AI Marketing Landscape & Leads Dataset
Case Study Summary
Client: PharmaSights & A billion-dollar European Pharmaceutical Company - Confidential
Website: www.pharmasights.com
Industry: Biopharma & Drug Development
Impact Metrics:
- Cut 5 years of manual research into 8 weeks with AI-powered automation
- Built a proprietary database of 3.5M+ global events by aggregating data from diverse online sources
- Uncovered 1,000+ high-value deals for targeted marketing
- Saved $50K+ annually by replacing costly third-party tools with in-house intelligence
- Gained exclusive market insights from a proprietary data map unavailable anywhere else
A pharmaceutical company aims to develop a five-year overview of all biopharma deals to better understand the competitive landscape and identify potential future marketing & business development collaborations. (Further details cannot be disclosed due to NDA)
Challenge
Tracking various deal types (such as co-development, co-commercialization, etc.) gives companies a competitive edge by revealing competitor strategies and marketing opportunities. However, this data is hard to access. Most subscription-based platforms, which can cost over $50,000 annually, cover only about 5% of these deals, even though much of the information is publicly available online.
Our Approach
To address this challenge, we developed a custom AI-powered search agent to collect, filter, and enrich relevant data. The process begins with a targeted search across the internet, leveraging APIs such as ClinicalTrials.gov and custom-built web scrapers, to gather initial deal information. A context-aware LLM then reviews the data to determine whether it meets the predefined criteria. For deals identified as “interesting”, the system performs a deeper, more focused search to extract additional details such as deal size, participating companies, and other key metrics.
Results & Impact
- Identified 20x more deals than any other platform with a custom-built dataset
- Delivered +1,000 marketing-ready opportunities aligned with the company’s exact vision
- Saved 5 years of manual work and cut $50K+ in yearly costs
- Cut 5 years of manual research into 8 weeks with AI-powered automation
Solution Overview
High level data curation process
Tech Stack
- OpenAI
- Python
- FastAPI
- PlayWright
- SQL
Additional Context
- Timeline: 2 months
- Team Size: 3 people
- Role: AI Engineer
- Expertise in proprietary dataset curation
- Focus on OpenAI model integration
-
Let's have a virtual coffee together!
Want to see if we're a match? Let's have a chat and find out. Schedule a free 30-minute strategy session to discuss your AI challenges and explore how we can work together.