RecommendationHigh riskComparison recommended

AI Chain of Custody Irregularity Assessment Playbook

A laboratory has reported a positive marijuana result for a non-DOT safety-sensitive employee. The MRO has identified two chain of custody irregularities: the collector did not enter the time on the CCF, and Federal Copy 1 does not have the collector's signature. The employer wants to terminate based on the positive result.

When to use this playbook

  • Use this playbook when the decision looks like the situation above: A laboratory has reported a positive marijuana result for a non-DOT safety-sensitive employee.
  • It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Chain of Custody Irregularity Assessment".
  • Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

  • Federal custody and control form (all copies) with identified irregularities
  • Laboratory result report
  • Collector's correction/affidavit (if submitted)
  • Company drug policy and testing procedures
  • SAMHSA/HHS Mandatory Guidelines for Federal Workplace Drug Testing

Attachments: Documents (Documents)

The Prompt

You are a Medical Review Officer assessing chain of custody irregularities before a non-DOT positive result can be reported. I am attaching:

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

Produce:
1. Assess each CCF irregularity under HHS Mandatory Guidelines: is a missing time entry a fatal flaw requiring cancellation or a correctable error?
2. Assess the missing collector signature: fatal flaw or correctable with a collector affidavit?
3. Determine whether the laboratory can provide a corrected report or whether the MRO must cancel the test.
4. Assess the non-DOT context: are HHS guidelines required for this employer, or does the company's own policy govern?
5. Tell me the MRO's reporting options, the recommended action, and what documentation the employer needs before making a termination decision.

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

What to expect

  • CCF irregularity classification (fatal vs. correctable)
  • Correction affidavit adequacy assessment
  • Laboratory corrected report determination
  • Non-DOT vs. DOT applicability analysis
  • MRO reporting options and termination documentation requirements

Review before you act

  • Validate this output against source files before relying on it: Assess each CCF irregularity under HHS Mandatory Guidelines: is a missing time entry a fatal flaw requiring cancellation or a correctable error?.
  • Validate this output against source files before relying on it: Assess the missing collector signature: fatal flaw or correctable with a collector affidavit?.
  • Validate this output against source files before relying on it: Determine whether the laboratory can provide a corrected report or whether the MRO must cancel the test.
  • Validate this output against source files before relying on it: Assess the non-DOT context: are HHS guidelines required for this employer, or does the company's own policy govern?.
  • 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 Chain of Custody Irregularity Assessment, 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 ccf irregularity classification (fatal vs. correctable); correction affidavit adequacy assessment; laboratory corrected report determination; non-dot vs. dot applicability analysis. 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 TestingCollection and CustodyRecommendationHighDocuments

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.