ReviewHigh riskComparison recommended

AI Adulterated Specimen Investigation Playbook

A laboratory reported a specimen as adulterated with glutaraldehyde for a DOT-regulated airline employee. The donor denies any tampering. The MRO must determine whether to report this as a refusal to test. The donor is a 15-year employee with no prior test history and a clean safety record.

When to use this playbook

  • Use this playbook when the decision looks like the situation above: A laboratory reported a specimen as adulterated with glutaraldehyde for a DOT-regulated airline employee.
  • It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Adulterated Specimen Investigation".
  • Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

  • Laboratory adulteration report (glutaraldehyde detection and confirmatory test results)
  • DOT 49 CFR Part 40 adulterated specimen provisions
  • Donor interview notes (denial of tampering)
  • Employee work history and prior drug test record
  • FAA return-to-duty and safety-sensitive requirements

Attachments: Documents (Documents)

The Prompt

You are a Medical Review Officer adjudicating an adulterated specimen result for a DOT-regulated airline employee. I am attaching:

Work only from the attached source files. If a conclusion is not supported, say so.

Produce:
1. Assess the laboratory's adulteration finding: what is the scientific basis for the glutaraldehyde finding, and is there any endogenous explanation?
2. Review DOT 49 CFR Part 40: is an adulterated specimen automatically a refusal to test, or does the MRO have discretion based on the interview?
3. Assess the donor interview: under DOT rules, what can the MRO consider from the donor's explanation, and what is inadmissible?
4. Determine whether the employee's 15-year clean record has any bearing on the MRO's required determination.
5. Tell me the MRO's required reporting action, the exact regulatory language, and what the donor's appeal rights are.

Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.

What to expect

  • Glutaraldehyde scientific basis and endogenous explanation assessment
  • Refusal-to-test determination framework
  • Donor interview admissibility analysis
  • Prior record relevance to MRO determination
  • Required reporting action with regulatory citation and appeal rights

Review before you act

  • Validate this output against source files before relying on it: Assess the laboratory's adulteration finding: what is the scientific basis for the glutaraldehyde finding, and is there any endogenous explanation?.
  • Validate this output against source files before relying on it: Review DOT 49 CFR Part 40: is an adulterated specimen automatically a refusal to test, or does the MRO have discretion based on the interview?.
  • Validate this output against source files before relying on it: Assess the donor interview: under DOT rules, what can the MRO consider from the donor's explanation, and what is inadmissible?.
  • Validate this output against source files before relying on it: Determine whether the employee's 15-year clean record has any bearing on the MRO's required determination.
  • Confirm every cited figure, date, counterparty, or requirement against the attached originals — models compress and can drop a qualifier.
  • Treat disagreement between models as a review item, especially on classification, materiality, and recommended next action.
  • Do not authorize an operational, clinical, legal, credit, or enforcement action solely because the models agree.

Why compare models on this

For Adulterated Specimen Investigation, running the same attachments across independent models is useful because the hard part is classification and completeness, not fluency. The workflow is already designed to surface glutaraldehyde scientific basis and endogenous explanation assessment; refusal-to-test determination framework; donor interview admissibility analysis; prior record relevance to mro determination. Those are comparison artifacts — they only exist if more than one model runs. Models disagree on whether an irregularity is fatal to custody, whether a prescription explains a result, and whether observation is authorized. Those splits are MRO work, not auto-verification.

Forensic Drug TestingSpecimen ValidityReviewHighDocuments

See governed multi-model AI on your own prompt

Compare GPT-5, Claude, and Gemini side by side, with human review and a decision record built in.