Jeremy (Jezz) Kelway is a Vice President of Engineering at EDB, based within the Pacific Northwest, USA. He leads a team focused on delivering Postgres-based analytics and AI solutions. With experience in Database-as-a-Service (DBaaS) management, operational leadership, and modern technology delivery, Jezz has a powerful background in driving advancements in emerging technologies.
EDB supports PostgreSQL to align with business priorities, enabling cloud-native application development, cost-effective migration from legacy databases, and versatile deployment across cloud environments. With a growing talent pool and robust performance, EDB ensures security, reliability, and superior customer experiences for mission-critical applications.
Why is Postgres increasingly becoming the go-to database for constructing generative AI applications, and what key features make it suitable for this evolving landscape?
With nearly 75% of U.S. firms adopting AI, these businesses require a foundational technology that can allow them to quickly and simply access their abundance of knowledge and fully embrace AI. That is where Postgres is available in.
Postgres is maybe the right technical example of a permanent technology that has reemerged in popularity with greater relevance within the AI era than ever before. With robust architecture, native support for multiple data types, and extensibility by design, Postgres is a chief candidate for enterprises trying to harness the worth of their data for production-ready AI in a sovereign and secure environment.
Through the 20 years that EDB has existed, or the 30+ that Postgres as a technology has existed, the industry has moved through evolutions, shifts and innovations, and thru all of it users proceed to “just use Postgres” to tackle their most complex data challenges.
How is Retrieval-Augmented Generation (RAG) being applied today, and the way do you see it shaping the longer term of the “Intelligent Economy”?
RAG flows are gaining significant popularity and momentum, with good reason! When framed within the context of the ‘Intelligent Economy’ RAG flows are enabling access to information in ways in which facilitate the human experience, saving time by automating and filtering data and data output that may otherwise require significant manual time and effort to be created. The increased accuracy of the ‘search’ step (Retrieval) combined with with the ability to add specific content to a more widely trained LLM offers up a wealth of opportunity to speed up and enhance informed decision making with relevant data. A useful method to take into consideration that is as if you have got a talented research assistant that not only finds the appropriate information but in addition presents it in a way that matches the context.
What are a few of the most important challenges organizations face when implementing RAG in production, and what strategies might help address these challenges?
At the basic level, your data quality is your AI differentiator. The accuracy of, and particularly the generated responses of, a RAG application will all the time be subject to the standard of knowledge that’s getting used to coach and augment the output. The extent of sophistication being applied by the generative model might be less useful if/where the inputs are flawed, resulting in less appropriate and unexpected results for the query (sometimes called ‘hallucinations’). The standard of your data sources will all the time be key to the success of the retrieved content that’s feeding the generative steps—if the output is desired to be as accurate as possible, the contextual data sources for the LLM will should be as up up to now as possible.
From a performance perspective; adopting a proactive posture about what your RAG application is attempting to attain—together with when and where the info is being retrieved—will position you well to know potential impacts. As an example, in case your RAG flow is retrieving data from transactional data sources (I.e. always updated DB’s which might be critical to what you are promoting), monitoring the performance of those key data sources, at the side of the applications which might be drawing data from these sources, will provide understanding as to the impact of your RAG flow steps. These measures are a superb step for managing any potential or real-time implications to the performance of critical transactional data sources. As well as, this information also can provide precious context for tuning the RAG application to deal with appropriate data retrieval.
Given the rise of specialised vector databases for AI, what benefits does Postgres offer over these solutions, particularly for enterprises trying to operationalize AI workloads?
A mission-critical vector database has the flexibility to support demanding AI workloads while ensuring data security, availability, and suppleness to integrate with existing data sources and structured information. Constructing an AI/RAG solution will often utilize a vector database as these applications involve similarity assessments and suggestions that work with high-dimensional data. The vector databases function an efficient and effective data source for storage, management and retrieval for these critical data pipelines.
How does EDB Postgres handle the complexities of managing vector data for AI, and what are the important thing advantages of integrating AI workloads right into a Postgres environment?
While Postgres doesn’t have native vector capability, pgvector is an extension that lets you store your vector data alongside the remaining of your data in Postgres. This permits enterprises to leverage vector capabilities alongside existing database structures, simplifying the management and deployment of AI applications by reducing the necessity for separate data stores and complicated data transfers.
With Postgres becoming a central player in each transactional and analytical workloads, how does it help organizations streamline their data pipelines and unlock faster insights without adding complexity?
These data pipelines are effectively fueling AI applications. With the myriad data storage formats, locations, and data types, the complexities of how the retrieval phase is achieved quickly turn into a tangible challenge, particularly because the AI applications move from Proof-of-Concept, into Production.
EDB Postgres AI Pipelines extension is an example of how Postgres is playing a key role in shaping the ‘data management’ a part of the AI application story. Simplifying data processing with automated pipelines for fetching data from Postgres or object storage, generating vector embeddings as latest data is ingested, and triggering updates to embeddings when source data changes—meaning always-up-to-date data for query and retrieval without tedious maintenance.
What innovations or developments can we expect from Postgres within the near future, especially as AI continues to evolve and demand more from data infrastructure?
The vector database is not at all a finished article, further development and enhancement is anticipated because the utilization and reliance on vector database technology continues to grow. The PostgreSQL community continues to innovate on this space, searching for methods to reinforce indexing to permit for more complex search criteria alongside the progression of the pgvector capability itself.
How is Postgres, especially with EDB’s offerings, supporting the necessity for multi-cloud and hybrid cloud deployments, and why is that this flexibility vital for AI-driven enterprises?
A recent EDB study shows that 56% of enterprises now deploy mission-critical workloads in a hybrid model, highlighting the necessity for solutions that support each agility and data sovereignty. Postgres, with EDB’s enhancements, provides the essential flexibility for multi-cloud and hybrid cloud environments, empowering AI-driven enterprises to administer their data with each flexibility and control.
EDB Postgres AI brings cloud agility and observability to hybrid environments with sovereign control. This approach allows enterprises to manage the management of AI models, while also streamlining transactional, analytical, and AI workloads across hybrid or multi-cloud environments. By enabling data portability, granular TCO control, and a cloud-like experience on a wide range of infrastructures, EDB supports AI-driven enterprises in realizing faster, more agile responses to complex data demands.
As AI becomes more embedded in enterprise systems, how does Postgres support data governance, privacy, and security, particularly within the context of handling sensitive data for AI models?
As AI becomes each an operational cornerstone and a competitive differentiator, enterprises face mounting pressure to safeguard data integrity and uphold rigorous compliance standards. This evolving landscape puts data sovereignty front and center—where strict governance, security, and visibility should not just priorities but prerequisites. Businesses have to know and make certain about where their data is, and where it’s going.
Postgres excels because the backbone for AI-ready data environments, offering advanced capabilities to administer sensitive data across hybrid and multi-cloud settings. Its open-source foundation means enterprises profit from constant innovation, while EDB’s enhancements ensure adherence to enterprise-grade security, granular access controls, and deep observability—key for handling AI data responsibly. EDB’s Sovereign AI capabilities construct on this posture, specializing in bringing AI capability to the info, thus facilitating control over where that data is moving to, and from.
What makes EDB Postgres uniquely able to scaling AI workloads while maintaining high availability and performance, especially for mission-critical applications?
EDB Postgres AI helps elevate data infrastructure to a strategic technology asset by bringing analytical and AI systems closer to customers’ core operational and transactional data—all managed through Postgres. It provides the info platform foundation for AI-driven apps by reducing infrastructure complexity, optimizing cost-efficiency, and meeting enterprise requirements for data sovereignty, performance, and security.
A sublime data platform for contemporary operators, developers, data engineers, and AI application builders who require a battle-proven solution for his or her mission-critical workloads, allowing access to analytics and AI capabilities whilst using the enterprise’s core operational database system.
