The talk archive.

Production software keeps breaking, and it will only get worse. Here's how Traversal is fixing it.

Anish Agarwal · Matthew Schoenbauer

Coding and developer tools · Observability and reliability · Reasoning and models

Productionizing GenAI Models – Lessons from the world's best AI teams

Lukas Biewald

Data and model adaptation · Enterprise · Infrastructure and deployment

Prompt Engineering & AI Red Teaming

Sander Schulhoff

RAG, context, and search

Prompt Engineering is Dead

Nir Gazit

RAG, context, and search · Evals

Prompt Engineering Tactics

Dan Cleary

RAG, context, and search · Infrastructure and deployment

Prototyping as Leadership: How a CTO Ships with AI Agents

Hursh Agrawal

Data and model adaptation · Architecture · Leadership

Pydantic is STILL all you need

Jason Liu

Developer workflows and testing · Reasoning and models · Other / unclassified

RAG and the MongoDB Document Model

Ben Flast

Infrastructure and deployment · RAG, context, and search

RAG at scale: production-ready GenAI apps with Azure AI Search

Pablo Castro

RAG, context, and search

RAG Evaluation Is Broken! Here's Why (And How to Fix It)

Yuval Belfer · Niv Granot

Finance · RAG, context, and search · Evals

RAG for VPs of AI

Jerry Liu

RAG, context, and search · Leadership · Architecture

RAG in 2025: State of the Art and the Road Forward

Tengyu Ma

RAG, context, and search · Coding and developer tools

RAG is dead, right?? — Kuba Rogut, [REDACTED:username]

Coding and developer tools · RAG, context, and search

Ralph Loops: Build Dumb AI Loops That Ship

Chris Parsons

APIs, MCP, and protocols · Agent engineering · Coding and developer tools

Reachy Mini: the $300 open source robot you can actually hack — Andres Marafioti, Hugging Face

Andres Marafioti

Robotics and world models · Speech and audio

Real AI Agents Need Planning, Not Just Prompting

Yuval Belfer

APIs, MCP, and protocols · Agent engineering · Architecture

Real ROI: Lessons from Enterprises that Have already succeeded with LLMs [REDACTED:username] Scale

Raza Habib

Leadership · RAG, context, and search · Infrastructure and deployment

Real-time Experiments with an AI Co-Scientist

Stefania Druga

Other / unclassified · Industry applications · Robotics and world models

Real World Development with GitHub Copilot and VS Code — Harald Kirschner, Christopher Harrison

Harald Kirschner · Christopher Harrison

Agent engineering · Coding and developer tools · APIs, MCP, and protocols

Real world MCPs in GitHub Copilot Agent Mode

Jon Peck

Coding and developer tools · APIs, MCP, and protocols · Vision and video

Realtime Conversational Video with Pipecat and Tavus — Chad Bailey and Brian Johnson, Daily & Tavus

Chad Bailey · Brian Johnson

Speech and audio · Agent engineering · Vision and video

Realtime multiplayer, automation, and you!

Idan Gazit

RAG, context, and search · Safety and governance · Agent engineering

Recsys Keynote: Improving Recommendation Systems & Search in the Age of LLMs

Eugene Yan

Architecture · RAG, context, and search · Speech and audio

Recursive Coding Agents

Raymond Weitekamp

Coding and developer tools · Reasoning and models · RAG, context, and search

Recursive Model Improvement

Lee Robinson

Data and model adaptation · Infrastructure and deployment · Coding and developer tools

Reinforcement Learning without Verifiable Rewards — Will Brown, Prime Intellect

Will Brown

Coding and developer tools · RAG, context, and search · Safety and governance

remobi.app: Don't change your terminal workflow for mobile

Connor Adams

Infrastructure and deployment · Enterprise · Coding and developer tools

Remote MCPs: What we learned from shipping — John Welsh, Anthropic

John Welsh

Safety and governance · APIs, MCP, and protocols

Replacing 12K LoC with a 200 LoC Skill

David Gomes

Developer workflows and testing · Coding and developer tools · Evals

Research to Reality: Bringing frontier ML research to production

Vaidas Razgaitis

Architecture · Coding and developer tools · Vision and video

Research to Reality with Google DeepMind

Benoit Schillings

Coding and developer tools · Other / unclassified · Reasoning and models

Respect The Process

Andrew Dumit

APIs, MCP, and protocols · Coding and developer tools · Evals

Rethinking Environments for Long Horizon Work

Rayan Garg

Evals · Observability and reliability · Reasoning and models

Rethinking Team Building: How a 30-Person Startup Serves 50 Million Users — Grant Lee, Gamma

Grant Lee

Leadership · Enterprise

Retrieval Augmented Generation in the Wild

Anton Troynikov

Architecture · RAG, context, and search

Revenue Engineering: How to Price (and Reprice) Your AI Product

Kshitij Grover

Infrastructure and deployment · Safety and governance · Enterprise