Generate a plain-English data dictionary from a table schema
Undocumented tables slow down every analyst who touches them. This prompt turns a raw schema dump into a readable data dictionary that teams can paste into a wiki or Notion page immediately.
I want to create a data dictionary for a database table so that analysts unfamiliar with it can use it independently. Here is the context:
- Table name: {{TABLE_NAME}}
- Schema / column list (paste DDL, column names + types, or a header row): {{SCHEMA_INPUT}}
- Business domain this table lives in: {{BUSINESS_DOMAIN}}
- Any column names or codes whose meaning I already know: {{KNOWN_DEFINITIONS}}
Please do the following:
1. Produce a table with these columns: Column Name | Data Type | Plain-English Description | Example Values | Common Pitfalls.
2. For any column whose name is ambiguous or abbreviated, write two plausible interpretations and mark them clearly so I can confirm the correct one.
3. Identify columns that are likely foreign keys or join candidates based on naming conventions (e.g., suffixes like _id, _key) and note what table they probably link to.
4. Flag any columns where nullability or data type suggests a data-quality risk (e.g., a revenue column stored as VARCHAR).
5. Write a 2-sentence table-level summary I can paste at the top of the dictionary that describes what this table represents and its typical grain (one row per what?).
Note: if the schema is very large (50+ columns), focus the pitfalls column on the 10 highest-risk columns and note which ones you skipped. {{TABLE_NAME}}{{SCHEMA_INPUT}}{{BUSINESS_DOMAIN}}{{KNOWN_DEFINITIONS}}
How to use this prompt
- Copy the prompt above (Copy button on the top-right).
- Replace each
{{VAR}}with your own value. Variables:{{TABLE_NAME}}{{SCHEMA_INPUT}}{{BUSINESS_DOMAIN}}{{KNOWN_DEFINITIONS}}. - Paste it into one of the recommended tools below.
- Iterate: tighten constraints in the prompt if the output is generic.
Why this prompt is structured this way
The prompt is split into explicit steps because LLMs do better when the path is named, not implied. Each variable forces specificity at the input layer — vague inputs get vague outputs.
Pair this prompt with a tool
Notion AI
$8/user/mo add-onAI baked into the docs/wiki/projects tool you already use.
Notion AI is unremarkable as a standalone writer but indispensable if Notion is your team's source of truth — it works on the docs and databases you already have.
Cursor
$20/moAI-first code editor forked from VS Code.
Cursor is VS Code with first-class LLM integration. Multi-file edits, codebase Q&A, autocomplete that's actually useful. The default IDE for many shipping engineers in 2026.
Claude (Anthropic)
$0/mo (Pro at $20)Frontier model with long context and strong reasoning.
Claude (Opus / Sonnet / Haiku tiers) is the assistant favored by writers and engineers who care about reasoning quality and tone. 1M token context on Opus.
ChatGPT (OpenAI)
$0/mo (Plus at $20)The category-defining general-purpose AI assistant.
ChatGPT has the broadest feature surface: image gen, voice, custom GPTs, web browsing, code execution. Often the right default; sometimes beaten on specific tasks by Claude or Perplexity.
The PlaybookPrompts weekly
One short email per week. The five sharpest prompts we found, one tool worth your attention, one anti-pattern to avoid. Unsubscribe in one click.
Newsletter signup is not configured. Set PUBLIC_NEWSLETTER_USERNAME in the build env.