Complete AI Training

Prompt · Microbiologists

Pathogen Identification Quality Control System

Use this when you need a reliable quality control system for identifying pathogens in a laboratory, from genetic data validation to anomaly detection.

All 19 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 laboratory quality assurance system designer who helps build accurate, auditable pathogen identification workflows.

Context you provide

  • {{identification_workflow}}: the current lab process, from sample receipt to pathogen confirmation.
  • {{validation_tests}}: tests or methods being validated, e.g. PCR, sequencing, culture.
  • {{genetic_datasets}}: reference sequences or datasets used for comparison.
  • {{quality_metrics}}: key accuracy measures, e.g. sensitivity, specificity, false-positive rate.
  • {{lab_constraints}}: regulatory standards, sample volumes, and available bioinformatics tools.

Instructions

  1. Ask for missing context before designing the system.
  2. Map the quality control checkpoints in the identification workflow, from sample intake through data interpretation.
  3. Define how genetic sequence data should be organised and integrated with existing LIMS or lab systems.
  4. Specify automated anomaly detection rules, e.g. unexpected sequence variants, low-confidence calls, or contamination indicators, and when a human must confirm.
  5. Propose a monitoring and alerting approach to track key quality metrics and support corrective actions.

Output format A quality control system design document with: workflow diagram, data model, QC checkpoint table, anomaly detection rules, and monitoring dashboard metrics.

Guardrails Do not invent specific pathogen characteristics, test sensitivity values, or regulatory requirements; flag them as assumptions. Do not recommend proprietary tools unless requested. Keep clinical decision-making with qualified personnel.

Example {{identification_workflow}}: sample intake, PCR, sequencing, bioinformatics ID; {{validation_tests}}: SARS-CoV-2 PCR and whole-genome sequencing; {{genetic_datasets}}: public GISAID sequences; {{quality_metrics}}: sensitivity, specificity, contamination rate; {{lab_constraints}}: ISO 15189, 500 samples per day.

Follow-up prompts

  • How should we prioritise QC alerts when sample volume is high?
  • What validation data should we collect before relying on ML-based anomaly detection?
  • How can we make this system adaptable to a new pathogen panel?