RavenDB has unveiled its AI Agent Creator, a new feature in its NoSQL document database that enables developers to build and deploy AI agents instantly by integrating with the database to get direct access to operational data.
Seamless AI integration with built-in security controls
Now available as part of RavenDB 7.1, the company says the AI Agent Creator “turns months of uncertainty into days of reliable, context-aware AI delivery.”
The feature enables developers to deploy intelligent agents with built-in guardrails, providing them with full control over each agent’s scope of operation. The large language model (LLM) also follows a zero-trust, default-deny model, ensuring that no data or operations are accessible unless explicitly approved.
With each LLM request, the RavenDB agent communicates the tools and actions allowed within its defined scope. RavenDB then orchestrates the entire flow and leverages existing business logic to perform the operations. According to the company, this approach helps deliver personalized, data-driven responses without exposing the full database.
The AI Agent Creator also utilizes smart caching to enhance efficiency, minimizing redundant requests for reasoning-intensive tasks and summarizing agent memory and history to reduce costs.
Closing the consumer-enterprise AI gap
Oren Eini, chief executive officer and founder of RavenDB, noted that while consumer AI platforms like ChatGPT have developed to be versatile tools for everyday users, enterprises are still relying on AI solutions that remain “rigid, scripted chatbots.” Eini positioned the new feature as a direct answer to this gap.
“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,” he said.
RavenDB is an open-source, hybrid NoSQL document database designed for modern application development. Developed by Hibernating Rhinos, it has been adopted by more than 1,000 companies worldwide.
While AI agents are gaining traction in the enterprise space, they are also raising concerns as potential new attack surfaces. Security firm Radware has warned of the risks they pose, particularly as existing controls struggle to keep pace.