The AI for M&E toolkit
Choose what you are doing and get the right guide or playbook, with a map of where AI fits at each stage.
- task guides
- 21
- task guides
- playbooks
- 9
- playbooks
- lifecycle stages
- 8
- lifecycle stages
Build Your Shortlist
31 matches
- Where AI fits across your programThe landscape map: AI suitability, what it does well, and where a human is mandatory, stage by stage.Map
- How to Write AI Prompts That Actually Work for M&EStop getting generic outputs. The 4Cs Framework helps you write prompts that produce reviewable indicators, analysis, and reports on the first try.Guide
- How to Choose the Right AI Tool for M&EChatGPT, Claude, Gemini, and open-source models each have strengths. The TASK Framework helps you pick the right tool for the job instead of defaulting to whichever one you tried first.Guide
- Best AI Tools for M&E and Evaluators in 2026No single AI tool is best for all evaluation work. ChatGPT, Claude, Gemini, and local models each have genuine advantages for specific tasks. This comparison helps you match the tool to the job.Guide
- How to Use ChatGPT for M&EChatGPT can produce first drafts of indicators, qualitative summaries, and donor reports; a person must check them. A practical guide for M&E practitioners.Guide
- How to Build a Theory of Change with AIStop drawing boxes and arrows that nobody believes. A 4-step workflow that uses AI to surface hidden assumptions, stress-test causal logic, and produce a ToC your donors trust.Guide
- How to Use AI to Design an M&E FrameworkLogframe, results framework, outcome mapping, or something else? AI can help you choose the right structure and populate it, but you need to tell it what decisions the framework must support.Guide
- How to Use AI for Indicator DevelopmentGood indicators are specific, collectible (your team can realistically gather the data), and decision-linked (someone will act on the number). AI can generate dozens in seconds, but most will be generic unless you constrain the prompt with your actual project context and data collection capacity.Guide
- How to Write a Logframe with AIAI can build a first-draft logframe from your project brief in minutes. The challenge is knowing how to review it, fix it, and make it defensible to your donor.Guide
- How to Use AI to Write a MEL PlanA MEL plan is the most requested M&E deliverable, and the most time-consuming to write from scratch. AI can draft the structure, populate indicator tables, and flag gaps, but only if you guide it section by section.Guide
- How to Build Better Surveys with AIMost AI survey tools stop at generating questions. This guide covers the full lifecycle: choosing question types, catching bias, adding skip logic, and piloting before you deploy.Guide
- How to Clean Messy M&E Data with AIA 4-step workflow that combines free tools and AI checks to find errors, keep an audit trail, and leave your original file untouched.Guide
- How to Use AI for Baseline and Endline AnalysisCompare baseline and endline measurements using the actual sample design, sufficient inputs, and explicit limits on what observed change can show.Guide
- How to Code Qualitative Interview Data with ChatGPTUse AI to suggest codes and organize excerpts, with source checks and an analytic approach that fits your evaluation questions.Guide
- How to Draft Evaluation Reports with AIStop staring at a blank page. A 4-phase workflow turns your completed analysis into reviewable evaluation narrative in hours, not days.Guide
- How to Use AI for Donor Reports Without Fabricating ResultsDonor reports consume more M&E staff time than any other deliverable. The risk is not that AI writes badly, it is that AI writes confidently about results you never measured. Give it your real data and the donor template, and that failure mode largely disappears.Guide
- How to Assess Your M&E Team's AI ReadinessMost M&E teams jump to AI tools before knowing if they're ready. A 20-minute self-assessment across 5 dimensions tells you where to invest first and what to skip.Guide
- How to Govern AI Use in Your M&E WorkThis guide argues that most AI failures in M&E start in the setup, not at run time. Before AI touches the work, six decisions shape whether the outputs will hold up: which tasks AI should handle, where your data goes, where humans stay in the loop, and when to stop.Guide
- How to Quality-Assure AI-Assisted M&E WorkAI produces confident-looking wrong answers. Without a validation stack, you publish them. This 6-layer framework gives your M&E team the discipline to catch errors before they reach donors, boards, or communities.Guide
- How to Get Reliable AI Outputs in M&E WorkCloud AI is confident and fluent and sometimes just wrong. For M&E work that feeds into evaluations, donor reports, and funding decisions, fluent-sounding errors are the enemy. This page covers the practical moves that reduce AI failure rates: hallucination prevention, local model use, quality control patterns, and pipelined AI.Guide
- How to Protect Data Privacy When Using AI for M&EUse the SAFE Framework to assess identification risks, minimize data, and check approved processing before using AI for M&E.Guide
- How to Run a Data Protection Impact Assessment for AI in M&EDPIAs are becoming standard for AI use in evaluation and monitoring. This 4-step process helps you assess risks before uploading any data to an AI tool, not after something goes wrong.Guide
- Build an Evaluation Plan with AIA five-step workflow to draft evaluation questions, methods, collection activities, analysis and safeguards for accountable review.Playbook
- Code Qualitative Data with AIA 5-step prompt workflow that takes raw interview or focus group transcripts through to a coded dataset with thematic analysis. Run all prompts in a single AI conversation.Playbook
- Build a Theory of Change with AIA 5-step prompt workflow that helps draft a Theory of Change with causal pathways, assumptions, risks, and an indicator framework. Run all prompts in a single AI conversation.Playbook
- Design a Baseline Survey with AIA 5-step workflow for drafting indicator-linked survey questions, routing, a sampling design, and a pilot protocol for local review.Playbook
- Build a MEL Plan with AIA 5-step prompt workflow that helps draft a Monitoring, Evaluation, and Learning plan with results framework, indicator matrix, data collection plan, reporting schedule, and learning agenda.Playbook
- Create a Donor Report with AIA five-step workflow to draft a progress report from supplied indicator data, narrative evidence, documented lessons and proposed actions.Playbook
- Develop Indicators with AIA 5-step prompt workflow that takes you from program objectives to a complete indicator reference sheet with definitions, data sources, and targets.Playbook
- Clean M&E Data with AIA 4-step prompt workflow that takes raw survey data through validation, error detection, correction, and documentation to propose checks and a correction protocol for analyst review.Playbook
- Build a Results Framework with AIA 5-step prompt workflow that produces a populated results framework with impact, outcomes, outputs, indicators, and causal logic.Playbook
New to This? Start with the Map.
Where AI is strong, where it is risky, and where a human has to hold the pen, one stage at a time. Then come back here for the method.