Drafting a needs statement from your own community data
The statement of need is where most proposals stall — you have the census figures, intake numbers, and community survey results, but turning them into a tight narrative takes a full afternoon per proposal. Drafting is the single most common AI use among grant professionals (46% in Instrumentl's survey), and it works precisely because you supply the evidence and the AI supplies the first arrangement of it.
You are a grant writer's drafting assistant for {{organization_name}}, a nonprofit. Draft the statement of need for a grant proposal. Program context: {{program_summary}} Community data and evidence (the ONLY facts you may use): {{community_data}} Funder priorities to align with: {{funder_priorities}} Output format: - A statement of need of no more than 400 words, in plain, specific language. - Open with the problem in concrete local terms, not a global statistic. - Weave in the data points I provided, keeping every number exactly as written. - Close with why this organization is positioned to address the need. Rules: - Use only the facts, numbers, and sources I provided. Do not add statistics, research findings, or citations from your own knowledge — where stronger evidence would help, insert [DATA NEEDED: describe what to find] instead. - No filler phrases like "in today's rapidly evolving landscape" and no exaggerated urgency. - Write in our voice: direct, factual, community-focused. - After the draft, list any claims that still need a citation before submission.
Fill in your details and the prompt updates live — then copy.
In Eastport, more than a third of eighth graders — 38%, per the 2025 state assessment — read below grade level, and the students who need help most have the least access to it. The district's counselor ratio stands at 1:480, leaving little capacity for individualized academic support. Families have noticed: Harbor Youth Alliance's tutoring waitlist grew from 25 students to 61 in just two years, based on our intake records. [DATA NEEDED: neighborhood median income or free/reduced lunch rate to establish economic context] Claims still needing citations before submission: none — all figures trace to the sources provided above.
The full workflow
- Pull your strongest local data points and note the source for each before you open the AI tool
- Paste the funder's own priority language from their guidelines, not your paraphrase
- Run the prompt, then fill every [DATA NEEDED] flag with a real, citable figure
- Read the draft aloud and rewrite anything that doesn't sound like your organization
- Verify each number against its source one last time before it goes in the proposal
Watch out for
AI invents plausible statistics and citations. Every number in a needs statement must trace to a real source you can hand the funder — presenting fabricated evidence violates the accuracy and honesty requirements in the Grant Professionals Association Code of Ethics.
Never paste beneficiary names, case notes, or client-level records into consumer AI tools. NSF's own guidance warns that non-public information disclosed to public generative AI tools cannot be protected from being recorded and shared.
If the proposal is going to NIH, remember its policy: applications substantially developed by AI will not be reviewed as of September 25, 2025. AI can help arrange your evidence — the ideas and substance must be yours.
Where this comes from
Every use case on this site is grounded in real reports from working grant writers — not invented by us.