AI Engineer

Security Track Intro — Randall Degges, Snyk

AI’s Jurassic Park Period — Aaron Stanley, dbt Labs

In the Land of AI Agents, the Verifiers Are King — Tariq Shaukat, Sonar

Why Your Agent Disagrees With Itself (And What To Do About It) - Diane Lin, Datadog

Don't Let the LLM Drive - Ornella Bahidika & Joel Allou, Microsoft

Your Voice Agent Doesn't Need a Frontier Model - Joel Allou & Ornella Bahidika, Microsoft

Enterprise Agents Have a Structure Problem - Ishita Daga, Tesla

When Agents Meet Physical Data: The Other Physics of Agent Harnesses - Dmitry Petrov, DataChain

Build the AI GTM Agent That Knows the Buyer - Dr. Sajjan Kanukolanu, Position2 (Position Squared)

Agents Need Receipts, Not More Tool Calls - Armanas Povilionis, Alithea Bio

Agent Output Is Not UX: Rendering Layer Your LLM Pipeline Is Missing - Bala Ramdoss, Amazon Lens

Building effective user experiences for agentic AI requires shifting focus from the model itself to the delivery layer between the AI and the human interface. Rather than relying on raw text, developers should implement generative UI patterns where models output structured data that clients render using native componen...

Voice Agents That Handle Interrupts - Chintan Agrawal and Daniel Wirjo, AWS

Skills are the New SDKs - Elvin Aghammadzada, DataRobot

Medic for Apache Spark - First Aid for Failing Jobs - Drasko Profirovic, Pinterest

Can Oncology Workflows Run Without Human Touch? - Anant Shankhdhar, Risa Labs

Full Workshop: Setting Yourself Up for Success —Jason Liu, OpenAI Codex

Jason Liu demonstrates advanced workflows for the Codex application, focusing on personal automation, memory management, and agent orchestration. By leveraging features like "AppShots," which captures both visual and accessibility data, users can automate complex tasks such as document signing, email management, and cr...

From Tokens to Cells: Foundation Models for Single-Cell Biology - Akram Baharlouei, Altos Labs

You Didn't Ship a Bug. You Just Wrote It for a Human. - Ravi Madabhushi, Scalekit

From Blind Spots to Merged PRs: Continuous Agentic Performance Optimization - May Walter, Hud

Build Evals That Actually Matter - Nick Ung & Akshay Sharma, Lyft