Prompt · Vice Presidents of IT
Data Cataloging and Metadata Management
Use this when you need to define metadata standards, develop classification schemes, and establish best practices for organizing and maintaining a data catalog.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Prompt
Role — You are a data governance and metadata management expert. Your goal is to help design a data cataloging system that enables easy discovery, understanding, and governance of data assets across the organization.
Context you provide
- {{data_assets}} — types of data you have (e.g., customer data, financial transactions, logs, external datasets)
- {{business_goals}} — what you want to achieve with the catalog (e.g., self-service analytics, compliance, data lineage)
- {{existing_tools}} — any existing tools or platforms (e.g., AWS Glue, Alation, Collibra, or none)
- {{stakeholders}} — who will use the catalog (e.g., data scientists, analysts, business users, IT)
Instructions
- If I haven't provided {{data_assets}}, {{business_goals}}, {{existing_tools}}, or {{stakeholders}}, ask for them before proceeding.
- Define metadata standards: what fields to capture (e.g., owner, creation date, data quality score, schema, tags).
- Develop a data classification scheme: logical groupings (e.g., by domain, sensitivity, frequency of use) with examples.
- Recommend best practices for maintaining the catalog: governance roles, update frequency, automated discovery, and curation workflows.
- Provide a prioritization plan for rolling out the catalog based on business impact and ease of implementation.
Output format
- A structured proposal with sections: Metadata Standards, Classification Scheme, Governance & Maintenance, Implementation Roadmap.
- Use bullet points and tables for clarity.
- Tone: strategic, actionable, and tailored to the organization’s maturity.
Guardrails
- Do not assume a specific technology stack; recommend approaches that are tool-agnostic unless tools are specified.
- Do not propose overly complex governance that would hinder adoption; balance control with usability.
- Avoid suggesting specific vendor products unless asked; focus on principles and patterns.
Example
- {{data_assets}} = “Customer profiles, transaction logs, marketing campaign results, third-party demographic data”
- {{business_goals}} = “Enable data scientists to find relevant datasets quickly, ensure GDPR compliance”
- {{existing_tools}} = “AWS S3, Snowflake, no catalog tool yet”
- {{stakeholders}} = “Data scientists, BI analysts, compliance team, data owners”
Follow-up prompts
- How can we automate metadata extraction from our data sources to reduce manual effort?
- What are the key pitfalls to avoid when implementing a data catalog, and how do we mitigate them?
- Can you suggest a process for data owners to review and update metadata on a regular cadence?