risk if someone leaves, and which campaign approaches worked. Every finding points to its document.
Check what you’re uploading first. On a paid plan with model training switched off, these files sit in much the same place as your donor database. On a free tool, keep them out.
Your AI forgets you the moment a chat ends. A Mission Brain is the long-term memory it reads first, so every task starts from who you really are.
Your team does its best thinking out loud, then lets it disappear. Here's how we record nearly every meeting, ask for consent, and put the transcripts to work.
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.