Mahavir Teraiya | Gagan Chawla

Sr. Resident Solutions Architect | Director of Forward Deployed Engineering
Databricks
Germany

About

Mahavir Teraiya is a Data and AI Thought Leader at Databricks, helping Fortune 500 enterprises scale agentic AI on governed open lakehouses. With more than 15 years of experience across Databricks, AWS, and Zalando, he designed the first GenAI platform in EMEA with adidas, achieving 91% cost savings. A confirmed speaker at Data + AI Summit 2025 and 2026, and a PhD researcher in federated learning, Mahavir brings a rare combination of production experience and academic depth to the intersection of AI agents, data governance, and open architectures.Gagan Chawla is an award-winning Data and AI leader at Databricks, where he leads forward-deployed engineering and delivery across the DACH region. A business and technical leader with more than 18 years of experience spent entirely in data and AI, he has built and scaled data and AI organizations from the ground up – assembling teams of senior industry experts and guiding them from inception to real, measurable value. Gagan spends his days helping enterprises move data initiatives and AI agents from flashy demos into governed, production-grade systems, with work that impacts customer outcomes at global scale. He is also a strong advocate for open-source innovation, providing leadership to multiple Databricks Labs projects. Before Databricks, Gagan held diverse roles at organizations including Mercedes-Benz Research & Development, Teradata, and Infosys. He is a frequent speaker and host on topics related to the realities of operating data and AI at scale.
Linkedin
Talk

Mahavir Teraiya | Gagan Chawla | The Era of Demos Is Over: Engineering Production-Grade AI Agents on Databricks with Unity Catalog, Lakeflow and the Architecture Patterns

AI Agents Governance, Unity Catalog, Open Lakehouse Architecture, Evaluation Pipelines
If multi-agent workflows grew by 327% in four months, why are most engineering teams still stuck deploying zero agents to production? The answer is not more GPUs, better prompts, or bigger models. Databricks’ 2026 State of AI Agents report, based on telemetry from 20,000+ organizations, makes it clear: the bottleneck is engineering discipline. Organizations with governance deploy 12 times more. Those with evaluation frameworks deploy 6 times more. The “Supervisor Agent” pattern accounts for 37% of enterprise deployments. Agents now build 80% of databases and 97% of branches. Processing time drops by 60–80% when agentic workflows work correctly. This is a deep-tech talk for engineers who want the actual architecture, not the pitch deck: The Modern Databricks Stack for Agents (2026 Edition) Unity Catalog everywhere. Managed tables by default. Lakeflow Declarative Pipelines replacing hand-managed Delta Live Tables (DLT). Streaming tables for real-time agent access. Liquid clustering replacing manual partitioning. Predictive optimization automating maintenance. Agent-Aware Data Modeling How AI agents access data differently than dashboards and notebooks. Why a medallion architecture needs an agent-serving layer. How to design schemas that agents can discover, understand, and query safely. Multi-Format Engineering with Iceberg and Delta How Unity Catalog’s Iceberg REST Catalog API — read generally available (GA), write in preview — enables agents to query across engines without duplicating data or policies. The engineering trade-offs between Delta managed tables and Iceberg managed tables. Evaluation Pipelines as Code How to build repeatable, CI/CD-integrated evaluation pipelines using Mosaic AI and Lakeflow that test agent queries, validate outputs, and enforce cost guardrails before every production deployment. Failure Modes and War Stories The $47,000 query. The Cartesian product that crashed a cluster. The agent that leaked PII across dashboards. What broke, why, and the engineering fix. Code-level detail. Real architectures. Built for engineers who ship.