AI prompts for nonprofits and charities

Help me write a section of a grant application.

FUNDER AND FUND: [NAME AND WHAT THEY FUND]
THE SECTION AND ITS WORD LIMIT: [e.g. "Need for the project, 400 words"]
FUNDER'S CRITERIA FOR THIS SECTION: [PASTE GUIDANCE]
OUR ORGANISATION: [WHO WE ARE, TRACK RECORD]
THE PROJECT: [WHAT, WHO BENEFITS, HOW, BUDGET]
EVIDENCE WE HAVE: [DATA, SURVEYS, CASE STUDIES, REFERENCES - only real]

Write the section so that it:
- Answers the funder's criteria directly, in the order they list them
- Uses our evidence with sources; marks gaps as [EVIDENCE NEEDED: ...]
- Describes outcomes that are specific and measurable
- Stays within the word limit (state the word count)

Then give me a checklist scoring the draft against each funder criterion (met / partly / missing).

Write a case study.

CUSTOMER: [WHO THEY ARE - INDUSTRY, SIZE]
THEIR SITUATION BEFORE: [THE PROBLEM, WITH SPECIFICS]
WHAT THEY TRIED FIRST: [IF ANYTHING]
WHAT WE DID: [THE SOLUTION]
RESULTS: [NUMBERS, WITH TIMEFRAMES]
QUOTES AVAILABLE: [PASTE ANY]
WHAT WAS HARD ABOUT IT: [HONESTLY]
AUDIENCE FOR THIS CASE STUDY: [WHO WE WANT TO PERSUADE]

Structure:
1. THE RESULT - lead with the outcome and the number. Not 'Company X was founded in 1998'.
2. WHO THEY ARE - two sentences, enough for the reader to recognise themselves.
3. THE PROBLEM - specific and concrete. What was actually happening day to day, what it cost, what they had tried.
4. WHY IT WAS HARD - the constraints, the failed attempts, what made this non-trivial. A problem that sounds easy makes the solution sound unimpressive.
5. WHAT WE DID - the actual approach, with enough detail that a similar reader could judge whether it applies to them. Include what did not work.
6. THE RESULTS - with timeframes and the measurement method. 'Response time improved 40% within three months, measured by X.'
7. WHAT THEY SAY - real quotes. Use the awkward, specific ones over the polished ones.
8. WHO THIS APPLIES TO - and honestly, who it would not.

Rules:
- Never a percentage without a baseline. '300% increase' from what?
- State the measurement period and method for every number
- Include at least one honest difficulty. Case studies with no friction read as fiction and are discounted entirely.
- No superlatives, no 'game-changing', no 'seamless'
- Do not invent quotes. Use only what I gave you, marked [NEED QUOTE] otherwise.
- If my results are thin, say so rather than inflating them

Write a newsletter issue.

NEWSLETTER: [WHAT IT IS ABOUT, WHO SUBSCRIBES]
ISSUE TOPIC: [THIS WEEK'S SUBJECT]
WHAT I WANT TO SAY: [MY NOTES OR ARGUMENT]
LENGTH: [WORDS]
MY VOICE: [PASTE A PREVIOUS ISSUE, or describe]
WHAT I AM PROMOTING, IF ANYTHING: [PRODUCT/EVENT/POST, or 'nothing']

Structure:

1. SUBJECT LINE - five options. Specific, under 50 characters, no clickbait, no emoji unless my voice sample uses them. Never 'Newsletter #47'.
2. PREVIEW TEXT - the line after the subject in the inbox. It must add to the subject, not repeat it. Most newsletters waste this entirely.
3. THE OPENING - straight into the idea. No 'hope you had a great week', no weather, no apology for the gap since the last issue.
4. THE BODY - one idea, developed. Not five links with a sentence each.
5. THE PRACTICAL PART - something the reader can use this week.
6. THE CLOSE - one call to action if there is one. Never three.

Rules:
- Write to one person, not a list. 'You', not 'everyone'.
- One idea per issue. A newsletter covering four topics is remembered for none.
- If I am promoting something, it goes after the value, clearly marked, once, without a fake segue.
- No 'in this issue' contents list for anything under 1,000 words.
- Do not manufacture a personal anecdote. If my notes have one, use it; if not, do not invent one.

Then: the one sentence a reader would forward, and whether the issue delivers on the subject line.

Write a promotional email.

WHAT I AM SELLING: [PRODUCT/SERVICE AND PRICE]
TO WHOM: [SEGMENT - what they know about you already]
WHY IT HELPS THEM: [THE GENUINE BENEFIT]
WHY NOW: [THE REAL REASON FOR THIS EMAIL - launch, restock, season, or 'no particular reason']
OFFER: [DISCOUNT, BONUS, or 'none']
OBJECTIONS: [WHY THEY WOULD NOT BUY]
MY RELATIONSHIP WITH THIS LIST: [how often you email, how much you have sold to them before]

Structure:
1. OPEN with the reader's situation, not your announcement. One or two sentences.
2. THE THING - what it is and what it does for them, plainly.
3. WHO IT IS FOR AND NOT FOR - naming who should not buy makes everything else credible and reduces refunds.
4. THE MAIN OBJECTION - handled directly in the body, not in a PS.
5. PROOF - specific. A result with a number, a named customer, a guarantee.
6. PRICE - state it. Making people click to find the price costs more conversions than the price does.
7. ONE CALL TO ACTION - repeated at most twice, as the same action.
8. THE PS - one line, restating the single most important point. It is the second most-read part of an email.

Rules:
- Under 300 words
- If there is no real reason for this email beyond wanting sales, say so honestly in the brief rather than manufacturing urgency
- No countdown timers on offers that are not ending
- No 'last chance' unless it is
- No fake stock scarcity
- One offer. Two offers halve the response to both.
- No 'Hi [FIRST NAME], hope you're well'

Then:
- THE UNSUBSCRIBE RISK - how likely this email is to lose subscribers, given my stated relationship with this list
- THE HONEST CHECK - given how often I email and sell, is this email earned? If I have been selling constantly, say so.

Write a policy.

WHAT IT COVERS: [THE SUBJECT]
WHY IT IS NEEDED: [THE PROBLEM IT SOLVES]
WHO IT APPLIES TO: [SCOPE]
THE ACTUAL RULE: [WHAT PEOPLE MUST OR MUST NOT DO]
EXCEPTIONS: [IF ANY, AND WHO APPROVES THEM]
CONSEQUENCES: [WHAT HAPPENS IF NOT FOLLOWED]
WHO OWNS IT: [ROLE]

Structure:
1. PURPOSE - one sentence. Why this exists.
2. SCOPE - who and what it applies to, and explicitly who it does not.
3. DEFINITIONS - only terms whose meaning is genuinely disputable in this context. Do not define ordinary words.
4. THE POLICY - the rules themselves, numbered, each one thing. Use 'must', 'must not', and 'may' precisely, and say at the top what each means.
5. PROCEDURE - how to comply, step by step, for each common situation.
6. EXCEPTIONS - when the rule does not apply, and the named role who approves a deviation.
7. EDGE CASES - a table of 6-10 specific situations people will ask about: Situation | Does the policy apply? | What to do. This is the section that prevents the same question being asked forty times.
8. IF SOMETHING GOES WRONG - who to tell, how fast.
9. OWNERSHIP AND REVIEW - who owns it, when it is reviewed next.

Rules:
- Every rule must be testable. 'Use good judgement' is not a policy.
- Avoid 'should' - it means neither must nor may and produces inconsistent application
- No rule without a procedure for following it
- Write for the person trying to comply, not for the lawyer
- Where I have not given enough to write a section, write [DECISION NEEDED: the question]

Then: THE THREE QUESTIONS people will ask that this does not answer.

Analyse these open-text responses.

RESPONSES:
"""
[PASTE]
"""

THE QUESTION THEY WERE ANSWERING: [EXACT WORDING]
WHO ANSWERED: [RESPONDENT DESCRIPTION AND HOW THEY WERE RECRUITED]
RESPONSE COUNT: [TOTAL, AND OUT OF HOW MANY ASKED]
WHAT I WANT TO LEARN: [PURPOSE]

Produce:

1. THE RESPONSE RATE CAVEAT - who answered the open question versus who was asked. People with strong feelings answer free-text questions; the silent majority is missing. State what this sample can support.

2. THE THEMES - with counts and the percentage of responses. For each: the theme, how many mentioned it, two or three representative verbatim quotes, and the range of intensity within it.

3. THE CODING FRAME - how you grouped responses, stated explicitly so I can check the judgement. Flag any response that could reasonably have gone in two themes.

4. FREQUENCY VERSUS INTENSITY - separate these. A theme mentioned by five people with great force is different from one mentioned in passing by forty. Both matter and they are different findings.

5. THE QUESTION WORDING EFFECT - assess whether the exact question wording steered the answers. If it asked 'what could be improved', you will get complaints regardless of overall satisfaction, and those complaints are not a satisfaction measure.

6. THE UNPROMPTED - things mentioned that the question did not ask about. These carry more weight than answers to the question, because nobody was steered toward them.

7. WHAT NOBODY SAID that you would expect. Note it, carefully, as an observation.

8. THE OUTLIERS - individual responses that are unusual and worth reading in full. Sometimes one person articulates something the themes flatten. Quote them.

9. THE LANGUAGE - the words respondents use for the thing you are asking about. Useful for future surveys, for marketing and for search.

10. THE FINDINGS ranked by confidence, with what each rests on.

Do not report a theme as a finding on the basis of two responses. State counts everywhere.

Turn this feedback into a priority list.

FEEDBACK:
"""
[PASTE - SURVEY RESPONSES, REVIEWS, SUPPORT TICKETS, OR ALL OF THEM, LABELLED BY SOURCE]
"""

WHAT I PROVIDE: [CONTEXT]
MY RESOURCES: [WHAT YOU CAN REALISTICALLY CHANGE]
WHO GAVE THIS FEEDBACK: [AND HOW THEY WERE SELECTED]

Produce:

1. THE SOURCE BIAS - each feedback source over-represents someone. Reviews come from the extremes, support tickets from people with problems, surveys from responders. Say what this combined set over- and under-represents.

2. THE THEMES - with counts by source. A theme appearing across several sources is stronger evidence than one concentrated in a single channel.

3. THE CLASSIFICATION - each theme as one of:
   - REAL PROBLEM: something is broken or missing
   - EXPECTATION PROBLEM: it works as designed and was described badly. Usually the cheapest to fix.
   - WRONG CUSTOMER: people who should never have bought or signed up. A targeting problem.
   - PREFERENCE: someone wants it different, not broken. Changing may make it worse for others.

4. THE VOCAL MINORITY CHECK - for each theme, how many people, out of how many total. One articulate person can make a preference sound like a crisis. State counts everywhere.

5. THE SILENT MAJORITY - for each theme, who is affected but did not write in. Usually a multiple of those who did. Note where the true impact is likely much larger than the feedback volume suggests, and where it is not.

6. THE PRIORITY MATRIX - each theme scored on: how many are affected, how badly, whether it causes them to leave, and effort to fix. Rank by (impact / effort).

7. THE QUICK WINS - expectation problems and documentation gaps, which cost little and remove real friction.

8. WHAT NOT TO CHANGE - requests that would damage the offering for your main audience, come from people outside your target, or would take resources from something that matters more. Name them explicitly, because the loudest requests are frequently in this category.

9. WHAT TO INVESTIGATE - themes where the feedback signals a problem but not its cause.

10. WHAT TO TELL THE PEOPLE who gave feedback, including on the things you will not do.

Write a weekly update.

AUDIENCE: [WHO READS IT AND WHAT THEY DECIDE]
PERIOD: [DATES]
MY RAW NOTES: [PASTE EVERYTHING FROM THE WEEK]
KEY NUMBERS: [METRICS AND VALUES, WITH LAST WEEK'S IF YOU HAVE THEM]
WHAT I NEED FROM THE READER: [DECISION / AWARENESS / HELP]

Structure:

**Headline** - one sentence, the single most important thing that changed this week. If nothing changed, say that.

**Numbers** - a compact table: Metric | This week | Last week | Change | Comment (only where the change needs explaining).

**Shipped** - what actually completed. Not what was worked on.

**Risks** - only things that are newly risky or have got worse. Each with: what it threatens, and what would resolve it.

**Decisions needed** - a numbered list. Each with: the question, the options, my recommendation, and the deadline. If none, write 'None this week.'

**Next week** - three lines maximum.

Rules:
- Under 400 words total
- No progress-as-narrative. 'Continued working on X' is banned.
- Never carry a risk forward unchanged without noting how many weeks it has been open
- If a number moved and I have not explained why, write [UNEXPLAINED] next to it rather than guessing

Write an announcement.

WHAT IS CHANGING: [THE CHANGE]
WHO IT AFFECTS AND HOW: [IMPACT BY GROUP]
WHEN: [DATE AND ANY PHASES]
WHY: [THE REAL REASON]
WHAT PEOPLE NEED TO DO: [ACTION REQUIRED, BY GROUP]
WHAT WILL WORRY THEM: [ANTICIPATED CONCERNS]
AUDIENCE: [customers / staff / users / community]
CHANNEL: [email / in-app / blog post / all-hands]

Write it so that:
1. The first sentence states what is changing and when. Not background, not 'we're excited to share'.
2. The second paragraph says who is affected and what they must do. If different groups are affected differently, use a table or clear headings - never make someone work out whether this applies to them.
3. The reason comes next, honestly and briefly. If the reason is commercial, say so; transparent commercial reasoning is better received than a wellbeing framing nobody believes.
4. The concerns from my list are addressed directly, including the ones with unwelcome answers.
5. What is NOT changing is stated. Announcements cause disproportionate anxiety because people assume more changed than did.
6. There is a named route for questions.

Rules:
- No 'we're excited to announce' for something people will not be excited about
- No 'this will allow us to serve you better' unless you can say specifically how
- Do not bury a price increase, a removal, or a downgrade below good news
- If something is being taken away, say so in plain words in the first paragraph
- Give dates, not 'in the coming weeks'

Then give me:
- THE SENTENCE PEOPLE WILL QUOTE ANGRILY, and whether it can be honestly improved or is just the truth
- THE FAQ - the six questions you will be asked, with honest answers
- WHAT I AM NOT SAYING that people will notice is missing

Build a social media content plan.

PLATFORMS: [WHERE YOU POST]
WHAT MY BUSINESS DOES: [CONTEXT]
AUDIENCE: [WHO AND WHAT THEY WANT]
TIME AVAILABLE PER WEEK: [HOURS]
WHAT I ALREADY PRODUCE: [BLOG POSTS, PROJECTS, CUSTOMER WORK, ANYTHING]
GOAL: [awareness / leads / community / recruitment]
WHY PREVIOUS ATTEMPTS FAILED: [IF APPLICABLE]

Produce:

1. FREQUENCY REALITY CHECK - given my hours, what cadence can I sustain for a year? Be conservative. Most social plans fail in week five from over-commitment, not from bad content. Recommend fewer posts than I want.

2. PLATFORM CHOICE - should I be on all the platforms I listed? Concentrating on one platform properly beats being mediocre on four. Say which to drop.

3. CONTENT PILLARS - 3-4 recurring themes, derived from my business and audience. Each with: what it covers, why the audience cares, and roughly what proportion of posts.

4. REPEATABLE FORMATS - the actual point of a content plan. 5-6 post formats I can refill indefinitely without inventing a new idea each time. For example: a question customers ask, something that went wrong and what changed, a short breakdown of a piece of work, a contrarian take on a common practice, a useful thing found elsewhere with commentary.
   For each: the structure, roughly how long it takes to make, and where the raw material comes from.

5. THE SOURCE PIPELINE - where content comes from in my existing work. A plan requiring separate content creation is a plan that stops. Describe the capture habit.

6. THE CALENDAR - four weeks, mapped to formats and pillars, with specific topics for week one.

7. THE BATCHING PLAN - how to produce a week's posts in one session.

8. WHAT TO CUT from my ambitions - anything that costs more than it returns: daily posting, video if I have no capacity, being on every platform, or designed graphics.

9. THE MEASUREMENT - what actually indicates this is working for my stated goal. Followers usually is not.

Build a structured onboarding checklist.

ROLE: [JOB TITLE]
REPORTS TO: [MANAGER ROLE]
KEY RESPONSIBILITIES: [PASTE FROM JOB DESCRIPTION]
SYSTEMS THEY WILL USE: [LIST TOOLS/SOFTWARE]
EXISTING DOCUMENTATION: [LIST SOP NAMES, OR 'none']

Produce a checklist across four phases: Before day one, Week one, Weeks 2-4, Days 31-90.

For each phase give a table: Task | Owner (new hire / manager / IT / other) | Done when (an observable, checkable condition) | Depends on.

Rules:
- 'Done when' must be observable. 'Understands the CRM' is wrong; 'Has independently logged one new lead in the CRM' is right.
- Every system in the list needs an access-request task in 'Before day one', owned by someone other than the new hire.
- Include at least two tasks where the new hire produces something reviewable, not just consumes information.
- Flag with [DOC GAP] any task that needs documentation you said does not exist.

Help me write an AI use policy.

THE ORGANISATION: [SIZE, SECTOR, WHAT IT DOES]
WHO IT APPLIES TO: [everyone / specific teams]
WHAT PEOPLE ARE ALREADY DOING: [CURRENT USE, INCLUDING UNOFFICIAL]
WHAT WE ARE WORRIED ABOUT: [YOUR CONCERNS]
WHAT TOOLS ARE APPROVED: [IF ANY]
REGULATORY CONTEXT: [ANY SECTOR REQUIREMENTS]

Produce:

1. THE REALISTIC STARTING POINT - people are already using these tools, including where there is no policy. A policy that prohibits everything drives use underground, where there is no oversight at all and no way to know what data has gone where. Design for the actual situation.

2. THE STRUCTURE - a usable policy covers:
   - What tools are approved, and how to request one
   - What data may and may not be entered, which is the most important section
   - Where output may be used and where it may not
   - What must be disclosed and to whom
   - Who is accountable for output
   - What to do when unsure

3. THE DATA SECTION - the highest-risk area and the one to write most carefully. What may never be entered: credentials, customer personal data unless the tool is approved for it, confidential information covered by contracts, and anything regulated in my sector. Be specific rather than general, because a general rule is interpreted variously.

4. THE APPROVED TOOLS - why the distinction matters: consumer and enterprise tiers differ on data retention, training use and processing location. Say what to check before approving a tool and what the approval should record.

5. THE OUTPUT ACCOUNTABILITY PRINCIPLE - the central rule. The person who uses AI-assisted output is accountable for it as if they had produced it themselves. This is clearer than trying to enumerate every acceptable use and it is the rule that actually works.

6. THE VERIFICATION REQUIREMENT - what must be checked before output is used: facts, figures, citations, code, and anything a person will rely on. Say what level of checking different kinds of work require.

7. THE HIGH-CAUTION LIST - where AI-assisted output must not be the basis of a decision without qualified review: decisions about individuals, anything with legal or regulatory weight, safety-related material, and anything going to a customer as authoritative.

8. THE DISCLOSURE RULES - when to say AI was involved: to customers, in submitted work, in creative or editorial contexts, and internally. Different contexts have different expectations and the policy should say which.

9. WHAT NOT TO INCLUDE - rules that cannot be enforced, technology-specific detail that dates immediately, and a prohibition on tools people will use anyway.

10. THE PRACTICAL SUPPORT - a policy alone changes little. What helps: an approved tool that is actually good enough, examples of acceptable and unacceptable use, and a named person to ask.

11. THE REVIEW - this area changes quickly. Set a review interval and name an owner.

12. THE ONE-PAGE VERSION - what people will actually read.

Requirements vary by sector and jurisdiction. Anything with regulatory implications needs legal and compliance input.