Live Labs
Short, practical sessions with the people building and applying AI right now.
Loading sessions…
Live Labs
Short, practical sessions with the people building and applying AI right now.
Showing 10 sessions
Build with Jev: System-1 Models in Action
Agentic workflows need decisions at every step: which tool to use, what to prioritize, and when to ask for help. Jev lets you turn those questions into structured outputs your code can use. In this session, you'll build a small request-routing workflow and learn how to handle uncertainty before it triggers the next action.
- Aishwarya Srinivasan
- Arvind Narayanamurthy
Optimizing Open Models for Production
Open models are getting dramatically larger and more capable, which makes serving them efficiently a systems problem of its own. This session explores modern inference techniques used to make state-of-the-art open models practical in production, covering caching, kernels, quantization, speculative decoding, and disaggregated inference, with lessons from the recent Kimi K3 launch and its production-scale vLLM integration.
Sujee ManiyamNebius
Build with rabbit OS3: The OS You Talk To
Jesse Lyu & Aidan Shain
Founder & CEO; Software Developer · rabbit
Build with rabbit OS3: The OS You Talk To
Jesse Lyu and Aidan Shain introduce rabbit OS3 and demonstrate its approach to an agentic operating system. Explore conversational tasks, connected devices, model switching, and the controls that guide actions across the system.
Jesse Lyu & Aidan Shainrabbit
Loop & Harness Engineering Masterclass
Loop and harness engineering is not another AI buzzword. In this masterclass, we move beyond the hype and focus on what it actually takes to build agents that work through tasks reliably. You’ll see how thoughtful loop design and the system around it can turn a promising demo into something capable of handling real work.
- Aishwarya Srinivasan
- Arvind Narayanamurthy
AI Tokenomics Explained
Haritha Thilakarathne explains the economics of AI tokens, connecting demand and supply with inference efficiency and monetization. Explore how these factors influence capacity, operating costs, and sustainable scaling.
Haritha ThilakarathneNVIDIA
Secure AI Agents: Identity, Secrets & Access in Production
Mariane Bekker
Director of Developer Relations · 1Password
Secure AI Agents: Identity, Secrets & Access in Production
Mariane Bekker explores how to protect production AI agents as they connect to business systems. Learn to manage agent identities, restrict access, safeguard credentials, and secure tool connections.
Mariane Bekker1Password
Inside LinkedIn: Building AI Products at Global Scale
Tim Jurka
VP of Consumer Products · LinkedIn
Inside LinkedIn: Building AI Products at Global Scale
Tim Jurka shares a leadership perspective on developing AI-powered consumer experiences at LinkedIn, where product decisions must work across a large professional network and multiple engineering disciplines.
Tim JurkaLinkedIn
Figma MCP vs. Paper MCP: What Evals Actually Tell You
Jessica Wang
Developer Advocate · Braintrust
Figma MCP vs. Paper MCP: What Evals Actually Tell You
Jessica Wang compares Figma and Paper MCP workflows to show how explicit tasks, representative datasets and scoring criteria turn AI-tool selection into a repeatable evaluation.
Jessica WangBraintrust
Deploying Sovereign AI Agents in the Enterprise
Siva Surendira examines deployment choices for organizations that need control over AI data and infrastructure, including isolated environments and governance across existing agent systems.
Siva SurendiraLyzr AI
Fireside Chat with Chris Taylor, VP & Fellow at Google
Christopher Taylor
VP and Engineering Fellow · Google
Fireside Chat with Chris Taylor, VP & Fellow at Google
Christopher Taylor discusses enterprise adoption of AI, the importance of context and data infrastructure, and how graph-based approaches and agent workloads change the engineering tradeoffs.
Christopher TaylorGoogle