AI for M&E Guides
Walk-through guides for every major M&E task. Filter by phase or search by topic.
What every guide includes
Every guide is written to get you from setup to a usable output, with the same three pieces in every one.
Step-by-step workflow
A clear process from setup to output, written for non-technical practitioners.
Copy-paste prompt templates
Ready-to-use prompts you can adapt immediately for your context.
Field-tested frameworks
Structured approaches grounded in M&E practice, not generic AI advice.
Start here
Featured guides
Three guides that cover the highest-leverage moves: how to prompt, how to plan, and how to analyze.
Browse all guides
Filter by phase or search by topic. Each guide is a complete walk-through with step-by-step instructions, copy-paste prompts, and field-tested frameworks.
Foundations
Cross-cutting skills and safeguards that apply to every AI-for-M&E task. Start with these before going deeper into a specific phase.
Get started with AI
Pick a tool, write better prompts, and get a usable output fast.
How to Write AI Prompts That Actually Work for M&E
Stop getting generic outputs. The 4Cs Framework helps you write prompts that produce donor-ready indicators, analysis, and reports on the first try.
Read guideHow to Use ChatGPT for M&E
ChatGPT can draft indicators, analyze qualitative data, and write donor reports -- if you know how to direct it. A practical guide for M&E practitioners.
Read guideHow to Choose the Right AI Tool for M&E
ChatGPT, 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.
Read guideBest AI Tools for M&E: ChatGPT, Claude, Gemini, and Local Models Compared
No single AI tool is best for all M&E work. ChatGPT, Claude, Gemini, and local models each have genuine advantages for specific tasks. This comparison helps you match the tool to the job.
Read guideUse AI responsibly
Privacy, governance, and the safeguards your organization needs in place.
How to Protect Data Privacy When Using AI for M&E
Beneficiary data belongs to beneficiaries, not AI servers. The SAFE Framework helps you use AI tools without risking a data protection breach, donor compliance violation, or loss of community trust.
Read guideHow to Govern AI Use in Your M&E Work
Most AI failures in M&E are not run-time problems. They are setup problems. 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.
Read guideHow to Run a Data Protection Impact Assessment for AI in M&E
DPIAs 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.
Read guideHow to Assess Your M&E Team's AI Readiness
Most 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.
Read guideReady to run a workflow?
Playbooks chain prompts together to produce a complete output in a single AI conversation, like a donor-ready MEL plan or a coded qualitative dataset.