AI Playbook for Shy Bladder Protocol Compliance
A DOT-regulated bus driver was unable to provide a sufficient specimen volume after 3 hours at the collection site. The collector followed shy bladder procedures. The MRO has referred the donor to a physician for evaluation. The physician's report is inconclusive. The employer is asking whether this is a refusal to test.
When to use this playbook
- Use this playbook when the decision looks like the situation above: A DOT-regulated bus driver was unable to provide a sufficient specimen volume after 3 hours at the collection site.
- It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Shy Bladder Protocol Compliance".
- Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.
What you'll need
- Collector's chain of custody documentation and shy bladder notation
- Collection site timeline (arrival, attempts, 3-hour mark)
- Referring physician's medical evaluation report
- DOT 49 CFR Part 40 shy bladder procedures
- Employer's inquiry on refusal-to-test determination
Attachments: Documents (Documents)
The Prompt
You are a Medical Review Officer adjudicating a shy bladder case for a DOT-regulated transit employee. I am attaching: Work only from the attached source files. If a conclusion is not supported, say so. Produce: 1. Review the collector's documentation: were all DOT shy bladder procedures followed correctly — notification, 40-ounce fluid authorization, 3-hour time limit? 2. Assess the physician's evaluation: what medical conditions could legitimately explain an inability to void, and does the inconclusive report meet or fail the DOT standard? 3. Determine the MRO's options under 49 CFR Part 40 when the physician cannot identify a medical reason. 4. Assess whether any step in the collection process, if done incorrectly, would require a cancellation regardless of the physician's finding. 5. Tell me the final MRO determination and the exact regulatory citation supporting it. Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.
What to expect
- Collector procedure compliance assessment
- Physician evaluation adequacy analysis
- MRO determination options under 49 CFR Part 40
- Collection error cancellation analysis
- Final MRO determination with regulatory citation
Review before you act
- Validate this output against source files before relying on it: Review the collector's documentation: were all DOT shy bladder procedures followed correctly — notification, 40-ounce fluid authorization, 3-hour time limit?.
- Validate this output against source files before relying on it: Assess the physician's evaluation: what medical conditions could legitimately explain an inability to void, and does the inconclusive report meet or fail the DOT standard?.
- Validate this output against source files before relying on it: Determine the MRO's options under 49 CFR Part 40 when the physician cannot identify a medical reason.
- Validate this output against source files before relying on it: Assess whether any step in the collection process, if done incorrectly, would require a cancellation regardless of the physician's finding.
- 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 Shy Bladder Protocol Compliance, 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 collector procedure compliance assessment; physician evaluation adequacy analysis; mro determination options under 49 cfr part 40; collection error cancellation 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.
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.

