AI Labeling Negotiation Strategy Playbook
A pharma company is in labeling negotiations with FDA for a new antidepressant. FDA is proposing a REMS program with a Medication Guide requirement. The company believes the REMS is not warranted given the safety profile. Additionally, FDA's proposed indication language is narrower than the trial population, which would limit commercial uptake.
When to use this playbook
- Use this playbook when the decision looks like the situation above: A pharma company is in labeling negotiations with FDA for a new antidepressant.
- It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Labeling Negotiation Strategy".
- Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.
What you'll need
- FDA's proposed label including REMS requirement and indication language
- Pivotal trial data and patient population description
- REMS justification letter from FDA
- Comparable approved antidepressants with and without REMS
- Commercial impact analysis of narrowed indication
Attachments: Documents (Documents)
The Prompt
You are a regulatory affairs director developing a labeling negotiation strategy for an antidepressant NDA. I am attaching: Work only from the attached source files. If a conclusion is not supported, say so. Produce: 1. Assess the REMS justification: does the safety data support a REMS requirement, and what is the regulatory standard FDA must meet to impose a REMS? 2. Identify the precedent arguments: which comparable antidepressants with similar safety profiles were approved without REMS, and how do they undercut FDA's position? 3. Develop the indication language negotiation: what broader language is scientifically supportable from the trial data, and what is the minimum acceptable indication? 4. Assess the commercial impact of REMS: what is the projected revenue difference between REMS and no-REMS scenarios over 5 years? 5. Tell me whether to request a formal dispute resolution meeting, submit a formal response, or negotiate informally — and what the escalation path is if FDA maintains its position. Call out where independent models are likely to disagree, and list follow-up documents a reviewer should request.
What to expect
- REMS justification assessment with regulatory standard
- Precedent argument development
- Indication language negotiation position and minimum acceptable
- Commercial impact of REMS scenarios
- Negotiation strategy and escalation path
Review before you act
- Validate this output against source files before relying on it: Assess the REMS justification: does the safety data support a REMS requirement, and what is the regulatory standard FDA must meet to impose a REMS?.
- Validate this output against source files before relying on it: Identify the precedent arguments: which comparable antidepressants with similar safety profiles were approved without REMS, and how do they undercut FDA's position?.
- Validate this output against source files before relying on it: Develop the indication language negotiation: what broader language is scientifically supportable from the trial data, and what is the minimum acceptable indication?.
- Validate this output against source files before relying on it: Assess the commercial impact of REMS: what is the projected revenue difference between REMS and no-REMS scenarios over 5 years?.
- 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 Labeling Negotiation Strategy, 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 rems justification assessment with regulatory standard; precedent argument development; indication language negotiation position and minimum acceptable; commercial impact of rems scenarios. Those are comparison artifacts — they only exist if more than one model runs. Models split on deficiency root cause, whether a signal is noise, and how aggressive a labeling position to take. Divergence should be resolved in a labeled review meeting.
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.

