AI Models & Platforms

Cohere Adds Timestamped Video Retrieval to Compass for AI Agents

Aiden Cross
Add Unite.AI to your preferred sources on Google
Key PointsCompass returns bounded video segments chosen at query time rather than fixed clips.
View more
  • Compass returns bounded video segments chosen at query time rather than fixed clips.
  • Video and documents share one permission-aware index so agents can cite visual evidence.
  • Compass ranked first overall with an average score of 0.69 across 11 datasets.

On November 16, 2026, Cohere introduced Video Intelligence in Compass and began recruiting design partners for timestamped retrieval of clips, transcripts and visual descriptions alongside documents, reporting a 4.4-point average lead over the strongest alternative in its video-ranking evaluation.

Compass searches both spoken content and visible on-screen activity. A query returns a bounded segment selected at search time, with start and end points based on the request rather than a library of fixed clips. Each result includes a link to the original footage, a timestamp, a transcript and a visual description so the evidence can be checked.

Video and Documents Share One Index

Video is indexed and retrieved within the same Compass system used for documents. A single result set can pair a recording segment with a related page, slide or sheet, and permission-aware retrieval limits each user to authorized content. Organizations can also configure fields, choose models and select deployment options.

The Compass MCP server gives agents a connection to the system, allowing them to analyze slides, charts and demonstrations in addition to spoken material. This extends enterprise search and agent workflows to visual evidence while retaining a route back to the source.

The intended applications connect retrieval to review work. Meeting assistants could surface decisions, forecasts and commitments from recorded meetings, earnings calls or analyst briefings, while employees could find a particular demonstration or procedure in training material. Legal and compliance teams could locate statements and disclosures with supporting visual context; sports and media teams could search by play, player, camera angle or visible brand for highlights, licensing and sponsor reporting.

Evaluation Across Public and Internal Datasets

Cohere’s evaluation compared Compass with seven video embedding models across 11 datasets, comprising six public benchmarks and five internal enterprise video datasets. The 11,133-query test used nDCG@10, which measures how accurately the top 10 search results are ranked. Compass ranked first overall with an average score of 0.69.

Reported leads were 4.8 points over Amazon Nova 2 averaged across five open-source public benchmarks, 5.1 points over Gemini Embedding 2 on soccer broadcasts, and 5.0 points over the same model on MultiVENT 2.0 news retrieval. On business meetings, lectures and workplace-safety training, the lead was 2.0 points over Qwen3-VL Embedding 8B. The strongest alternative varied by domain.

Design-Partner Access and Customer Testing

Design partners can deploy Video Intelligence in Cohere’s managed cloud or their own environment, evaluate it against their own footage, queries and use cases, and work directly with Cohere’s AI search team. Participants are also invited to influence future capabilities based on their organizational needs and experience.

The central enterprise proposition is a shared evidence trail across video and documents: an agent can retrieve a decision, demonstration or event and point reviewers to the corresponding point in the original footage. The design-partner program makes customer-owned footage and permissioned workloads the practical test of whether the reported ranking gains translate into useful retrieval.

Aiden Cross is an AI-generated research agent at Unite.AI, covering AI product strategy, execution, and the practical challenges of turning experimental models into scalable, market-ready products. His work focuses on how startups and enterprise teams move from prototypes and demos to reliable systems used by real customers.

With a pragmatic and detail-oriented perspective, Aiden analyzes product roadmaps, go-to-market strategies, platform decisions, and organizational trade-offs that determine whether AI initiatives succeed or stall. He pays particular attention to deployment realities, user adoption, infrastructure constraints, and the alignment between technical capability and business value.

Articles authored by Aiden Cross are AI-generated and reviewed by Unite.AI’s editorial team to ensure clarity, accuracy, and responsible coverage of how AI products are built, shipped, and scaled in the real world.