Yseop speeds up regulatory clinical documentation writing using Amazon Bedrock

Yseop provides a software workflow that converts structured and unstructured data into drafts of critical regulatory documents, including clinical study reports, patient narratives, and clinical summaries. The solution is built on Amazon Bedrock with support for Anthropic Claude 3.5 and uses AWS infrastructure for secure deployment. Medical writers and domain experts review and finalize the AI-generated drafts to preserve regulatory compliance and statistical accuracy.

Organization
Yseop
Industry
Pharma
Location
France
Published
May 2026

Reported outcomes

10 hours

timeTime & speed

Strategic outcomes

Speed & agilityCut document drafting from months to weeksSpeed & agilityGenerated reports in secondsScale & capacityEliminated writing and review timeRisk & compliancePreserved regulatory compliance and accuracy

Primary read

Use case focus

Showing 3 of 3

  • 1Regulatory document automation
  • 2Clinical documentation
  • 3Human-in-the-loop AI
  • Regulatory and clinical documents for drug approvals take weeks or months to prepare and require strict formatting and accuracy.
  • Medical writers spend substantial time assembling information from disparate sources while preserving clinical and statistical fidelity.
  • Use Amazon Bedrock as the backbone for document drafting.
  • Convert structured and unstructured data into precise document drafts for regulatory submission.
  • Keep humans in the loop for review and approval before regulatory submission.
  • Cut document drafting from months to weeks.
  • Reports that once took four hours now take four seconds with Yseop's AI solution.
  • Up to 10,000 hours of writing and review time were eliminated in the first year.
Architecture

Yseop's workflow uses Amazon Bedrock and Anthropic Claude 3.5 to draft structured regulatory documents from structured and unstructured data, deployed on AWS infrastructure with a human-in-the-loop review process where medical writers validate content before submission.

Sources & evidence1
Groundedness: 5/5Type: Customer StoryPublished: May 27, 2026Publisher: AWSEvidence: PrimaryConfidence: High

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Was this useful?

Similar cases