December 2025 Summaries

SurrealDB University has introduced a new tutorial designed for learners who prefer project-based learning, expanding the educational offerings to four distinct methods. This new tutorial addresses a gap in the curriculum by enabling students to learn through building, using the last four chapters of "Aeon’s Surreal Renaissance" as a foundation, which had previously been too fast-paced for beginners and potentially spoiled the story. The tutorial guides users in transforming loosely structured JSON data on popular movies into a schema-based SurrealDB instance, complete with graph relations, full-text search capabilities, and user-defined permissions. It provides a comprehensive, step-by-step approach to database building, including the conversion of data types, definition of database parameters, and the creation of user roles, all while encouraging learners to continue developing their projects post-tutorial. The course is structured to be completed in an afternoon or spread over two days for a more relaxed pace, with opportunities for learners to showcase their work and integrate SurrealDB with various programming languages.

In a recent discussion hosted by SurrealDB, CEO Tobie Morgan-Hitchcock and Agno founder Ashpreet Singh explored how Agno's Agent OS and SurrealDB combine to create reliable AI systems with memory capabilities. Agno offers a high-performance multi-agent framework that includes a harness for running language models, a deployable runtime, and a user interface for managing agents, while SurrealDB provides the memory and knowledge layer that enhances the agents' context comprehension. The integration focuses on addressing key challenges in building agent systems, such as ensuring reliability and delivering relevant context, instead of relying on larger context windows. SurrealDB serves as a comprehensive data store that supports structured facts, vectors, graph relationships, and time series, facilitating precise information retrieval that enhances the performance and consistency of AI agents. The collaboration is part of a broader vision to develop reliable, memory-capable agents that can eventually evolve from domain-specific applications to larger, interconnected workflows within organizations.

In a discussion between SurrealDB CEO Tobie Morgan-Hitchcock and PolyAI CTO Shawn Wen, they explore the challenges of deploying context-aware AI agents in enterprise contact centers, particularly for voice interactions where latency and accuracy are critical. The conversation highlights that while technology like RAG (Retrieval-Augmented Generation) isn't the differentiator, engineering disciplines around context, observability, and data ownership are vital. They stress the importance of treating the knowledge base like code, with versioning and governance, to ensure reliable and repeatable outputs. The discussion also underscores the need for enterprises to validate outcomes before heavily investing in centralizing knowledge bases or training their models. PolyAI's upcoming developer platform aims to facilitate the integration of voice and chat agents into existing enterprise systems, emphasizing model-agnostic and integration-first design principles. The session serves as a reminder that in customer support, especially with voice, latency and consistency are more than metrics—they define the user experience.

SurrealDB has joined the NVIDIA Inception Program, a global initiative supporting AI startups, enhancing its position within the NVIDIA ecosystem and accelerating its development of GPU-optimized database technology. This partnership provides SurrealDB with early access to GPU acceleration, significantly improving performance in vector search, graph queries, embedding workflows, and real-time AI workloads. The collaboration offers SurrealDB technical guidance, engineering resources, and advanced GPU tooling, which will enable faster query execution, higher throughput, and efficient edge AI deployments. Additionally, SurrealDB plans to expand GPU-accelerated features with NVIDIA's support, such as edge AI deployments with NVIDIA DGX Spark and deeper CUDA platform integrations, ensuring it remains a robust real-time, multi-model database for AI-native systems.