Agent Evaluation
Agent Evaluation workflow that groups context collection, production, review, and packaging tasks into one deliverable.
Assets tagged with evaluation.
Agent Evaluation workflow that groups context collection, production, review, and packaging tasks into one deliverable.
Build a theory of change and logic model for a nonprofit or mission-driven program - problem and population, assumptions and external factors, inputs, activities, outputs, short-, medium- and long-term outcomes, causal links as testable if-then statements, indicators with source, frequency, baseline and target, and what the program can claim to contribute to versus attribute. Non-clinical outcome wording for mental-health programs. Produces a table plus a Mermaid diagram. Use when asked for a logic model, theory of change, outcomes framework, program model for a grant application, or to tighten outcomes and indicators. Do not use for a full evaluation plan (design-program-evaluation), analyzing survey data (analyze-survey-results), company KPI trees (kpi-tree), or OKRs (okr-drafter prompt).
Build a theory of change and logic model for a nonprofit or mission-driven program - problem and population, assumptions and external factors, inputs, activities, outputs, short-, medium- and long-term outcomes, causal links as testable if-then statements, indicators with source, frequency, baseline and target, and what the program can claim to contribute to versus attribute. Non-clinical outcome wording for mental-health programs. Produces a table plus a Mermaid diagram. Use when asked for a logic model, theory of change, outcomes framework, program model for a grant application, or to tighten outcomes and indicators. Do not use for a full evaluation plan (design-program-evaluation), analyzing survey data (analyze-survey-results), company KPI trees (kpi-tree), or OKRs (okr-drafter prompt).
Design a proportionate evaluation plan for a nonprofit or mission-driven program: process and outcome evaluation questions, design choices and what each can support (pre/post, retrospective pre-post, comparison group, qualitative), indicators and instruments, sampling and response plans, consent and assent for minors, data privacy and small-cell suppression, analysis plan, limitations, and a reporting timeline sized to a small team. Non-clinical. Use when asked to plan an evaluation, measure program impact or outcomes for a funder, choose between pre-post and comparison designs, or plan measurement for a youth or family program. Do not use for drafting survey questions only (survey-designer prompt), a logic model (build-logic-model), or analyzing collected data (analyze-survey-results).
Design a proportionate evaluation plan for a nonprofit or mission-driven program: process and outcome evaluation questions, design choices and what each can support (pre/post, retrospective pre-post, comparison group, qualitative), indicators and instruments, sampling and response plans, consent and assent for minors, data privacy and small-cell suppression, analysis plan, limitations, and a reporting timeline sized to a small team. Non-clinical. Use when asked to plan an evaluation, measure program impact or outcomes for a funder, choose between pre-post and comparison designs, or plan measurement for a youth or family program. Do not use for drafting survey questions only (survey-designer prompt), a logic model (build-logic-model), or analyzing collected data (analyze-survey-results).
Turn a survey export (CSV) into a results report - cleaning duplicates, speeders and partials, response rate and nonresponse cautions, Likert distributions and top-2-box instead of inappropriate averages, matched versus unmatched pre/post, crosstabs with small-cell suppression at a user-set threshold, open-ended coding with a codebook, what can and cannot be concluded, and a plain-language summary. Includes a Python tabulation and suppression script. Use when asked to analyze survey results, summarize a feedback or pre/post survey export, report results by site or group, or write up survey findings for a funder or board. Do not use for writing survey questions (survey-designer prompt), planning an evaluation (design-program-evaluation), or interview synthesis (user-interview-synthesis prompt).
Turn a survey export (CSV) into a results report - cleaning duplicates, speeders and partials, response rate and nonresponse cautions, Likert distributions and top-2-box instead of inappropriate averages, matched versus unmatched pre/post, crosstabs with small-cell suppression at a user-set threshold, open-ended coding with a codebook, what can and cannot be concluded, and a plain-language summary. Includes a Python tabulation and suppression script. Use when asked to analyze survey results, summarize a feedback or pre/post survey export, report results by site or group, or write up survey findings for a funder or board. Do not use for writing survey questions (survey-designer prompt), planning an evaluation (design-program-evaluation), or interview synthesis (user-interview-synthesis prompt).