Build a Results Framework with AI
A 5-step prompt workflow that produces a populated results framework with impact, outcomes, outputs, indicators, and causal logic.
What you'll build
A complete results framework table with impact, outcomes, outputs, indicators, baselines, targets, and a narrative summary explaining the program logic.
Before you start
- Your program description or concept note
- Target population, geographic scope, and timeline
- Donor requirements or strategic framework to align with (if applicable)
- If you completed the Theory of Change workflow, paste the causal pathway from that guide and start at Step 3 (Define Outputs)
Start at the top: what is the long-term change this program contributes to? The impact statement anchors the entire framework. If you already built a Theory of Change using another workflow guide, you can skip to Step 3 and use your ToC impact and outcomes as inputs.
You are a senior M&E specialist. I need to build a results framework. Start with the impact statement. Based on the program description I provide, draft 2-3 candidate impact statements. Each should be: - One sentence - Long-term (beyond the program's timeframe) - Broader than what this program alone can achieve (contribution, not attribution) - Aligned with sector goals or SDGs For each candidate, explain the strengths and weaknesses and recommend which one to use. Here is my program description: [Describe your program, sector, target population, and overall goal]
The impact statement should be something you contribute to, not something you achieve alone. "Reduced child mortality in target districts" is good. "All children survive to age 5" is aspirational fantasy.
Define the medium-term changes your program expects to achieve. Outcomes are changes in behavior, practice, or conditions that happen because of your outputs.
Based on the impact statement, define 2-4 program outcomes. For each outcome: - Outcome statement (one sentence, starts with a change verb: "increased," "improved," "strengthened," "reduced") - Which impact pathway it contributes to (how does this outcome lead toward the impact?) - Target group (who experiences this change?) - Timeframe (when should this change be observable?) - How you will know (what would evidence of this outcome look like?) Ensure outcomes are: - Logically connected to the impact (not a separate goal) - Measurable within the program timeframe - Distinct from each other (not overlapping) - At the right level (not so high they are impacts, not so low they are outputs)
Map the outputs (what the program directly delivers) and key activities (what the program does). Every output should logically contribute to at least one outcome.
For each outcome, define the outputs and activities that produce it. **Outputs** (3-6 total): The direct, tangible products or services the program delivers. For each: - Output statement (what is delivered, to whom, how many) - Which outcome it contributes to - Key activities that produce this output (2-4 activities per output) **Causal logic**: For each output-to-outcome link, state the "because" explicitly. "Output X contributes to Outcome Y because..." Present as a hierarchical table: Impact > Outcome > Output > Activities, with the causal logic column. Flag any outputs that do not clearly connect to an outcome, and any outcomes that lack outputs.
Attach at least one SMART indicator to each result level. This is what makes the framework measurable.
For each level of the results framework (impact, outcomes, outputs), assign SMART indicators. Present as a table with columns: - Result level - Result statement - Indicator - Type (quantitative/qualitative) - Baseline (known or "TBD") - Annual target - End-of-project target - Data source - Collection frequency Rules: - 1 indicator for impact level - 1-2 indicators per outcome - 1 indicator per output - Total should not exceed 15 indicators - Use standard donor indicators where they exist - Every indicator must be measurable with realistic resources
If you cannot explain how you would collect data for an indicator in two sentences, it is probably too complex to measure reliably.
Write a short narrative that explains the program logic to someone looking at the framework for the first time.
Write a results framework narrative (500-700 words) that explains: 1. **The program logic** (200-300 words): How activities produce outputs, how outputs produce outcomes, and how outcomes contribute to impact. Make the "because" logic explicit at each level. 2. **Key assumptions** (100-150 words): What must be true for this logic to hold? List 3-5 critical assumptions. 3. **Measurement approach** (100-150 words): How the program will track progress at each level, including data sources and frequency. 4. **Limitations** (50-100 words): What this framework does not capture and why. Write for a mixed audience of program staff, donors, and partners. Use plain language.
Use MEStudio's scoring rubric to check the quality of what you just built. Send this prompt in the same conversation to get a scored assessment with specific revision suggestions.
Open the scoring rubricIf any dimension scores below 4, go back to the relevant step and ask the AI to strengthen that section. The rubric tells you exactly what to fix.
Not sure which AI tool to use?
Try the AI Tool Selector to find the best tool for your specific M&E task, or browse 130+ M&E-specific prompts.