Decision-Linked Measurement Quality: Score how well a deliverable links its data, indicators, or findings to specific decisions across five dimensions using AI. Use to assess MEL plans, indicator reference sheets, monitoring briefs, evaluation reports, learning agendas, and any deliverable that should drive action rather than only describe state.
Logframe Assumptions Column Quality: Score the assumptions column of a logframe for completeness, testability, and link to causal logic. Paste the logframe to assess whether assumptions are doing their analytic job. Use this for the logframe or results framework column; for the assumptions section of a Theory of Change narrative see toc-assumptions-quality.
Logframe Means of Verification Column: Score the means of verification (MoV) column of a logframe for source specificity, method appropriateness, and frequency clarity. Paste the logframe to assess whether the MoV column will guide data collection.
Logframe Quality Assessment: Score a logframe across five dimensions using AI. Paste your logframe into the prompt to get a structured quality assessment with dimension scores, evidence citations, and priority revisions.
MEL Data Flow Diagram Quality: Score the data flow diagram inside a MEL plan for completeness, role clarity, and feasibility. Paste the diagram (or its narrative description) to get a structured assessment with revision priorities.
MEL Learning Agenda Quality: Score the learning questions section of a MEL plan for strategic relevance, answerability, and decision-linkage. Paste the section to assess whether questions will drive learning that informs program adaptation.
MEL Plan Review: Score a Monitoring, Evaluation and Learning plan across five dimensions using AI. Paste your MEL plan to get a structured quality assessment with dimension scores, evidence citations, and priority revisions.
MEL Roles and Responsibilities Matrix: Score the roles and responsibilities matrix inside a MEL plan for completeness, specificity, and feasibility. Paste the matrix to assess whether every M&E function has named ownership.
Theory of Change Assessment: Score a Theory of Change across five dimensions using AI. Paste your ToC narrative or diagram description to get a structured quality assessment with dimension scores, evidence citations, and priority revisions.
Theory of Change Causal Logic: Score the causal logic of a theory of change in five dimensions using AI. This is a focused component rubric for the causal pathway only, useful when a ToC is embedded in a logframe, MEL plan, contribution analysis, or adaptive management memo. For a holistic assessment of a complete ToC document including stakeholder engagement and presentation, use the theory-of-change-assessment rubric instead.
ToC Assumptions Quality: Score the assumptions section of a Theory of Change. Paste the assumptions to assess whether they are stated explicitly, testable, prioritized, and connected to specific causal links. Use this for the ToC narrative assumptions section; for the assumptions column of a logframe or results framework see logframe-assumptions-column.
ToC Pathway Completeness: Score whether the causal pathway in a Theory of Change covers the full logic from inputs to impact. Paste the ToC to assess gaps, jumps, and missing intermediate steps.
Baseline and Target Validity: Score the baseline values and targets attached to indicators for plausibility, evidence basis, and ambition calibration. Paste the indicator with baseline and target to assess whether the numbers are defensible.
Composite Indicator Design: Score the design of a composite or index indicator for component selection, weighting logic, and transparency. Paste the indicator definition to assess construction quality.
Disaggregation Quality: Score data disaggregation quality across the full data pipeline (planning, collection, analysis, reporting, use) using AI. Applies to MEL plans, indicator frameworks, surveys, evaluation reports, donor progress reports, and monitoring briefs where data should be disaggregated.
Donor Indicator Alignment: Score whether indicators align with the required donor framework (FFP, USAID, DAC, etc.). Paste your indicator set with the target donor's framework named.
Indicator Quality: Score any indicator or set of indicators in any M&E document (logframes, MEL plans, PIRS, indicator reference sheets, results frameworks) for SMART criteria, definition clarity, disaggregation, source documentation, and indicator family coherence using AI.
Indicator Source Fitness: Score whether the means of verification (data source plus collection method) named for each indicator are appropriate, specific, and feasible. Paste the indicator with its MoV to assess source-method fit.
Indicator Statement Clarity: Score just the wording of an indicator statement for clarity, precision, and unit specification. Paste the indicator statement to get a focused diagnostic on language quality.
Output vs Outcome Classification: Score whether indicators are correctly classified at output, outcome, or impact levels. Paste indicators to identify mis-classifications that obscure the results chain.
Proxy Indicator Justification: Score the justification for using proxy indicators. Paste the proxy indicator and its rationale to assess whether the proxy-to-outcome link is defended and bounded.
SMART Criteria Check: Score one or more indicators specifically against the SMART criteria (Specific, Measurable, Achievable, Relevant, Time-bound). Paste the indicator(s) to get a per-criterion assessment with revision suggestions.
FGD Guide Quality: Score a focus group discussion guide across five dimensions using AI. Paste your guide to get a scored assessment of question design, structure, ethics, research alignment, and facilitator guidance. Use when reviewing an FGD guide as a standalone document or embedded in an inception report, evaluation design, or needs assessment.
FGD Probes Quality: Score the probe questions in a Focus Group Discussion guide for depth, neutrality, and sequencing. Paste the FGD guide to assess whether probes will surface meaningful insight.
FGD/KII Protocol Quality: Score a focus group discussion or key informant interview protocol across five dimensions using AI. Paste your protocol to get a structured assessment of question design, structure, ethics, alignment, and facilitator guidance before fielding.
KII Guide Quality: Score a key informant interview guide across five dimensions using AI. Paste your guide to get a scored assessment of question design, structure, ethics, research alignment, and interviewer guidance. Use when reviewing a KII guide as a standalone document or embedded in an inception report, evaluation design, or needs assessment.
KII Question Design: Score the question design in a Key Informant Interview guide for depth, openness, and tailoring to informant type. Paste the KII guide to assess whether questions will surface expert insight.
Observation Checklist Quality: Score the design of a structured observation checklist for observability, inter-rater consistency, and field-usability. Paste the checklist to assess whether observations will be reliable.
Sampling Design Quality: Score a sampling design across five dimensions using AI. Paste your sampling plan to get a structured assessment of strategy, size, selection, coverage, and replicability before fielding begins.
Survey Instrument Review: Use AI to review a survey questionnaire before field deployment. Get dimension scores, flagged questions with corrections, and a ready-to-implement revision list in minutes.
Survey Question Wording: Score the wording of survey questions for clarity, neutrality, and freedom from common biases (leading, double-barreled, ambiguous). Paste your survey questions to get a per-question diagnostic.
Survey Response Options Quality: Score the response options in a survey for exhaustiveness, mutual exclusivity, and scale design. Paste the survey to assess whether response choices will yield clean, analyzable data.
Survey Translation Quality: Score the quality of a translated survey instrument for fidelity, cultural appropriateness, and back-translation evidence. Paste source and translation to assess equivalence.
Evaluation Inception Report Quality: Score an evaluation inception report across five dimensions using AI. Paste your draft to get a structured assessment of refined questions, methodology, tools, analysis plan, and risk/ethics provisions before approval to proceed to fieldwork.
Evaluation Management Arrangements: Score the governance and oversight structure for an evaluation. Paste the section to assess whether the management arrangements will sustain the evaluation through delivery.
Evaluation ToR Quality: Score an evaluation Terms of Reference across five dimensions using AI. Paste your draft ToR to get a structured assessment of scope, questions, methodology, deliverables, and ethics before procurement.
Evaluator Selection Criteria: Score the evaluator selection criteria and scoring matrix in a ToR. Paste the section to assess whether the criteria will identify the right candidate.
Inception Stakeholder Engagement Plan: Score the stakeholder engagement plan section of an inception report. Paste the section to assess whether stakeholders will be appropriately engaged across the evaluation.
Inception Workplan Quality: Score the workplan section of an evaluation inception report for timeline realism, milestone clarity, and dependency mapping. Paste the workplan to assess whether the evaluation will deliver on time.
ToR Budget Fitness: Score whether the budget in an evaluation Terms of Reference is fit for the scope and methods. Paste the budget and scope sections to assess feasibility.
ToR Evaluation Questions: Score the evaluation questions in a Terms of Reference for scope, answerability, and decision-relevance. Paste the questions section to assess whether they will produce useful findings.
Adaptive Management Plan: Score the adaptive management plan that operationalizes how findings flow back to program decisions. Paste the section to assess whether learning will actually drive program change.
Analysis Plan Quality: Score the analysis plan section of any document where one is required, including MEL plans, inception reports, evaluation reports, contribution analyses, and needs assessments. Use to confirm the plan maps to questions, names methods specifically, and includes triangulation and quality checks.
Instrument Pilot Results: Score the documentation of instrument pilot testing (what was piloted, with whom, what was revised). Paste the pilot report to assess whether the final instrument is field-ready.
Limitations Disclosure: Score the methodology limitations disclosure in a report for honesty, completeness, and impact-on-findings explanation. Paste the limitations section to assess credibility.
Methodology Rigor: Score the methodological rigor of an evaluation, study, or assessment across five dimensions using AI. Use to assess MEL plans, evaluation ToRs, inception reports, evaluation reports, contribution analyses, needs assessments, sampling plans, and any document where methodology choices need justification and quality safeguards.
Mixed Methods Integration: Score how qualitative and quantitative data are integrated in a mixed-methods design. Paste the methodology or analysis section to assess whether integration is substantive (not parallel).
Qualitative Coding Frame Quality: Score a qualitative coding frame (codebook) for structure, mutual exclusivity, and grounded-theory hygiene. Paste the codebook to assess whether it will yield consistent coding.
Sample Justification: Score the sample size and selection rationale in a methodology or sampling plan. Paste the sampling section to assess whether the sample will support the intended analyses. Use this for sample-size justification and selection rationale (analytic purpose, power, method fit, feasibility); for the sampling frame itself (the list or source the sample is drawn from) see sampling-frame-quality.
Sampling Frame Quality: Score the sampling frame itself (the list or source from which the sample is drawn) for completeness, currency, and coverage. Separate from sample-size justification. Use this for the frame itself (coverage, currency, cleaning, frame limitations); for the sample-size justification and selection rationale see sample-justification.
Stakeholder Engagement Quality: Score the quality of stakeholder engagement across five dimensions using AI. Use to assess MEL plans, evaluation ToRs, inception reports, evaluation reports, learning agendas, contribution analyses, and any deliverable involving stakeholder consultation.
Triangulation Strength: Score the triangulation approach across methods, sources, and perspectives in an evaluation or analysis plan. Paste the relevant section to assess whether findings will be defensibly cross-corroborated. Use this for the triangulation approach itself (method, source, investigator, conflict resolution, reporting visibility); for per-finding evidentiary review in a report see findings-evidence-strength.
Budget vs Actuals Narrative: Score the financial commentary in a progress report (budget vs actuals plus variance explanation). Paste the narrative section to assess transparency and decision-readiness.
Contribution Analysis Section: Score a formal contribution analysis write-up. Paste the section to assess whether contribution claims are appropriately bounded by evidence and counterfactual reasoning.
Data Visualization Quality: Score the charts and data visualizations in a report for chart-type appropriateness, labeling, and integrity. Paste the report (with viz descriptions if no images) to assess whether visuals communicate cleanly.
Donor Progress Report Review: Score a donor progress report across five dimensions using AI. Paste your narrative report to get a structured quality assessment with dimension scores, evidence citations, and priority revisions before submission.
Evaluation Report Scoring: Use AI to score an evaluation report across five quality dimensions. Get a structured verdict with evidence citations and a revision brief before accepting or publishing the report.
Executive Summary Quality: Score the executive summary of an evaluation report for completeness, key-finding clarity, and stand-alone value. Paste the executive summary to assess whether it can serve as a decision-maker's brief.
Findings Evidence Strength: Score whether each finding in a report is properly evidenced. Paste the findings section to assess source citation, triangulation, and inference strength per finding. Use this for per-finding evidentiary review in a report; for scoring the triangulation approach itself (method, source, investigator, conflict resolution) see triangulation-strength.
Findings-to-Recommendations Quality: Score how well findings translate into actionable recommendations across five dimensions using AI. Use to assess evaluation reports, donor progress reports, contribution analyses, learning briefs, monitoring briefs, case studies, and any document where findings should drive recommendations.
Lessons Learned Quality: Score the lessons learned section of a report for actionability, generalizability, and evidence basis. Paste the lessons learned to assess whether they will be useful beyond this program.
Methods Section Quality: Score the methods section of an evaluation report for transparency, completeness, and replicability. Paste the methods section to assess whether a reader could reconstruct the study.
Needs Assessment Report Quality: Score a needs assessment report across five dimensions using AI. Paste your report to get a structured assessment of problem definition, methodology, needs identification, population voice, and recommendations before program design.
Plain Language and Accessibility: Score the plain language quality and accessibility of any M&E deliverable across five dimensions using AI. Use to assess donor reports, monitoring briefs, learning briefs, adaptive memos, evaluation reports, case studies, and any deliverable communicated to a non-specialist audience.
Recommendations Actionability: Score recommendations in a report for clarity, ownership, and actionability. Paste the recommendations section to assess whether decision-makers can act on them.
Theory-Based Evaluation Write-Up: Score the explicit ToC test in the findings narrative. Paste the section to assess whether the theory of change has actually been evaluated, not just used as a planning artifact.
Data Storage and Privacy Practices: Score the data storage and privacy practices in a methodology or data management plan. Paste the relevant section to assess whether respondent data will be protected end-to-end.
Do No Harm Protocol: Score the do-no-harm risk identification and mitigation protocol for an evaluation, monitoring, or research activity. Paste the protocol to assess coverage of physical, psychological, social, and economic risks. Use this for the substantive risk-and-mitigation analysis; for the organizational machinery (training, reporting channels, escalation chain, audit trail) see safeguarding-procedures.
Ethical Standards: Score the ethical standards of an M&E or research deliverable across five dimensions using AI. Use to assess MEL plans, evaluation ToRs, inception reports, surveys, FGD/KII protocols, sampling plans, evaluation reports, case studies, and any deliverable involving human participants or sensitive data.
Gender Equality and Social Inclusion (GESI): Score any M&E deliverable for GESI integration across five dimensions using AI. Use to assess MEL plans, evaluation ToRs, inception reports, indicator frameworks, surveys, FGD/KII protocols, and evaluation reports.
Gender Integration Depth: Score how deeply gender is integrated into an M&E design (beyond disaggregation). Paste the gender-relevant sections to assess whether gender analysis informs methods, interpretation, and use. Use this for the depth of gender as a single analytic lens; for multi-axis identity analysis (gender x disability x age x ethnicity) see intersectionality-analysis.
Informed Consent Design: Score the informed consent form or process for clarity, comprehension, and voluntariness. Paste the consent script or form to assess whether respondents will truly consent informed.
Intersectionality Analysis: Score whether the M&E design treats identity intersections (gender, disability, age, ethnicity) as distinct analytic categories, beyond single-axis disaggregation. Use this for multi-axis intersectional analysis; for the depth of gender as a single analytic lens (methods, interpretation, use) see gender-integration-depth.
Reflexivity and Positionality: Score evaluator self-reflection on bias, perspective, and positionality. Paste the relevant section to assess whether qualitative findings are grounded in reflexive practice.
Safeguarding Procedures: Score the safeguarding procedures in a research or evaluation design. Goes deeper than do-no-harm: training, escalation chain, response protocol, audit trail. Use this for the organizational machinery of safeguarding; for substantive risk identification and mitigation see do-no-harm-protocol.
Vulnerable Population Protections: Score the protections for vulnerable populations (children, refugees, survivors, people with disabilities, etc.) in an evaluation or research design. Paste the relevant section to assess safeguards.