Novo Nordisk, a global pharmaceutical company and maker of Ozempic, develops innovative medicines for chronic diseases including diabetes and obesity. The company serves millions of patients worldwide with life-changing treatments that require extensive regulatory documentation before they can reach patients.
With Claude, Novo Nordisk:
For pharmaceutical companies, the path from drug discovery to patient access is paved with paperwork. It’s a highly regulated industry, so each new treatment Novo Nordisk develops comes with its own mountain of required documentation: Clinical study reports that run hundreds of pages. Highly technical device verification protocols. Guides that explain complex treatments in consumer-friendly ways. Producing the documentation for a clinical trial consumed so much time and so many resources, even with help from external agencies, that it was slowing down the organization’s ability to bring new medicines to market.
The pinnacle of this process is the clinical study report (CSR), which summarizes drug trial results in a document that can be up to 300 pages long. Producing a CSR was a grueling multi-month cycle of writing, reviews, rewrites, and approvals. Staff writers averaged only 2.3 CSRs per year, and the manual process remained prone to errors and subjective interpretation.
The stakes couldn't have been higher. Each day of delay in bringing a new medicine to market can cost pharmaceutical companies up to $15 million in potential revenue. More importantly, patients with diabetes, obesity, and other chronic conditions continue waiting for treatments that could transform their lives.
Transform document production from a months-long manual process into an automated system producing regulatory-grade content in minutes. Through NovoScribe, their AI-powered documentation platform built with Claude Code and Anthropic partner MongoDB Atlas, Novo Nordisk creates regulatory documents that consistently receive positive feedback from regulators while dramatically reducing time and resource requirements.
Novo Nordisk used Claude Code to develop NovoScribe, their generative AI platform built on Amazon Bedrock and MongoDB Atlas, with Claude models as the frontier intelligence driving the entire system. The platform combines retrieval-augmented generation (RAG) with domain expert-approved text and case-specific variables to produce accurate, compliant documentation. Initially the team focused on perfecting NovoScribe for CSR production, and then expanded to device protocol documentation and patient materials.
The time saved by NovoScribe was immediate and substantial. “Claude has helped us cut writing times on CSRs by 90% so we can get documentation directly into human hands for review and approval,” said Waheed Jowiya, Digitalization Strategy Director at Novo Nordisk.
Review-to-approval cycles for these automated CSRs have also decreased significantly as reviewers became increasingly satisfied with clinical interpretation and overall output quality. For new trials, the team can now produce a complete study booklet and patient guide in under a minute — materials that previously required months of back-and-forth work with external agencies.
Technical setup for these use cases varied. Adapting the RAG configuration for patient booklets took minimal time, while integrating legacy systems for device protocols required several months of development to ingest unstructured data. "In a highly regulated industry, we can't just throw our data and information into a large language model and hope for the best," Jowiya said. “Our conversations with Anthropic really guided in the ways we can securely use Claude for planning, for strategic tasks, for code generation.” In fact, he adds, Claude has already solved one of his team’s biggest headaches: extracting data from historical research documents.
Adopting Claude Code has fundamentally changed product development at Novo Nordisk. Now, even non-technical team members can prototype ideas – including Jowiya, who has a PhD in molecular biology but not much programming experience. When he has an idea, he says, Claude Code lets him quickly generate a POC using natural language, versus having to sit down and translate that into technical features and tickets he hands off to the development team.
"It allows our scientific domain experts, people like myself and my director Louise, to have a much bigger impact on how things are developed," Jowiya says.
The ability for any team member to spin up a prototype in hours instead of days or weeks has been a strategic catalyst for a relatively small development team of 11 people: now, any member can be a product developer, he explains. "Claude Code lets us do experiments easily, make decisions fast, and iterate quickly to get products out."
This agility has allowed the team to maintain its small size while dramatically expanding capabilities – avoiding the need to scale up headcount and preserving the team's ability to move quickly without the overhead of traditional agile ceremonies.
Today, NovoScribe represents a shift in how Novo Nordisk approaches document creation. The system has gained positive feedback from regulators — perhaps the ultimate validation in this heavily scrutinized industry. What started as an effort to automate clinical study reports has expanded across the organization, transforming how Novo Nordisk handles everything from device verification protocols to patient materials.
The results speak for themselves: documentation that once took entire departments now requires single users. Review cycles have been cut in half. Most importantly, medicines are reaching patients faster than ever before.
The company continues expanding Claude's application across the organization, with pilots underway in medical affairs and plans for broader deployment. They are using Claude Code to expand NovoScribe's current capabilities, with the goal of automating the entire process of producing Common Technical Documents (CTDs), the comprehensive regulatory submissions required for drug approval.
Looking ahead, Novo Nordisk is exploring Claude's potential for data analysis to extract deeper insights from clinical trials and modernize their data infrastructure. The partnership with Anthropic has fundamentally changed how the company thinks about AI's role in pharmaceutical development.
"We've consistently been one of the first movers when it comes to document and content automation in pharma development," said Louise Lind Skov, Director Content Digitalisation. "Our work with Anthropic and Claude has set a new standard — we're not just automating tasks, we're transforming how medicines get from discovery to the patients who need them."