Create a Learning Agenda

Develop learning questions, methods, and a plan for how your program will capture and use lessons.

Your Prompt

Also open in:GeminiCopilotThese open empty, so paste the prompt in.
What You Need
Supply the main program decisions, intended users, results or theory of change, current evidence, stakeholders, timing, and resource limits.
Choose This Prompt When
Use this to decide what the program needs to learn; choose a data-use plan to map routine reporting and decision flow.

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.

Use only program material supplied in this chat. Ask me to paste the program decisions, learning priorities, theory of change, current evidence, and constraints if essential details are absent. Do not treat this request as evidence that those materials exist.

Draft a learning agenda that helps the supplied team make specific decisions. If the program purpose and at least one decision or uncertainty are missing, ask for them before drafting questions. Do not claim that stakeholders chose priorities unless their input is provided.

Start with a short table of priority learning questions, why each matters, who will use the answer, and when a decision is due. Then map each question to existing evidence, feasible additional inquiry, analysis, owner, and a review or sharing moment. Choose the smallest adequate method set; mixed methods are optional, and disaggregate only when meaningful, feasible, and safe. Add a timeline fitted to the actual program period and a feedback loop showing how findings, dissent, and decisions will be recorded. Close with limitations, open priorities, and proposed next steps. Label all proposed questions and arrangements as draft until agreed.

Specify how the relevant stakeholders will participate in choosing questions, interpreting findings, and receiving results. Mark any unconfirmed engagement role as proposed.