Every year, the Azure Cosmos DB Conf provides a behind-the-scenes look at how modern applications are built—not in theory, but at global scale in production. In 2026, the dominant theme was unmistakable: artificial intelligence is no longer just another workload. It is fundamentally transforming the way applications—and the data platforms that power them—are architected.
In the opening keynote, Kirill Gavrylyuk, Vice President of Azure Cosmos DB, outlined three major shifts that are driving this change. These shifts were echoed in virtually every customer story shared at the event, from startups to enterprises operating at planetary scale.
The Three Key Shifts Driving AI-Powered Applications
These shifts represent a new paradigm for building data-intensive, intelligent apps. They demand a rethinking of database design, developer workflows, and query capabilities.
Shift 1: Flexible, Semi-Structured Data Becomes Foundational
AI applications don’t operate on rigid schemas. They rely on prompts, memory, and context—all of which are inherently semi-structured and evolve over time. This fundamentally changes how databases must behave.
Data platforms are no longer just systems of record; they are becoming systems of reasoning. Flexibility is no longer optional—it is critical for applications to learn, adapt, and generate outcomes effectively. Azure Cosmos DB’s schema-agnostic design enables developers to store and query diverse data shapes without predefined models, making it ideal for AI workloads that require constant iteration.
Shift 2: AI Accelerates Development Velocity
AI—especially coding agents—is changing how software is built. Developers today are iterating faster, shipping more frequently, and scaling from zero to massive usage almost instantly.
As Kirill emphasized, developers can no longer be constrained by strict schemas. Flexibility isn’t just a convenience—it’s what enables teams to move at AI speed. Databases need to meet this demand with a serverless form factor, instant and limitless scalability, advanced integrated caching, and agent-friendly interfaces. Azure Cosmos DB delivers these capabilities, allowing teams to focus on innovation rather than infrastructure management.
Shift 3: Semantic Search as a First-Class Query Operator
The third shift is equally transformative. AI applications require vector search, full-text search, hybrid search, and semantic ranking. These are no longer “add-ons”; they are core to how modern applications function.
Across Cosmos DB Conf, a clear pattern emerged: teams are building applications where retrieval, reasoning, and real-time context are tightly integrated. Azure Cosmos DB now natively supports these capabilities, enabling developers to combine traditional queries with semantic search in a single, unified platform.
Real-World Impact: OpenAI’s Approach at Planet Scale
These shifts are most visible in what organizations like OpenAI are building. Speaking at the conference, Jon Lee from OpenAI shared how they are operating at massive scale—processing trillions of transactions and petabytes of data. His key message resonated deeply: what matters most is not just scale, but the ability to evolve quickly.
Jon outlined three critical requirements for modern systems:
- Instant scalability – the ability to scale from zero to millions of queries per second and from zero bytes to petabytes of data without friction.
- Schema-less design – enabling rapid onboarding of new data sources and use cases without lengthy schema migrations.
- Parallel development – allowing thousands of developers to iterate simultaneously on the same data platform.
“The most important thing… is being able to scale from zero to millions of QPS, being able to scale from zero bytes to petabytes,” Jon noted, highlighting that flexibility and speed are non-negotiable in the AI era.
Embracing the New Paradigm with Azure Cosmos DB
To succeed in this new landscape, developers need a database that aligns with AI-native development patterns. Azure Cosmos DB provides:
- Serverless form factor – automatically scales up or down based on demand, eliminating capacity planning.
- Instant, limitless scalability – handles unpredictable traffic spikes without manual intervention.
- Advanced integrated caching – reduces latency for real-time AI interactions.
- Agent-friendly interfaces – supports REST APIs, SDKs, and direct integration with AI orchestrators.
- Unified query capabilities – combines vector, full-text, and hybrid search in a single query engine.
The three shifts from Cosmos DB Conf are not just trends; they represent a fundamental evolution in application architecture. As AI continues to accelerate development and redefine data requirements, Azure Cosmos DB is positioned to be the data platform that powers the next generation of intelligent applications.
To dive deeper into these capabilities, explore flexible data design, accelerated development, and semantic search with Azure Cosmos DB today.