# Amazon — How Social Department built culture-aware video discovery

- Company: Amazon (amazon.com)
- Announced: 2026-11-18T19:27:56+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://aws.amazon.com/blogs/machine-learning/how-social-department-built-culture-aware-video-discovery/
- Record: https://forck.live/items/38197-how-social-department-built-culture-aware-video-discovery
- Subject: Bedrock / Nova
- Models affected: Marengo 3.0, Pegasus 1.2, Claude

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.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/how-social-department-built-culture-aware-video-discovery/:

> This post is co-written by Mariah Miller and Sirajus Salekin from AWS and Nicholas Chase from Social Department.
> 
> Entertainment marketing teams manage tens of thousands of video assets across studios, networks, and streaming applications. Most campaigns begin with the same video discovery problem: finding the one moment in the footage that will resonate with an audience. When a brief lands, the clock starts, and what they need is almost never something a database can describe.
> 
> Semantic search, on its own, has a ceiling: It answers the question you can articulate. Ask it for a character holding a coffee mug and it will find every coffee mug in a thousand episodes. The queries that actually drive entertainment campaigns look nothing like that. They are questions of judgment: which moment in a show will travel, which line is quotable, and which single frame will work as a meme.
> 
> Those questions can’t be typed into a search box. Answering them requires two things the search index doesn’t have: an editorial definition of what “quotable” or “memeable” means for a given library, and a continuously refreshed view of what is moving outside the library.

---

Record: https://forck.live/items/38197-how-social-department-built-culture-aware-video-discovery
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
