High-performance NoSQL database provider RavenDB Ltd. today announced the launch of AI Agent Creator, a feature fully integrated into the database that it claims reduces the time required to build AI agents from weeks, months or even years to just days.

The new offering helps overcome the issues of artificial intelligence adoption, where embedding agents into workflows and data systems is often too complex for many enterprises. RavenDB’s AI Agent Creator removes the difficulty barrier by running agents natively inside the database, giving developers secure, direct access to operational data.

The idea is that by keeping agents close to the data and automating integration, RavenDB turns months of uncertainty into days of reliable, context-aware AI delivery.

“Consumers can already plan meals, design entire trips, or get advice from AI platforms such as ChatGPT and Gemini in seconds, yet enterprises are still stuck with rigid, scripted chatbots,” said founder and Chief Executive Oren Eini. “Our AI Agent Creator is the missing piece, enabling developers to build fully integrated agents directly within the database, with secure access to live operational data so that they can go from idea to proof of concept in minutes and production-ready agents in a matter of just a few days.”

Differing from scripted bots or AI-assisted chatbots limited to generic knowledge, RavenDB’s AI Agent Creator allows developers to deploy intelligent agents with built-in guardrails. Developers can define the scope in which each agent can operate on behalf of specific users while connecting to existing validation, authorization and business logic.

To give developers even more control, enhance safety and greater precision over how data and operations are accessed, the large language model follows a zero-trust, default-deny approach, where no data or operations are accessible unless explicitly approved.

For end users who send a request in natural language, RavenDB invokes the agent to process the request and communicates the tools and actions it has within the scope defined by the developer. RavenDB then orchestrates the entire flow, referencing existing business logic to perform approved operations.

The result, according to the company, is accurate, personalized responses without ever exposing the full database, moving data to external servers, writing complex code, or compromising security.

The AI Agent Creator supports all LLMs and uses smart caching, summarizing memory and history while also reducing redundant requests for reasoning-intensive tasks. The caching significantly cuts AI spend and optimizes costs without sacrificing accuracy, making it an ideal efficiency tool in agentic AI workflows.

The new AI Agent Creator is available now as part of RavenDB 7.1.

Image: SiliconANGLE/Reve