From the source
- AWS's post describes how Social Department built QuickSearch, four single-action queries that return clips for entertainment marketers without requiring them to describe what they want.
- The problem is that semantic search answers only the question you can articulate, while campaign queries are questions of judgment about which moment will travel.
- QuickSearch offers Shareable Scenes, Quotable Quotes, Memeable Moments and Trend Align, each with its own retrieval strategy, editorial criteria and ranking model.
- Content understanding and trend acquisition run as independent pipelines on their own schedules and are joined only when a user selects an action.
- Social Department owns the pipeline architecture, retrieval system and editorial criteria, while TrackIt implemented and delivered against that design.
- TwelveLabs' Marengo 3.0 and Pegasus 1.2 models on
Amazon Bedrock provide scene-level video reasoning, and AWS supplies the infrastructure, model access including
Anthropic's Claude models, and Amazon OpenSearch Serverless for retrieval.
- The models run on Amazon Bedrock so customer data stays within the AWS data boundary, is not shared with model providers and is not used to train the underlying models.






