Inference Routing Summit

Agenda AI Frontiers 9:00 AM Welcome and introduction — David Wang and JJ, Tetrate 9:10 AM Opening Remarks — Jeyappragash JJ, Tetrate 9:20 AM Raising the Reliability Floor of ChatGPT with Envoy Gateway —  Delyan Raychev, OpenAI 9:45 AM Google's Approach to Governing and Optimizing Agents Everywhere with Envoy — Vaibhav Katkade, Google 10:10 AM Many Models, Many Clouds, Many Chips: Matching Inference Supply to Demand — Panel with Guido Appenzeller, a16z; James Watters, VMware Broadcom; and Ian Andrews, Groq Nvidia; moderated by David Wang, Tetrate 10:45 AM Morning break Optimizing Inference in the Enterprise 11:00 AM Keynote: What's Important About Inference in the Enterprise — Guido Appenzeller, a16z 11:20 AM Governed by Default: Faster AI Adoption at Box — Sesh Jalagam, Box 11:45 AM From Tokens to Value: Enterprise AI Cost Governance — Milind Pathak, Hitachi America 12:10 PM A Customer Lens on Sovereign AI and Private Inference — Debojyoti Dutta, Nutanix 12:30 PM Safer AI Without Filing a Ticket — John Landa, Tetrate 12:45 PM Lunch Ecosystem and community 1:35 PM Advancing Agentic Inference in the Open — Alex Salkever, Agentic AI Foundation 1:45 PM What's Next in the Ecosystem — Panel with Yan Avlasov, Google; Ignasi Barrera, Tetrate; and Johnu George, Nutanix; moderated by Alex Salkever, AAIF 2:20 PM Tools, Guardrails, Controls: Extending Agent Router — Panel with Soham Ganatra, Composio; Milind Torney, Broadcom; and Vinod Kone, StackTrace; moderated by Matt Baldwin, Tetrate 2:55 PM Afternoon break From Silicon to Inference 3:10 PM Inference optimization from Silicon to Network — David Wang, Tetrate (MC Intro) 3:15 PM Inference at Scale: Smarter Routing for Cost, Quality, and Performance — Panel with Tina Tsou, Bitdeer; Mandar Jog, xAI; Sven Mawson, SambaNova; Moderator: Matt Baldwin, Tetrate 3:45 PM From Cluster to Fleet: Global Inference Routing with Dynamo and Tetrate — Malick Sachal, Nvidia; Varun Talwar, Tetrate 4:15 PM The Right Model for Every Request with Smart Routing — Ian Cairns, Nvidia; Nick DiZazzo, Tetrate 4:30 PM Closing remarks — David Wang, Tetrate 4:35 PM Drinks and networking 6:00 PM End Request to Attend If you're a CTO, VP of Engineering, or head of platform, AI, or infrastructure responsible for building and maintaining an AI stack in production, request access below. The Venue Join us at the The SVB Experience Center: A 120-seat event and networking venue operated by Silicon Valley Bank at 532 Market Street in downtown San Francisco, California. About Tetrate Tetrate runs AI traffic for enterprises and service providers, giving them consistent control everywhere their business operates. Its AI gateway technology translates technical AI requirements into policies the business can govern, such as cost, model capability, customer experience, resilience, and sovereignty, then enforces those policies consistently across every gateway and location the business depends on. Teams remain free to choose the models, providers, agent harnesses, guardrails, and other AI tools that fit their needs while the enterprise maintains central control. For more information, visit www.tetrate.io.