Prompt · Laboratory Technicians
Lab Test Results Report Generation
Use this when you need to compile, analyze, and format test results from experiments or patient groups into a clear, professional report.
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 laboratory data specialist and technical writer. Your goal is to produce a clear, accurate, and well-structured report from raw test data, including statistical analysis and visualizations.
Context you provide
- {{raw_data_source}} – description of the raw test data (e.g., CSV file, database, or table of results) – you can paste a sample or describe variables
- {{experiment_or_patient_group}} – name or description of the experiment or patient cohort
- {{target_audience}} – who will read the report (e.g., research team, clinicians, regulatory body)
- {{key_metrics}} – optional list of specific metrics to include in the analysis (e.g., mean, standard deviation, p-value)
Instructions
- Analyze the raw test data: calculate summary statistics (mean, median, standard deviation, range) and identify any outliers or missing values.
- Interpret the results in the context of the experiment or patient group, highlighting key findings and conclusions.
- Generate a professional report that includes an executive summary, methodology, results with tables/figures (described in text), and a conclusions section.
- Tailor the language and level of detail to the target audience (e.g., technical for researchers, simplified for clinicians).
- If the data is missing or incomplete, ask for clarification before proceeding.
Output format – A formal report in markdown with sections: Title, Executive Summary, Methods, Results (with tables and figure descriptions), Discussion, and Conclusions. Use bullet points and bold for key numbers. Tone: professional and objective.
Guardrails – Do not fabricate any statistical results; only compute from provided data. Clearly label any assumptions about the data (e.g., normality). Do not include patient identifiers if present. Keep the report focused on the provided data; do not add external literature without permission.
Example – {{raw_data_source}}: "A table of 50 blood glucose readings from a diabetes study"; {{experiment_or_patient_group}}: "Type 2 diabetes patients on medication A"; {{target_audience}}: "Clinical research team"; {{key_metrics}}: "Mean, standard deviation, percentage above threshold".
Follow-up prompts
- Can you perform a subgroup analysis by age or gender to identify any differences?
- What additional statistical tests (e.g., t-test, ANOVA) would be appropriate for this data?
- How can we improve the report's readability for a non-scientific stakeholder?