The Challenge
Arrive Health, a pharmacy benefits manager, relied on highly manual, specialist-intensive processes to review FDA drug sheets and identify cost-equivalent drug therapies. Specialists would read complex pharmaceutical PDFs, compare drug equivalencies, and manually enter data into a rules engine — a slow, expensive process that limited how quickly the company could surface cost savings for insurers, pharmacies, and patients. Scaling this review process without proportionally scaling headcount was the core challenge.
What They Built
Artium built a RAG-based generative AI system that preprocesses FDA pharmaceutical PDFs, extracts and structures drug information, and generates drug equivalency recommendations for human specialist review, using a proprietary Continuous Alignment Testing (CAT) framework to prevent hallucinations.
Artium began by designing purpose-built preprocessing pipelines capable of ingesting complex pharmaceutical PDFs — structured documents with regulatory language that standard parsers struggled to handle accurately. Drug information was extracted, normalized, and structured for downstream retrieval. The RAG architecture was then tuned specifically to the domain, with semantic chunking aligned to pharmaceutical data patterns and a hybrid retrieval layer optimized for both structured queries and open-ended equivalency questions.
To manage hallucination risk in a regulated healthcare environment, Artium developed its proprietary Continuous Alignment Testing (CAT) framework — a multi-stage reliability system that monitored AI outputs at the developer level, overnight in automated test suites, and in production. Rather than treating reliability as a final QA pass, CAT was embedded throughout the build cycle. Human specialists were kept in the loop for final validation, ensuring the system served as an accelerant to expert review rather than a replacement. The entire solution was delivered in approximately 10 weeks on AWS, compressing what had previously been projected as a multi-year initiative.
AI Role
By automating the preprocessing of FDA drug sheets and generating equivalency recommendations before specialist review, the system significantly reduced manual data processing burden — allowing specialists to focus their time on validation and high-judgment decisions rather than initial data extraction.
AI Model
Custom / proprietary
Infrastructure
• AWS (cloud infrastructure and hosting) • RAG architecture (custom-built) • Proprietary CAT (Continuous Alignment Testing) framework • FDA pharmaceutical PDF ingestion pipeline
Integration Points
• AWS services integrated with custom RAG retrieval layer • PDF preprocessing pipeline feeding structured drug data into vector store • CAT framework connected across developer, CI/CD, and production environments • Human specialist review interface receiving AI-generated recommendations
Fortune 500 enterprises and growth-stage companies (Series A and up) in highly regulated industries — especially healthcare, financial services, and media/entertainment — that need to build custom AI-native software, move quickly from POC to production, and require reliability frameworks for non-deterministic AI outputs.
