Condé Nast cuts video search time from 250 minutes to 2 minutes using Amazon Bedrock and TwelveLabs Marengo
Condé Nast’s editorial teams spent an average of 250 minutes per task manually searching through 140,000+ videos using only titles and descriptions. This slowed content discovery for brands like Vogue, GQ, and Wired, hurting revenue capture in a fast-moving media environment. The bottleneck stemmed from traditional search tools’ inability to analyze video content beyond metadata.
Key points
- Condé Nast’s video search time dropped from 250 minutes to under 2 minutes per task using TwelveLabs Marengo embeddings on Amazon Bedrock
- System combines video transcripts, audio, and visuals into vector embeddings for intent-based semantic search, reducing manual review by 90%
- Estimated annual savings of $800,000 from productivity gains across 140,000+ videos, with multi-AZ design ensuring uptime
The publisher partnered with AWS’s Generative AI Innovation Center to build a multimodal video discovery system using Amazon Bedrock and the TwelveLabs Marengo embedding model. The solution processes video transcripts, visuals, and audio into vector embeddings, enabling intent-based semantic search. By decoupling embedding generation from search serving, the team scaled the system efficiently. Results include a 99.2% reduction in discovery time (from 250 minutes to under 2 minutes), a 90% drop in manual review effort, and $800,000 in annual savings. The architecture’s high availability and modular design also ensure reliability for daily use.
The story so far
2 episodes →- Condé Nast cuts video search time from 250 minutes to 2 minutes using Amazon Bedrock and TwelveLabs Marengothis story
How Condé Nast built multimodal video discovery with Amazon Bedrock
AWS Machine Learning Blog · 29 September 2026
Loading the full article…
This text was published by AWS Machine Learning Blog and written by Mariah Miller. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Enterprise & Industry
All →- Cyara’s CEO outlines AI agent oversight as a workforce model · 1 src
- Arcana adds institutional portfolio data to Claude’s connectors · 1 src
- Anthropic brings Claude inference to India via Amazon Bedrock · 6 src
- Infor adds industry-specific AI agents to Velocity Suite, citing generic AI gaps · 1 src
- Tech Mahindra trains 12,500+ staff on Google’s Gemini Enterprise agents · 1 src
Comments
via GitHub Discussions