How Condé Nast built multimodal video discovery with Amazon Bedrock
Condé Nast cut video discovery time from 250 minutes to under 2 minutes using multimodal AI search
Condé Nast and AWS built a multimodal video search system over 140,000+ videos using TwelveLabs Marengo embeddings on Amazon Bedrock, achieving a 125x reduction in content discovery time. The architecture decouples embedding ingestion from low-latency query serving, with OpenSearch handling vector retrieval and natural language converted to timestamp-precise results. This is a concrete enterprise case study showing multimodal AI delivering measurable operational ROI in media publishing.