Let's Talk Fundraising
Welcome to "Let's Talk Fundraising" with Keith Greer, CFRE! This podcast is your go-to resource for mastering the essentials of fundraising while discovering how innovative tools and technology can supercharge your efforts. Whether you're a new fundraiser looking to level up your skills or a seasoned professional seeking timely reminders and fresh insights, each episode is packed with practical advice, creative ideas, and inspiring stories.
Join Keith as he explores the core principles that drive successful fundraising and uncovers the latest strategies to make your job easier, more enjoyable, and incredibly impactful. From relationship-building and storytelling to leveraging the newest tech, "Let's Talk Fundraising" is here to help you transform your approach and achieve remarkable results for your organization.
Subscribe now and be part of a community dedicated to elevating the art and science of fundraising. Together, we'll make a bigger impact, one episode at a time.
Let's Talk Fundraising
Why Accuracy Is the Hidden Superpower of Stewardship
Every fundraiser faces the same dilemma: we need efficiency, but we can't sacrifice accuracy. When that major donor asks for one critical data point before finalizing their six-figure gift, the pressure to respond quickly meets our professional obligation to be absolutely correct.
ChatGPT makes this balancing act even trickier. Its confident, polished responses can mask a dangerous problem: AI hallucinations—fabricated information delivered with complete assurance. These aren't intentional lies but rather the model filling knowledge gaps with what sounds plausible. The danger comes when these fabrications slip into donor communications, undermining the trust foundation that every successful fundraising relationship requires.
This episode introduces a powerful principle: accuracy is stewardship. When donors receive information from your organization, they're not just reading facts; they're making judgments about your credibility. Even small inaccuracies can create cracks in the foundation of trust, and in fundraising, these cracks directly impact your ability to secure and retain support for your mission.
The good news? A simple five-word prompt can dramatically reduce this risk: "Cite sources for every claim." By implementing the "source-then-write loop" workflow, you can transform how you use AI—requesting verification before content creation rather than after. This approach doesn't just protect against errors; it lets you leverage AI's efficiency while maintaining complete confidence in what you send.
Whether you're writing donor updates, impact reports, or quick responses to board inquiries, this verification-first approach ensures you never sacrifice integrity for speed. Because in fundraising, trust isn't just nice to have—it's everything. Join us to discover how the most successful fundraisers are using AI to enhance relationships rather than potentially damage them.
💡 Want to take the next small step?
→ Free Download: 12 Fundraising Prompts You'll Actually Use
→ Course: The Fundraiser's AI Starter Suite
A major donor emails she's ready to move forward with a six-figure gift, but asks for one last data point before wiring the funds. You type the question into chat, gpt, hit, enter and wait. A polished answer appears in seconds. But then it hits you when did that number come from? You scan the response again no source, no citation, just AI's confidence. But now your confidence is rattled because here's the thing Send a made-up stat and the damage doesn't stay on your screen. It follows you into donor conversations, into credibility calls, into missed renewals. But with one five-word prompt you could have surfaced the source and safeguarded the trust you've worked so hard to build. So let's talk fundraising.
Keith Greer, CFRE:There's a golden rule in fundraising that often gets less airtime than it should. Accuracy is stewardship. We talk a lot about relationships, emotion, storytelling, and rightly so. But the foundation underneath all that warmth and connection is trust, and trust hinges on credibility. When a donor receives a message from your organization, whether it's an impact report, a campaign update or a one-line email with a statistic, they're not just reading facts, they're making decisions about whether they believe you, whether they believe in you. And when the details in that message are even slightly off, even if the mistake is unintentional, the donor's belief wobbles. That wobble might not make a sound, but it does leave a mark. This is especially true when it comes to numbers. Donors love stories, but they also crave evidence. They want to know the gift made a difference. They want to feel the transformation, yes, but they also want to see the proof. So when they ask for a data point, something specific and verifiable, they're handing you an opportunity to reinforce trust. And the moment that data point is inaccurate or fabricated, even if it's well-written or well-meaning, that opportunity can vanish. So here's the challenge that makes this even more pressing.
Keith Greer, CFRE:Today, Tools like ChatGPT are confident communicators. They're designed to sound fluent, polished and persuasive, but they're also prediction engines, not search engines. That means they're pulling from patterns and probabilities, not always from hard verifiable facts. And when that nuance goes unacknowledged, it opens the door for something we call hallucinations, confidently delivered falsehoods. Let's be clear Hallucinations aren't intentional deception. They're not lies in the way a person might lie. They're simply the model filling in gaps with its best guess. The trouble is that guess can sound so smooth and so authoritative we forget to question it.
Keith Greer, CFRE:You've probably seen this yourself. Maybe you asked ChatGPT to summarize a research study. It named a journal that sounded familiar but didn't actually exist. Or maybe you asked for the history of a donor program and it gave you a beautifully written paragraph, none of which matched your records. These aren't rare glitches. They're built into how large language models operate. This is why the principle matters so much. Language models operate. This is why the principle matters so much.
Keith Greer, CFRE:If stewardship is about honoring your donor's trust, then verifying your facts, especially AI-generated ones, isn't optional. It's part of the job, and the gap between that sounds right and that is right can be enormous. But here's what's most encouraging Most errors don't happen because fundraisers are careless. They happen because we're moving fast. We're under pressure. There's an email to send a proposal to finalize, a board member waiting for a statistic and in the flurry of activity, we assume the information is sound, especially when it looks polished.
Keith Greer, CFRE:This is where a simple practice can change everything. Imagine if, before asking ChatGPT to write your next donor message, you took a beat and ran one short check, cite sources for every claim, five words, that's it. Suddenly, the model shifts from just drafting content to backing it up, and if it can't, that's your cue to pause, check and revise before anything goes live. So let's be honest. You probably already fact-checked your own work, but AI output can feel deceptively done, which makes skipping the step even more tempting, and that's why building the check into your prompt up front is so powerful. It prevents you from being lulled into false confidence by a well-written hallucination.
Keith Greer, CFRE:There's also a deeper truth here worth naming. When a donor receives information that isn't accurate, it doesn't matter whether the mistake came from a rushed human or an overconfident AI. To them it feels the same and the risk to the relationship is the same. Think about your own recent work when the last time you sent a message with a number or a fact that you assumed was correct but didn't double check. Maybe it was a stat from a past report, maybe it was a program outcome you remembered from last year. Nothing sinister, just a quick assumption. Most of us have done it and most of the time it goes unnoticed. But that, most of the time, is exactly the issue, because it only takes one time for a donor to notice and once that trust is questioned, it's incredibly hard to rebuild. In a profession where trust is the foundation of every major gift, every renewal, every legacy commitment, that's not a gamble worth taking.
Keith Greer, CFRE:The beauty of a proactive approach is that it doesn't require you to become a fact-checking machine or a data analyst. It simply invites you to lead with curiosity, to build a culture of asking where did this come from? That single question can save relationships and, even better, it can model for your team, your interns, your colleagues that accuracy isn't about perfectionism, it's about care, because when you care enough to check, your donors feel it and that kind of trust isn't just preserved, it's deepened. So here's the fundraising principle we're standing on today. Accuracy is stewardship, and AI is only as accurate as the prompts and follow-up questions that you give it. When you bring that mindset into your writing process, everything shifts. Your messages get sharper, your stats get cleaner, your confidence gets stronger and, most importantly, your donors stay rooted in trust.
Keith Greer, CFRE:Take 10 seconds now. Think about the last stat or data point you included in a donor communication. Did you verify the source? Did you cross-check it or did it just sound right? No shame here, just awareness. And with awareness comes the opportunity to lead with integrity, even when you're working fast. In a moment we'll break down exactly how to build this verification into your chat GPT workflow, but for now, remember this Stewardship isn't just about stories and smiles, it's also about precision, and, in the age of AI, the fundraisers who pair speed with accuracy will be the ones who earn and keep the deepest donor trust.
Keith Greer, CFRE:Let's turn now from principle to practice. You know that accuracy is non-negotiable and that AI, powerful as it is, doesn't guarantee truth. But here's the good news With the right workflow, chatgpt can actually make your fact-checking faster, more structured and less stressful. The key is what I call the source-then-write loop. It's a two-step process that flips the usual sequence fundraisers follow when using AI.
Keith Greer, CFRE:Instead of asking ChatGPT to write the whole paragraph and then hoping it got the details right, you start by asking for the sources first. Here's how it works Before drafting anything, you prompt ChatGPT like this Cite sources for every claim. That's the five-word safety check. It's simple, but it's powerful. By asking for sources up front, you signal that you're not just looking for smooth sentences. By asking for sources up front, you signal that you're not just looking for smooth sentences, you're looking for verifiable facts. You're not delegating judgment, you're guiding it.
Keith Greer, CFRE:So let's say you're preparing a donor update about a $25,000 endowed gift that supported underrepresented engineering students last year. Normally you might say chat GPT write a 150-word impact paragraph thanking the donor and describing how their gift made a difference. But in the source, then write loop. Your prompt would sound more like this Before writing, list three verifiable sources that prove how last year's $25,000 endowed gift supported underrepresented engineering students. Cite program statistics from the attached files or my organization's website. After I confirm them, draft a 150-word impact paragraph in a warm, donor-centric tone. In response, chatgpt might list a program report from your own organization's website, a press release or a blog post featuring a student spotlight, a funding update published in last year's annual report. Then, and only then, do you move forward to the writing step. Once you've confirmed that the sources are real, accurate and appropriately cited, you invite ChatGPT to create the donor message.
Keith Greer, CFRE:This workflow has a few big advantages. First, it prevents you from relying on confident sounding guesses. When you ask for sources first, you're much more likely to notice if something feels fishy or vague. You won't be seduced by smooth language. You'll be focused on truth. Second, it saves time, and that might sound counterintuitive. Doesn't adding a step make things slower? Not really, because it's much faster to validate three sources before you write than to rewrite a message after realizing something's wrong. In most cases, you'll shave off revision cycles, clarification emails and back and forth with colleagues. Third, it builds muscle memory. After a few repetitions, this process becomes second nature. You start spotting red flags faster, you trust your draft more fully and, best of all, you start sending AI-assisted content with real confidence, not quiet anxiety. Now let's talk about the second part of this process, the one-click reference audit.
Keith Greer, CFRE:After ChatGPT gives you its sources, usually as URLs or citations, take a minute to verify them. Paste the links into your browser. See if they actually lead to the source that's described. If one fails, don't panic. Just flag the sentence and either adjust it or find a replacement. This isn't about being perfect. It's about protecting your credibility. You don't need to become a full-time fact checker. You just need to stay in the driver's seat One of the simplest ways to spot trouble. Watch out for citations that sound almost right but don't quite exist. If a URL looks plausible but doesn't lead anywhere, that's your cue to dig deeper. If ChatGPT references a stat but can't tell you where it came from, treat it like a placeholder until you can confirm it.
Keith Greer, CFRE:Here's another real-world tip. If you're pulling from your own organization's materials, like annual reports, campaign updates or board decks, drop those into your ChatGPT prompt as part of the source list. That way, the model has grounded content to draw from and is less likely to hallucinate. You're narrowing the focus, giving it guardrails and dramatically increasing the odds of a clean and accurate draft. So let's recap the practical prompts that power this approach. First, source first prompt Before writing list three verifiable sources that show impact statement and include URLs. Second, after you verify, now write a 150-word donor update based on the verified sources above. Keep it warm, professional and specific, avoid generalities. This structure works beautifully for a wide range of communications, whether that's donor updates, a grant report, board briefings, maybe a fundraising appeal or even year-end recaps. And the best part Once you've confirmed the sources, once you can often reuse the language across multiple messages or segments with small tweaks instead of the full rewrites, you don't just save time, you reduce the cognitive load, you stop wondering is this right?
Keith Greer, CFRE:And you start knowing yes, it's sound, it's supported and it's safe to send. And when you're writing under pressure which, let's be honest, is most of the time having that confidence is priceless. So as you move into your next donor message, pause for a second. Ask yourself am I trusting the output because it looks good or because I know it's grounded. If it's the first, take the extra step, because accuracy isn't a bonus, it's the baseline. And when you pair that commitment with a tool like ChatGPT, you don't just write well, you lead well, you fundraise with integrity and your donors feel the difference.
Keith Greer, CFRE:Let's take a breath here, because this section isn't about prompts or protocols. It's about you and what might be running through your mind even after learning the source. Then write loop. You might be thinking this all makes sense. I see the value, but doesn't verifying AI output just cancel out the time I was trying to save in the first place? And that question is honest and it deserves an honest answer. Yes, adding a verification step means spending another 60 to 90 seconds checking links or confirming a statistic. But let's zoom out.
Keith Greer, CFRE:What's the real cost of skipping that check? If a donor catches a factual error in your message, especially one tied to their gift or program area, you don't just lose face, you lose trust, you lose the sense of reliability they felt when they handed you that check or they wired those funds. And rebuilding that trust that doesn't take 60 seconds. That takes weeks, months, maybe even years. And it's rarely just one donor the moment. A stat is wrong in a board report or a fabricated ranking slips into an appeal, the ripple effect begins. Donor, trust is relational, it's not transactional. The word spreads, even subtly. They're not buttoned up. That number didn't check out, that wasn't accurate. Those are dangerous impressions to leave behind. So if you're wondering whether a quick fact check slows you down, I'd offer this it's not a slowdown, it's a safeguard, it's speed that lasts, because the fastest route to credibility is consistency, and that comes from details that hold up.
Keith Greer, CFRE:Here's another shift that's often necessary. Many fundraisers, especially high-capacity performers, see revisions or fact-checking as a rework, as something to be minimized. And if you're using ChatGPT, there's a temptation to see its fluency as final. The writing sounds so good, so fast, that editing feels optional. But let's reframe that. The goal isn't to cut editing, it's to edit smarter, to bring discernment back to the surface, instead of letting the tool lull you into copy-paste confidence. When you ask for the sourc list first or run a link audit, you're not adding steps, you're taking back control.
Keith Greer, CFRE:This is especially important for those of you who are trusted as the voice of your shop. You're the one who drafts the messages, the one leadership counts on to get the language right. Your tone is your brand and your accuracy is your integrity. That responsibility can feel heavy, but it also gives you power the power to model what thoughtful, ethical AI use looks like in the real world. When you're the person who both embraces the efficiency and protects the truth, you set the tone for everyone else. Your team learns that it's possible to be fast and right at the same time, that quality and speed aren't opposites, they're partners. You also may be thinking, keith, do I really have the time to train my whole team in this? If you're stretched, I hear that, but here's the shift. You don't need to become the AI gatekeeper. You need to become the culture setter.
Keith Greer, CFRE:If you build these habits into your prompts, your workflows, your templates, and share that with your teams, others will follow your lead. You can even start with something as small as a shared checklist. Add placeholders for any sensitive data, ask for sources before writing, Confirm every citation, customize tone after verifying content. That's it. That's your culture of accuracy built into behavior. And as this mindset starts to sink in, you'll notice something unexpected your confidence grows. You're no longer wondering if that paragraph you copied from ChatGPT will hold up under scrutiny. You know it will, because you guided it, you checked it and you owned it. That's the real reward of this mindset shift.
Keith Greer, CFRE:It's not just about reducing errors or preventing embarrassment. It's about showing up with clarity and confidence. It's about knowing that every message you send reflects your integrity, not just your productivity. So pause and ask yourself what would change if I trusted myself more than I trusted the tool. What would shift if accuracy wasn't just a back-end correction but a front-end filter for everything I write. Let that land, because when you're rooted in stewardship of time, of truth, of trust, you write differently, you lead differently and your donors feel the difference.
Keith Greer, CFRE:So today we tackled one of the most important questions in AI-assisted fundraising Can I trust the output? We explored why large language models like ChatGPT sometimes hallucinate, how those errors happen and why trust with donors depends on your ability to separate confident-sounding fiction from verifiable fact. We covered the source-then-write loop, a simple, repeatable workflow that asks for citations before drafting copy, and the five-word safety check Cite sources for every claim. These aren't just techniques. They're habits that protect the integrity of your message, your brand and your donor relationships. And we talked mindset. Accuracy isn't the enemy of speed. It's what gives speed real staying power. When you verify before you write, you send messages with confidence instead of crossing your fingers.
Keith Greer, CFRE:Now, if this episode helped you feel more confident about using ChatGPT in your donor communications, there's one small thing you can do that makes a big difference. Would you please leave a rating or review? Wherever you listen, it helps more fundraisers discover the show and join you in building donor trust with intention and integrity. Next week, we'll start exploring workflow wins and time savers. We'll start with the inbox how to train ChatGPT to reply to routine donor emails and give you back your time. Until then, stay curious, stay clear and keep fundraising with heart. I'll see you real soon.
