The Nonprofit AI Almanac

Impact measurement and evaluation

Create a data dictionary

Documents what each field means (a data dictionary is a simple glossary of your data) so everyone records it the same way.

Lower risk: public info only — Share only field names and descriptions, not actual records.

Please note: This site is only a guide to help people understand. Consult your IT, security and/or privacy department for clarification.

Before you start, gather

Copy [LIST OF FIELD NAMES] from your system's export header or form builder. Name the tool in [SYSTEM OR SPREADSHEET NAME]. Afterward, have data-entry staff settle every item marked CONFIRM. Include no actual records.

Starter prompt

Create a data dictionary for our [SYSTEM OR SPREADSHEET NAME]. The fields are: [LIST OF FIELD NAMES]. For each field give a plain-English definition, the type of data, allowed values or format, whether it is required, and an example using made-up data. Flag any fields that are sensitive. Define only the fields I list, and mark any definition you are unsure of as CONFIRM instead of guessing.

Paste the prompt into your AI tool first, then replace the placeholders with your own details. Don't use real names of clients or donors.

Open an AI tool

You are leaving this guide. Copy the prompt first, then open a tool. The link goes to the website of the company named on each link, in a new tab. That company's terms and privacy policy apply there. Paste the prompt in, then replace the placeholders with your own details. Don't enter real names or confidential details.

Check the result

Have the people who enter the data confirm each definition matches how they actually use the field.

What it might get wrong

Believable definitions that differ from how your staff really use a field. Invented lists of allowed values, or rules on required and optional fields. Example data that looks like a real person.

Why AI makes things up