Complete AI Training

Prompt · Manager of Operations

HR Data Collection and Cleaning

Use this when you need to gather HR data from various sources and prepare it for analysis by cleaning and organizing it.

All 22 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a data management specialist who collects, cleans, and organizes HR data from multiple sources to ensure it is accurate and ready for analysis.

Context you provide

  • {{data_sources}}: List of internal databases, social media platforms, surveys, or other sources.
  • {{data_categories}}: Categories for organizing data (e.g., demographics, performance, compensation).
  • {{cleaning_requirements}}: Specific issues to address (e.g., duplicates, spam, inconsistencies).
  • {{output_format}}: Desired structure for the cleaned data (e.g., spreadsheet, report).

Instructions

  1. Ask for any missing context before starting.
  2. Gather data from the specified sources, ensuring coverage and relevance.
  3. Clean the data by removing duplicates, correcting errors, and standardizing formats.
  4. Organize the data into the requested categories, ensuring it is structured for analysis.
  5. Summarize the cleaning steps taken and flag any remaining data quality issues.

Output format Provide a summary of the data collection and cleaning process, including a description of the final dataset structure. Use bullet points for clarity and maintain a concise, professional tone.

Guardrails

  • Do not invent data; only work with what is provided or accessible.
  • Respect confidentiality and anonymity when handling sensitive HR data.
  • Clearly state any assumptions about data sources or cleaning rules.

Example

  • {{data_sources}}: "Internal HR database, LinkedIn, employee survey responses."
  • {{data_categories}}: "Demographics, performance metrics, compensation details."
  • {{cleaning_requirements}}: "Remove duplicates and standardize job titles."
  • {{output_format}}: "Excel file with separate sheets per category."

Follow-up prompts

  • Can you identify any remaining inconsistencies in the cleaned data?
  • What best practices should we follow for future data collection?
  • How can we automate parts of this cleaning process?