RecommendationCritical riskDivergence review useful

AI Parallel Scientific Advice Strategy Playbook

A biotech is developing a first-in-class gene therapy for a rare pediatric neurological disease. The company plans to seek approval in both the US and EU. Development decisions made now will affect both submissions. The team wants to align FDA and EMA requirements before the Phase 2/3 pivotal study design is locked.

When to use this playbook

  • Use this playbook when the decision looks like the situation above: A biotech is developing a first-in-class gene therapy for a rare pediatric neurological disease.
  • It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "Parallel Scientific Advice Strategy".
  • Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

  • Phase 1 clinical data summary
  • Proposed Phase 2/3 pivotal study design
  • FDA Breakthrough Therapy Designation letter
  • EMA PRIME designation letter
  • Regulatory guidance from FDA and EMA on gene therapy development

Attachments: Documents (Documents)

The Prompt

You are a global regulatory affairs director designing a parallel FDA/EMA scientific advice strategy for a gene therapy. I am attaching:

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

Produce:
1. Identify the key areas of divergence between FDA and EMA requirements for gene therapy: manufacturing, long-term follow-up, endpoints, patient population.
2. Design the scientific advice questions for each agency: what specific design questions to ask FDA (Type B/C meeting) and EMA (Scientific Advice) to align pivotal study requirements.
3. Assess the endpoint strategy: what endpoints FDA will accept, what EMA requires, and whether a single pivotal study can satisfy both agencies.
4. Identify the accelerated approval/conditional marketing authorization strategy for both agencies given the rare pediatric disease.
5. Tell me the sequencing strategy: run FDA and EMA scientific advice in parallel or in sequence, and how to use each agency's feedback to strengthen the other submission.

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

What to expect

  • FDA/EMA requirement divergence analysis
  • Scientific advice question design for each agency
  • Endpoint harmonization strategy
  • Accelerated/conditional approval pathway assessment
  • Meeting sequencing strategy

Review before you act

  • Validate this output against source files before relying on it: Identify the key areas of divergence between FDA and EMA requirements for gene therapy: manufacturing, long-term follow-up, endpoints, patient population.
  • Validate this output against source files before relying on it: Design the scientific advice questions for each agency: what specific design questions to ask FDA (Type B/C meeting) and EMA (Scientific Advice) to align pivotal study requirements.
  • Validate this output against source files before relying on it: Assess the endpoint strategy: what endpoints FDA will accept, what EMA requires, and whether a single pivotal study can satisfy both agencies.
  • Validate this output against source files before relying on it: Identify the accelerated approval/conditional marketing authorization strategy for both agencies given the rare pediatric disease.
  • 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 Parallel Scientific Advice 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 fda/ema requirement divergence analysis; scientific advice question design for each agency; endpoint harmonization strategy; accelerated/conditional approval pathway assessment. 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.

Pharma & Life SciencesClinical and Evidence StrategyRecommendationCriticalDocuments

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.