PlanningCritical riskComparison recommended

AI CMC Manufacturing Change Assessment Playbook

A pharma company is scaling its manufacturing process from clinical-scale (200L bioreactor) to commercial-scale (2000L). The CMC team has identified 3 process parameters that show different behavior at scale. FDA's scale-up guidance requires comparability data. The NDA is on a rolling submission schedule with a 6-month window.

When to use this playbook

  • Use this playbook when the decision looks like the situation above: A pharma company is scaling its manufacturing process from clinical-scale (200L bioreactor) to commercial-scale (2000L).
  • It is a fit when you have source files in hand and need a structured, reviewable analysis — not a generic chat answer about "CMC Manufacturing Change Assessment".
  • Do not use it as a substitute for licensed, legal, clinical, or authorized official judgment in the domain.

What you'll need

  • Clinical-scale and commercial-scale process parameter comparison data
  • Drug substance quality attribute results at both scales
  • FDA scale-up and post-approval changes guidance (SUPAC)
  • Rolling NDA submission schedule
  • Prior FDA feedback on CMC from pre-NDA meeting

Attachments: Documents (Documents)

The Prompt

You are a CMC regulatory specialist assessing scale-up manufacturing comparability for an NDA submission. I am attaching:

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

Produce:
1. Assess the 3 divergent process parameters: are they within acceptable ranges for process comparability, or do they represent material changes requiring additional bridging data?
2. Determine the regulatory classification of the scale change: is this a Level 1, 2, or 3 change under SUPAC, and what is the filing requirement?
3. Identify the critical quality attributes (CQAs) most at risk from the scale change and what additional comparability testing is needed.
4. Design the comparability protocol: which batches, which tests, and which acceptance criteria will satisfy FDA's requirements.
5. Tell me the impact on the NDA submission timeline and whether a prior approval supplement (PAS) will be required.

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

What to expect

  • Process parameter comparability assessment
  • SUPAC change level classification
  • CQA risk analysis
  • Comparability protocol design
  • NDA timeline impact and PAS requirement determination

Review before you act

  • Validate this output against source files before relying on it: Assess the 3 divergent process parameters: are they within acceptable ranges for process comparability, or do they represent material changes requiring additional bridging data?.
  • Validate this output against source files before relying on it: Determine the regulatory classification of the scale change: is this a Level 1, 2, or 3 change under SUPAC, and what is the filing requirement?.
  • Validate this output against source files before relying on it: Identify the critical quality attributes (CQAs) most at risk from the scale change and what additional comparability testing is needed.
  • Validate this output against source files before relying on it: Design the comparability protocol: which batches, which tests, and which acceptance criteria will satisfy FDA's requirements.
  • 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 CMC Manufacturing Change 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 process parameter comparability assessment; supac change level classification; cqa risk analysis; comparability protocol design. 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 SciencesCMC and Development PathwaysPlanningCriticalDocuments

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.