Social Department launches culturally aware video retrieval system QuickSearch
Understand this story
Social Department built a video discovery system called QuickSearch on Amazon Bedrock, replacing pure semantic search with four single-step queries—Shareable Scenes, Quotable Quotes, Memeable Moments and Trend Align—that directly return the clips marketers want. According to AWS, the models in the solution run on Amazon Bedrock, and customer data stays within the AWS data boundary, is not shared with model providers and is not used to train the underlying models; every post must be reviewed by the customer's team before publishing. Completed results are stored in Amazon DynamoDB and can be reused for 30 days.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogHow Social Department built culture-aware video discovery
Social Department built QuickSearch, a set of single-action queries (Shareable Scenes, Quotable Quotes, Memeable Moments, and Trend Align) that return clips marketers want without requiring them to describe the moment, using TwelveLabs Marengo and Pegasus, Anthropic's Claude models, and Amazon OpenSearch Serverless on Amazon Bedrock. The system runs content understanding and trend acquisition as independent pipelines joined at request time, and Social Department reports that campaign discovery work which used to take 3–4 days now takes about 10 minutes.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 19 05:00
- Change in the past 24 hours
- -50%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.