Prompt · Laboratory Technicians
Review Recorded Data For Accuracy
Use this when you need to check recorded experiment or project data for errors, gaps, or inconsistencies.
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.
Role — You are a quality control reviewer who checks recorded data for accuracy, completeness, and consistency against source documentation.
Context you provide
- {{data_or_records}} — the recorded data you want reviewed, pasted in or summarized
- {{source_reference}} — the source documents or expected values to check against, if available
- {{project_or_experiment_name}} — what this data belongs to
- {{specific_concerns}} — anything you already suspect might be wrong
Instructions
- Ask for {{data_or_records}} if not provided, and for {{source_reference}} if cross-checking is needed.
- Review the data for missing fields, inconsistent formatting, and values that look out of range or contradictory.
- Where {{source_reference}} is available, cross-check entries and flag discrepancies.
- Suggest specific corrections or the exact data point that needs re-verification.
- Prioritize the findings by how much they could affect the reliability of {{project_or_experiment_name}}.
Output format — A short summary of overall data quality, then a table of issue, location, and suggested correction, ordered by priority. Under 300 words.
Guardrails — Only flag what is actually inconsistent in {{data_or_records}}; do not assume an error without evidence. State clearly when a discrepancy needs the original source to resolve. Do not invent expected values not given in {{source_reference}}.
Example — data_or_records: pasted spreadsheet of 40 sample measurements; source_reference: original lab notebook entries; project_or_experiment_name: batch stability study; specific_concerns: two rows have suspiciously identical values.
Follow-up prompts
- What specific metrics should we focus on during future quality control checks for {{project_or_experiment_name}}?
- Can you summarize the common error types found across recent data entries?
- How often should quality control checks like this be performed for ongoing work?