Vast Data has announced the launch of its new agentic AI application environment, the Vast AgentEngine. This innovation enhances its data management portfolio, which is rooted in its foundational product, the Vast Data Store. The introduction of AgentEngine marks a significant expansion for Vast Data, branching further into data management and AI applications.
The platform will be available in the latter half of 2025 and allows customers to deploy and manage AI agents tailored to specific needs. AgentEngine facilitates the deployment of customizable AI agents capable of interacting with existing storage, database, and messaging systems. Vast Data plans to release a pre-configured agent each month, while also allowing customers the flexibility to build custom agents suited to their operations.
Agents can be equipped with various tools such as directory services, S3 bucket management, search, cataloguing, and functional tools. Users can also assign reasoning models and integrate AI frameworks with built-in guardrails to enhance functionality. At the heart of this innovation lie three core components:
Vast Data Store: High-density, PB-scale storage with storage-class memory optimised for performance and lifespan.
Vast DataBase: A diverse database solution offering SQL, Kafka, Python, and Parquet options. Vast DataEngine: A containerised Python-based layer providing scalable, event-driven computing atop storage functionalities. AgentEngine’s versatility is enhanced by Vast’s DataSpace concept, allowing deployment in both cloud and on-premise environments.
Vast Data extends AI capabilities
Jeff Denworth, Vast’s co-founder, highlighted practical applications of this technology, citing a collaboration with a UK broadcast studio. The studio utilizes a video summarisation tool developed through AgentEngine to monitor and summarise competitor channels without producers having to watch the content manually.
“We’re creating a system that can watch competitors’ channels and summarise them for producers. This way, they don’t need to sit in front of the TV to know what their competitors are doing,” said Denworth. To achieve this, it’s crucial to have reasoning capabilities combined with large video language models.”
By releasing monthly agents, Vast aims to meet the varying needs of different customers.
The development environment is designed to be accessible, utilizing no code/low code tools to make it user-friendly for all customers, regardless of their technical expertise. “We want to encourage adoption by offering development tools that are simple to use,” Denworth explained. Even without extensive expertise, customers can develop solutions that meet about 70-80% of their needs, which is a great starting point.
Vast Data sees the move to agentic AI as a natural extension of its expertise in storage and data management.
Denworth emphasized that their sophisticated infrastructure has always been geared towards advanced applications, with scalable, orchestrated, and database-integrated designs from the start. “Our journey began with a focus on storage, as we knew it was the most critical element to build upon. Now, as AI applications advance, the robustness of our data architecture becomes evident,” Denworth added.
Transactional vector databases are essential for real-time data analysis, a prerequisite for effective AI.
The release of Vast AgentEngine marks a pivotal step in data management evolution, enabling businesses to harness the power of AI in streamlining operations and enhancing decision-making.
Deanna Ritchie is a managing editor at DevX. She has a degree in English Literature. She has written 2000+ articles on getting out of debt and mastering your finances. She has edited over 60,000 articles in her life. She has a passion for helping writers inspire others through their words. Deanna has also been an editor at Entrepreneur Magazine and ReadWrite.
