Make the content library
useful again.
A scalable AI pipeline classifies pharmaceutical marketing materials so teams can find, reuse and manage them more consistently.
A global pharmaceutical company
The challenge
A global pharmaceutical organisation manages a vast library of marketing materials, from brochures and presentations to digital assets. To support efficient reuse and compliance, these materials must be classified accurately by content, therapeutic area and intended messaging.
This classification used to be done by hand: a time-consuming and error-prone process. Content often ended up incompletely classified or not classified at all, which made it hard to search, retrieve or repurpose materials across teams.
The solution
Common Sense AI designed and deployed a scalable automation pipeline that uses large language models (LLMs) to classify marketing materials based on their content and context.
Key features:
- Batch processing of more than 1,000 materials at a time
- A deterministic LLM output format, for consistency and easy integration
- An intelligent recovery mechanism: when the model returns an incorrectly formatted response, the system starts a follow-up conversation with the LLM to resolve the issue automatically
The pipeline was engineered for robustness and scalability, for fast and reliable classification even at high volumes.
The result
With the new classification system in place, teams now benefit from:
- Automated tagging of materials with accurate categories
- Less manual effort, freeing up time for higher-value work
- A scalable solution that adapts to every new batch of assets
- Better findability and reuse of marketing content across the organisation
The project shows how LLM-based automation can streamline knowledge organisation in regulated industries, improving both speed and consistency at scale.