AWS adds TwelveLabs Marengo 3.0 to Bedrock for managed multimodal retrieval
Multimodal search
Amazon Bedrock Managed Knowledge Base now supports TwelveLabs Marengo 3.0 embeddings for video, audio and image content.
Segment results
Retrieved video results can include segment start and end times so applications can jump to the relevant moment.
Managed pipeline
Developers can upload media from sources such as Amazon S3, sync it and search with natural language without managing retrieval infrastructure.
AWS has added TwelveLabs Marengo 3.0 as an embedding model in Amazon Bedrock Managed Knowledge Base, giving developers a managed way to build natural-language search across video, audio and image archives without assembling separate pipelines for frames, transcripts, vector indexing and retrieval.1
The move expands Bedrock Knowledge Bases beyond text-centered retrieval-augmented generation workflows. AWS said the service already supported media search by transcribing audio and video into text and generating text embeddings. Marengo 3.0 adds multimodal embeddings that encode visual scenes, speech and video cues directly, capturing signals that transcript-only systems can miss.1
For AI application developers, the practical change is architectural. Instead of extracting frames, generating transcripts, choosing embedding models for each modality, storing vectors and mapping search results back to timestamps, teams can upload media assets from sources such as Amazon S3, sync them with Bedrock Managed Knowledge Base and query them in natural language.1
Retrieval-augmented generation systems have typically centered on text: documents are chunked, embedded, stored in a vector index and retrieved to ground model responses. That pattern works well for manuals, web pages, support tickets and knowledge articles. It becomes more complex when the source material is a video library, classroom recording archive, surveillance repository or product imagery collection.
In those settings, developers often need to decide how frequently to sample video frames, how to align speech transcripts with visuals, how to represent images and audio in a shared embedding space, and how to return results that point users to the right moment rather than simply the right file. AWS is positioning the Marengo 3.0 integration as a managed alternative to that custom stack.
According to AWS, Marengo 3.0 generates compact 512-dimensional vectors and supports configurable segmentation options, allowing developers to tune how media is divided based on the structure of the content.1 That matters for applications where retrieval quality depends not only on finding the right video, but also on identifying the relevant clip inside it.
A key feature of the integration is segment-level retrieval. AWS said results include segment start and end times, enabling applications to send users directly to the relevant moment in a video.1
That capability changes the user experience for media search. A security analyst could search for a specific visual event, an educator could locate the portion of a lecture that explains a concept, and a media editor could find a scene type or spoken reference across a large archive. Instead of returning a long file and leaving the user to scrub through it manually, an application can surface the relevant temporal span.
For developers building AI assistants over media assets, segment timestamps can also improve downstream generation. A model can cite or summarize the relevant clip while the application preserves a path back to the original evidence.
AWS cited use cases across sports analytics, media and entertainment, security, education and retail.1 In media organizations, multimodal retrieval can help teams search broadcast footage, production archives or marketing assets by meaning rather than file names or tags. In education, lecture videos can become searchable by topic, example or concept, even when the exact keyword is not spoken.
In security, natural-language retrieval over video could help investigators find events that combine visual and temporal context. In retail, teams could search product imagery, store video or customer-experience recordings to locate scenes, displays or behaviors relevant to operations and merchandising.
The common engineering pattern is the same: large media repositories become searchable through embeddings that represent more than text. By packaging that capability inside Bedrock Managed Knowledge Base, AWS is treating multimodal retrieval as infrastructure rather than a bespoke application layer.
The announcement reduces systems work, but it does not remove application design choices. Developers still need to decide how to organize source media, set segmentation options, govern access to sensitive audio and video, and design user interfaces that clearly expose retrieved clips, confidence signals and source context.
They also need to evaluate retrieval quality for domain-specific content. A retail visual search workflow, a lecture archive and a security investigation tool may require different segmentation strategies, metadata filters and relevance thresholds.
Still, the direction is clear: cloud providers are moving retrieval systems from text-only knowledge bases toward managed multimodal infrastructure. With Marengo 3.0 in Bedrock Managed Knowledge Base, AWS is making video, audio and image search a more native part of the generative AI application stack.1
Microsoft is retiring the preview =COPILOT worksheet function in Excel on September 14, 2026, before it ever reached general availability. The move suggests Microsoft is favoring guided Copilot workflows over embedding generative AI calls directly into spreadsheet formulas.
Extreme Networks has made Agent ONE Coworker generally available to Platform ONE customers, pitching the assistant as a context-aware AI agent grounded in live telemetry, topology and operational relationships. The launch reflects a broader enterprise networking shift: vendors are trying to make AI useful by connecting agents to current network state and history, rather than simply adding chat interfaces to existing dashboards.
Automox says its AI-assisted pipeline can draft and test mitigation Worklets for vulnerabilities that are not immediately patchable, with human review before customer release. The move reflects a broader shift in security tooling: finding CVEs faster is no longer enough if teams cannot safely scope, verify and roll back endpoint changes.
Google is rolling out new Workspace Studio steps that let users automate file movement, file copying, email replies and Google Chat replies inside Workspace. The update broadens Workspace Studio from prompt-driven assistance toward governed cross-app actions that admins can gate through existing controls and AI-related settings.
Retrieval-augmented generation
A technique that retrieves relevant external content and provides it to an AI model so responses can be grounded in source material.
Multimodal embeddings
Vector representations that encode meaning from more than one type of data, such as video, images, speech and text.
Segment-level retrieval
A retrieval method that returns a specific time span inside a video or audio file instead of only returning the full asset.
Vector index
A database or search structure used to store embeddings and find items that are semantically similar to a query.
Comments