OossaAI is evolving fast. We explain it simply.

Condé Nast cuts video search time from 250 minutes to 2 minutes

Using Amazon Bedrock and OpenSearch, the publisher reduced discovery time by 99% and expects $800 K in yearly savings.

NoteOossa1 min read

Condé Nast’s editors now find clips in under two minutes instead of 250 minutes. The change comes from an AI‑driven search tool built with Amazon Bedrock, Amazon OpenSearch Service and TwelveLabs’ Marengo embedding model. The system looks inside video transcripts, visuals and audio to match natural‑language queries. It is already used across Vogue, GQ, Vanity Fair and Wired.

Why it matters

Faster video search lets editors respond quickly to advertisers and repurpose hidden content, saving time and about $800 K each year.

Was this article useful?
Share

Read next

Oossa · Newsletter

The week in AI, explained

Every Monday: the stories worth knowing, in plain language. Free, no spam.

Sources & references

#SourceOutletDateKey takeaway
1How Condé Nast built multimodal video discovery with Amazon Bedrock ↗AWSSep 29, 2026Condé Nast's editorial teams spent an average of 250 minutes per task searching a library of more than 140,000 videos using only titles and descriptions.

1 sources

Last updated: ·Markdown·llms.txt