Competitor intelligence¶
Project Title: Generative AI for Competitor Intelligence
Client: Dr. Reddy’s Laboratories (via Deloitte)
Timeline: August 2023 – January 2024
Location: Hyderabad, India
Team Size: 1 (data scientist)
Technologies: Python, Google Cloud Platform (GCP), Vertex AI, PaLM 2 API, Google News API, Web Scraping
Links: Chatbot PoC which answers questions based on an article
Problem Statement
The goal was to proactively identify potential supply chain disruptions caused by FDA inspections at competitor pharmaceutical plants. These inspections, if resulting in FDA 483 reports or warning letters, could delay drug supply to the U.S. market—creating opportunities for competitors.
FDA inspects plants across the world that supply to the US. If any issues are found during these inspections, an FDA 483 report is generated. Based on this report and the responses, it can take up to six months for the FDA to give a warning letter which can cause supply issues from the inspected plant to the USA.
Many news articles will be published on these inspections as they take place, and the results have been based on FDA 483 reports. This can help sales managers identify future opportunities due to competitors' supply issues.
Solution A pipeline was built using the Google News API to fetch news articles about FDA inspections filtered by time and geography. Web scraping techniques extracted article content, which was then processed using the PaLM 2 API to extract structured insights such as inspection dates, company names, locations, and inspection outcomes. This information was mapped to FDA datasets to identify affected drugs. The entire workflow was automated using Vertex AI and deployed on GCP for daily execution.
Vertex AI's PALM API was fine-tuned to provide results in a specific format using Prompt engineering, few-shot prompting techniques and RAG architecture.
Impact The system enabled sourcing and sales teams to monitor competitor vulnerabilities in near real-time, supporting strategic decision-making and opportunity identification in the pharmaceutical supply chain.