# Logic Model Builder

Builds a logic model covering inputs, activities, outputs, short-term outcomes, and long-term outcomes from your program facts. Use it when you need to submit a logic model as a proposal attachment or when your narrative needs the logic model to be written out before drafting begins.

## Prompt

## Context
You are helping a grant writer at [ORGANIZATION NAME] build a logic model for [PROGRAM NAME]. The proposal is for [FUNDER NAME]. A logic model connects what goes in (inputs) to what is done (activities) to what is produced (outputs) to what changes for participants (outcomes). It is a planning and accountability tool, not a marketing document. Every cell must reflect what the program actually does.

## Task
Build a logic model using these inputs:

Program resources:
[PROGRAM RESOURCES]

Program activities:
[PROGRAM ACTIVITIES]

Program reach (who is served and how many):
[PROGRAM REACH]

Known or expected outcomes:
[KNOWN OR EXPECTED OUTCOMES]

Grant period:
[GRANT PERIOD]

Present the logic model in five labeled sections:
1. Inputs: resources that go into the program (staff, funding, volunteers, facilities, equipment, partners)
2. Activities: what the program does (services delivered, trainings held, sessions provided)
3. Outputs: countable products of the activities (number of participants served, sessions held, materials distributed)
4. Short-term outcomes: changes participants experience during or immediately after the program (knowledge gained, skills learned, behaviors adopted)
5. Long-term outcomes: changes expected to persist beyond the program period (improved health, stable employment, reduced recidivism)

After the five sections, add a one-paragraph narrative that explains the causal logic: if these inputs support these activities, these outputs will result, and over time these outcomes should follow.

## Standards
- Present each section as a labeled list, not a paragraph. Keep each item to one line.
- Use only inputs, activities, and outcomes that appear in the program design the writer supplied. Do not add services, partners, or outcomes not present in the inputs.
- Short-term outcomes should be observable within the grant period. Long-term outcomes sit beyond the grant period or represent sustained change.
- Do not inflate outcomes to match funder preferences. If the program cannot plausibly produce a long-term outcome from its activities alone, say so and ask.
- Do not invent partner organizations, staffing, or resources.
- If the program reach or resources are missing, ask before filling them in.

## Variables

- ORGANIZATION NAME
- PROGRAM NAME
- FUNDER NAME
- PROGRAM RESOURCES
- PROGRAM ACTIVITIES
- PROGRAM REACH
- KNOWN OR EXPECTED OUTCOMES
- GRANT PERIOD

## Input checklist

- [ ] A list of program resources: staff positions and FTE, funding sources, volunteer roles, facility, partner organizations
- [ ] A specific list of program activities, not a summary (e.g., "eight-session job readiness workshop" not "job training")
- [ ] Your intended reach: number of participants, frequency of service, duration of participation
- [ ] Known or expected outcomes, separated if possible into what you expect during the grant period versus long-term
- [ ] The funder's RFP or guidelines to confirm whether a specific logic model format is required
- [ ] Remove any beneficiary names or identifying data before pasting, or confirm your AI tool is approved under your organization's data policy

## Verification checklist

- [ ] Verify every input listed is a real resource your program has or will have during the grant period
- [ ] Confirm every activity listed is something your program actually does, not something adjacent or aspirational
- [ ] Check that outputs are countable and based on your actual capacity, not inflated
- [ ] Verify short-term outcomes are achievable within the grant timeline given the activities
- [ ] Confirm long-term outcomes follow logically from short-term outcomes rather than jumping several steps ahead
- [ ] Check that no partner organizations, staff roles, or program features were invented by the AI
- [ ] Verify the causal narrative paragraph does not promise outcomes the program cannot demonstrate

## Sample output

Sample output. Generated by AI from sample inputs:

**Inputs**
- 1.0 FTE Program Director (Riverside Youth Coalition)
- 2.0 FTE Site Coordinators
- 12 part-time tutors (Millbrook Community College students, work-study funded)
- Grant funding: $180,000 requested from Hartfield Foundation
- Existing funding: $45,000 from city contract
- Two school sites: Millbrook Elementary and Jefferson Middle School (space donated by district)
- Second Step social-emotional learning curriculum (licensed)
- Fountas and Pinnell benchmark assessment materials

**Activities**
- Weekly tutoring sessions (Monday through Thursday, 3:00 to 5:30 p.m., school year)
- Monthly tutor training sessions led by Program Director
- Quarterly academic benchmark assessments for all enrolled students
- Weekly social-emotional learning activities using Second Step curriculum
- Monthly family communication (written progress updates)

**Outputs**
- Up to 120 students served across two sites
- 640 total program sessions delivered
- 480 tutor-student contacts per week at full enrollment
- 4 benchmark assessment cycles completed
- 120 quarterly progress reports distributed to families

**Short-term outcomes (within grant period)**
- Students demonstrate measurable improvement in reading benchmark level
- Students demonstrate improved mathematics performance on report card
- Students demonstrate improved social-emotional skills on pre/post assessment
- Students attend at least three sessions per week on average

**Long-term outcomes (beyond grant period)**
- Students advance to the next grade level on time
- Students sustain academic performance gains in subsequent school years
- Students demonstrate school connectedness and reduced dropout risk

**Causal logic:** When a trained tutoring workforce supported by experienced coordinators delivers consistent, structured academic support to students over a full school year, those students gain academic skills and improve their performance on measurable indicators. When social-emotional learning is integrated consistently alongside academic support, students also develop the self-regulation and relationship skills that support continued engagement in school. Over time, students who experience consistent support and measurable skill growth during the middle elementary and middle school years are better positioned to advance on track and remain connected to school.

## Customization notes

Many funders supply their own logic model template. If yours does, paste the template headers as the required elements variable so the AI populates your funder's format rather than a generic one. For multi-year grants, split outcomes into year one and year two columns. If your program is early-stage and outcomes data is not yet available, say so in the inputs and ask the AI to note where evidence is forthcoming versus established.

---

From The Nonprofit Grant & Fundraising Library at vetslearn.com/libraries/nonprofit