AWS Adapts Its Databases for AI Agents

AWS enriches its existing databases with vector indexing and access to MCP servers for AI use cases. Its head of non-relational databases, Krishnamurthi, emphasizes the conditions under which agents can leverage reliable information.
AWS maintains a common governance for data
AWS is adding features such as vector indexing and access to MCP servers to its existing databases while preserving consistent governance. For Krishnamurthi, rigorous management of the data layer is essential for AI agents to generate value. He emphasizes that the goal is to provide agents with the right information under appropriate governance.
Krishnamurthi highlights several criteria to ensure the reliability of information: governance, accessibility, context, and proximity of data. According to him, agents must quickly access data close to their storage location to reduce friction between storage and action.
Le brief IA que les pros lisent chaque soir
Les 7 actus IA du jour, décryptées en 5 min. Gratuit.
Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.
Choisissez votre rythme
Gratuit · Pas de spam · Désabonnement en 1 clic
AWS retains multiple engines based on applications
AWS has chosen to offer a wide range of specialized database engines rather than relying on a single general-purpose system. This strategy is being tested and expanded as AI agents become major workloads. Krishnamurthi compares this choice to software engineers selecting different data structures based on the problems they need to solve. He believes that AI enables the creation of new experiences and enhances productivity.
Krishnamurthi was interviewed on the Targeting AI podcast. Before leading non-relational databases at AWS, he worked for nearly eight years at Meta, where he was recently in charge of AI infrastructure, and sixteen years at Microsoft.
Brief IA — L'actualité IA en français
L'essentiel de l'actualité de l'intelligence artificielle, décrypté et expliqué chaque jour.