Draft a Theory of Change from a Program Narrative
Transform an existing program narrative into a structured theory of change with causal pathway, intermediate outcomes, and testable assumptions. Useful when the program description is written but the ToC is not yet formalized.
Draft: Draft a Theory of Change from a Program Narrative
Your Prompt
- What You Need
- Paste the program narrative and long-term outcome, plus any cited studies, context evidence, assumptions, and required format.
- Choose This Prompt When
- Use this to transform an existing narrative into a ToC. Choose Create a Theory of Change to build one from program inputs, or Create a Logframe from ToC once the pathway is agreed.
Describe your goal, audience, available information and constraints. Your words are added to the prompt as supplied. You can also use the guided fields below.
Kept in this tab while you work. Copy and Start includes this description.
Copy this prompt and paste it into your AI chat to start. If it needs source material, the AI will ask for it.
Evidence and applicability: use only supplied or verifiable evidence for historical facts, values, quotations, completed activities and approvals. Preserve conflicting sources with their provenance; do not choose a preferred value without adjudication. Mark missing evidence as unknown or not evidenced, not as proof an activity never occurred. Keep proposed plans and illustrative examples separate from findings. Never invent a baseline, quote, pilot, validation or sign-off to complete a template. Match methods to the purpose and population; a suitable single-method design is valid. Distinguish descriptive change from causal attribution. Check obligations in the applicable funding agreement rather than assuming a universal donor rule.
You are a senior MEAL specialist. Your task is to transform an existing program narrative into a formalized Theory of Change (ToC) with a clear causal pathway, intermediate outcomes, and testable assumptions.
Program Narrative: paste your program narrative covering problem statement, target population, activities, and intended outcomes
Long-Term Outcome: your program's long-term outcome
Donor Context: the relevant donor framework
Requirements:
- Extract the Long-Term Outcome: Identify the long-term outcome from the narrative, or use the one provided above. Confirm it is stated as a population-level change (not an output or activity).
- Backwards-Map Intermediate Outcomes: Identify the intermediate outcomes supported by the narrative that plausibly lead to the long-term outcome. Each intermediate outcome should describe a behavior change, capacity change, or system-level shift, not a deliverable.
- Map Outputs to Outcomes: For each intermediate outcome, identify the specific outputs (products, services, trained individuals, completed infrastructure) that produce it. Flag any intermediate outcome lacking a plausible output chain.
- List Activities: Under each output, list the activities required to deliver it. Draw activities directly from the narrative where possible.
- Testable Assumptions: At each causal step (activity -> output, output -> intermediate outcome, intermediate outcome -> long-term outcome), articulate the specific assumption that must hold for the next level to occur. Assumptions must be falsifiable, not truisms. For each assumption, state how it could be tested or monitored during implementation, aligned with the relevant donor framework.
- Evidence Base Gaps: For each causal link, indicate whether the link is supported by the strength of evidence actually available, citing the study or report and its relevance; otherwise mark the link unverified. Flag links where evidence is weak and a learning question is warranted.
Output Format:
- Structured ToC Narrative: A written explanation of the causal pathway from activities through outputs, intermediate outcomes, and long-term outcome, with assumptions and evidence flags integrated at each step.
- Diagram Description: A text description of a ToC diagram (boxes and arrows) that a designer could render. Specify node labels, connecting arrows, and where assumptions appear between levels.
- Assumptions Table: A table listing each assumption, the causal step it supports, how it will be tested or monitored, and the evidence strength for that link.
- Evidence Gap Register: A short list of causal links where evidence is weak, framed as learning questions the program should address.
If essential material is missing: Request the actual narrative and supporting evidence before asserting a causal pathway or rating evidence strength. Keep source-derived statements distinct from proposed links and assumptions. A literature title alone cannot justify a link; mark unsupported links for verification with the team.
Check: Score It with the Theory of Change Assessment Rubric
The Review Prompt
Paste the draft at the bottom of this prompt and run it. It scores each criterion from 1 to 5 and says why.
Establish the document purpose, design, stage, applicable requirements, and available source evidence before rating. Distinguish N/A with a reason, not evidenced, unresolved conflicting evidence, and observed inadequate performance. Missing records do not prove an activity did not occur. Missing records alone justify evidence requests and a deferred readiness decision, not an inferred failure or mandatory repeat activity. Do not invent documentary, signature or approval requirements. Cite document locations for every finding. Keep supported facts separate from proposals, assumptions, and illustrative examples. Never invent completed fieldwork, validation, consent, approval, values, dates, quotations, or assigned ownership. Label unconfirmed owners and proposed revisions for confirmation. Report blocking ethics, safety, confidentiality, measurement-validity, or inference failures first regardless of scores. Give a total and band only when all five dimensions are applicable and sufficiently evidenced with no unresolved evidence conflict; otherwise show the dimension profile, coverage, and evidence requests without a total, band, or rescaled equivalent. A documentation score never authorizes use, fielding, compliance, or approval.
You are an expert M&E advisor. Score the Theory of Change I will provide using the rubric below.
SCORING RUBRIC - Theory of Change Assessment Rate each applicable and evidenced dimension 1-5: Choose the highest anchor fully supported by the evidence; a material defect takes precedence over a favorable element count. An absent required feature in a complete submitted artifact is an observed documentation defect; an unavailable source or record is not evidenced, not proof the underlying activity failed.
DIMENSION 1: Causal Logic
- Score 5: Pathway from activities to long-term change explicit at every step. Each causal link stated. A reviewer unfamiliar with the context can trace the full logic without additional explanation.
- Score 4: Pathway explicit at every step with no more than two links implied rather than stated.
- Score 3: Pathway recognizable but half or more causal links are implied rather than stated. A reader can follow general direction but must fill in multiple steps.
- Score 2: Half or more causal steps are missing or jumpy. Several outcomes do not follow from the preceding change.
- Score 1: No clear causal pathway. Reads as a list of activities and aspirations.
DIMENSION 2: Evidence Base
- Score 5: Every major causal claim references specific evidence (research, program data, or contextual analysis). Evidence directly supports the claimed mechanism.
- Score 4: At least 80 percent of major causal claims reference specific evidence. The remainder rely on assertion, but no major mechanism is unsupported.
- Score 3: Half or more major causal claims reference evidence; the remainder rely on assertion. Evidence cited may lack specificity or direct relevance for some claims.
- Score 2: Less than half of causal claims reference evidence, OR cited evidence is generic ("research shows") without specific source.
- Score 1: No evidence cited. ToC is entirely assertion-based.
DIMENSION 3: Assumptions
- Score 5: Material preconditions, mechanism beliefs, participant-behavior assumptions, and external dependencies are identified at relevant transitions. Each is specific and testable/trackable; assumptions are distinguished from activities and facts.
- Score 4: Assumptions listed at at least 80 percent of major transition points. The remainder may be vague but major dependencies are visible.
- Score 3: Assumptions listed at half or more transition points. Those listed are recognizable as causal preconditions or beliefs but half or more lack the specificity needed for monitoring.
- Score 2: Assumptions listed at less than half of transition points, OR half or more are trivially true or program activities.
- Score 1: No assumptions stated. Change is presented as inevitable.
DIMENSION 4: Outcomes Hierarchy
- Score 5: Short-term, intermediate, and long-term outcomes clearly differentiated and correctly sequenced. Levels and depth fit the mechanism/scope; no universal knowledge-behavior-system-population sequence is required.
- Score 4: Hierarchy present and correctly sequenced. No more than two outcomes appear at the wrong level or are ambiguously labeled.
- Score 3: Hierarchy visible but at least three outcomes are at the wrong level or sit ambiguously between adjacent levels.
- Score 2: Half or more outcomes are at the wrong level, OR levels are inconsistently labeled.
- Score 1: No usable sequence exists where multiple steps are needed. A justified short pathway or one relevant outcome level is not automatically inadequate.
DIMENSION 5: Boundary & Sustainability
- Score 5: ToC scoped to what the program can plausibly influence within its timeframe and resources. Sustainability section names who owns the change post-project, what conditions must hold, and what handover steps the program will take.
- Score 4: Scope reasonable. Sustainability section present but lacks one of (named post-project owner, required conditions, handover steps).
- Score 3: Scope implied but not stated. Sustainability referenced in general terms (e.g., "the change will be sustained through capacity building") without specifying owner, conditions, or handover.
- Score 2: ToC over-ambitious (claims credit for changes the program cannot drive alone), OR no sustainability section.
- Score 1: No boundary defined and no sustainability mention.
OUTPUT FORMAT: Return your assessment as a table followed by a summary:
| Dimension | Score (1-5), N/A, or not evidenced | Evidence from ToC | Priority Revision |
|---|---|---|---|
| Causal Logic | |||
| Evidence Base | |||
| Assumptions | |||
| Outcomes Hierarchy | |||
| Boundary & Sustainability |
Blockers and evidence gaps: Report these first, with source locations. Coverage: State applicable and sufficiently evidenced dimensions out of five. Total: X/25, only when all five dimensions are applicable and evidenced with no unresolved evidence conflict. Otherwise omit the total and band. Optional descriptive band (eligible totals only; never approval): Strong (22-25) / Adequate (17-21) / Needs Revision (11-16) / Substantial Revision (5-10) Single Most Important Revision: [One specific sentence]
For any dimension scored 1 or 2, add a brief explanation and a concrete revision example.
THEORY OF CHANGE TO SCORE: [Paste your Theory of Change narrative or diagram description here]
Fix: Revise What Scored Low
The Revise Prompt
Paste the draft and its scores at the bottom of this prompt. It revises the parts that scored below 4.
Establish the document purpose, design, stage, applicable requirements, and available source evidence before rating. Distinguish N/A with a reason, not evidenced, unresolved conflicting evidence, and observed inadequate performance. Missing records do not prove an activity did not occur. Missing records alone justify evidence requests and a deferred readiness decision, not an inferred failure or mandatory repeat activity. Do not invent documentary, signature or approval requirements. Cite document locations for every finding. Keep supported facts separate from proposals, assumptions, and illustrative examples. Never invent completed fieldwork, validation, consent, approval, values, dates, quotations, or assigned ownership. Label unconfirmed owners and proposed revisions for confirmation. Report blocking ethics, safety, confidentiality, measurement-validity, or inference failures first regardless of scores. Give a total and band only when all five dimensions are applicable and sufficiently evidenced with no unresolved evidence conflict; otherwise show the dimension profile, coverage, and evidence requests without a total, band, or rescaled equivalent. A documentation score never authorizes use, fielding, compliance, or approval.
You are an expert M&E advisor. Review the draft Theory of Change I will provide and fix every problem that falls below the Good (4) threshold on the Theory of Change Assessment rubric.
WHAT TO LOOK FOR AND FIX:
Causal Logic problems: Steps that jump without explanation (e.g., "training leads to improved livelihoods" with no intermediate step). Activities presented as outcomes. Outcomes listed in the wrong order.
Evidence Base problems: Claims stated as fact without any citation. Generic references ("evidence shows") without specifics. Causal mechanisms that contradict published research.
Assumption problems: Missing assumptions at major transition points. Participant-behavior assumptions presented as inevitable without specifying or testing their conditions. Assumptions that are actually program activities. Assumptions so broad they cannot be monitored ("government will be supportive").
Outcomes Hierarchy problems: Knowledge-level changes labeled as long-term outcomes. Behavior change listed before the enabling conditions are in place. Ultimate goal stated as an activity output.
Boundary and Sustainability problems: Program claims full attribution for changes involving many actors. No mention of what happens after project close. No identification of who sustains the change.
OUTPUT FORMAT: For each problem found:
- Dimension: [which dimension]
- Location: [which section or statement in the ToC]
- Problem: [one sentence describing what is wrong]
- Revised version: [the corrected text]
Retain unsupported facts as evidence requests and mark proposed owners, dates, and procedures for confirmation. Then provide the complete revised Theory of Change incorporating all corrections.
DRAFT THEORY OF CHANGE TO REVISE: [Paste your draft Theory of Change here]