The talk archive.

Serving 2 Million Models Without Melting: Scaling the Hugging Face Hub

Arek Borucki

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

Serving Voice AI at $1/hr: Open-source, LoRAs, Latency, Load Balancing

Neil Dwyer · Jack Dwyer

Vision and video · Speech and audio · Infrastructure and deployment

Serving Voice AI at Scale — Arjun Desai (Cartesia) & Rohit Talluri (AWS)

Arjun Desai · Rohit Talluri

Vision and video · Speech and audio · Infrastructure and deployment

Shift Left: How to Become an AI Engineer from a Full-Stack Background

Reid Mayo

Evals · Architecture · APIs, MCP, and protocols

Ship Agents that Ship: A Hands-On Workshop for SWE Agent Builders

Kyle Penfound · Jeremy Adams - Casañas

Observability and reliability · Agent engineering · Coding and developer tools

Ship it! Building Production-Ready Agents

Mike Chambers

Architecture · Reasoning and models · APIs, MCP, and protocols

Ship Production Software in Minutes, Not Months

Eno Reyes

Coding and developer tools · Reasoning and models · Developer workflows and testing

Ship Real Agents: Hands-On Evals for Agentic Applications

Laurie Voss

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

Shipping AI That Works: An Evaluation Framework for PMs

Aman Khan

RAG, context, and search · Leadership · Evals

Shipping AI to a Million Patients Without an A/B Test

Jared Joselowitz

Healthcare · Safety and governance

Shipping an Enterprise Voice AI Agent in 100 Days

Peter Bar

Observability and reliability · Speech and audio · RAG, context, and search

Shipping complex AI applications | Braintrust & Trainline

Giran Moodley · Mayan Soni · Oussama Hafferssas · Mayank Soni

APIs, MCP, and protocols · Developer workflows and testing · Reasoning and models

Shipping Products When You Don’t Know What they Can Do

Ben Stein

Evals · Agent engineering · Enterprise

Shipping something to someone always wins

Kenneth Auchenberg

Enterprise · APIs, MCP, and protocols

Simulation-Maxxing: How Nubank ships agents 20× faster with simulations

Shreya Rajpal · Aman Gupta

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

Skill Issue: How We Used AI to Make Agents Actually Good at Supabase

Pedro Rodrigues

Coding and developer tools · Evals · Agent engineering

Skill issue: Lessons from skilling up coding agents to use Langfuse

Marc Klingen

Coding and developer tools · RAG, context, and search · Evals

Skills are new features: Building Skill-Centric Harness — Yogendra Miraje, FactSet

Yogendra Miraje

Agent engineering · Enterprise · Finance

Skills are the New SDKs

Elvin Aghammadzada

APIs, MCP, and protocols · RAG, context, and search · Safety and governance

Skills at Scale

Nick Nisi · Zack Proser

Agent engineering · Enterprise · APIs, MCP, and protocols

Small AI Teams with Huge Impact — Vik Paruchuri, Datalab

Vikas Paruchuri

Leadership · Enterprise · RAG, context, and search

Small Bets, Big Impact: Building GenBI at a Fortune 100

Asaf Bord

Enterprise · Leadership · Infrastructure and deployment

Software Development Agents: What Works and What Doesn't

Robert Brennan

Coding and developer tools · Developer workflows and testing

Software Engineering + AI = ?

Gergely Orosz · swyx

Enterprise · Coding and developer tools · Leadership

Software Engineering Is Becoming Plan and Review

Louis Knight-Webb

Observability and reliability · Architecture · Coding and developer tools

Sovereign Escape Velocity: Ownership with Open Models — Gus Martins and Ian Ballantyne, Google DeepMind

Gus Martins · Ian Ballantyne

Coding and developer tools · Reasoning and models · Infrastructure and deployment

Spec-Driven Development: Agentic Coding at FAANG Scale and Quality — Al Harris, Amazon Kiro

Al Harris

Infrastructure and deployment · Coding and developer tools · APIs, MCP, and protocols

Spec-Driven Testing for Agents With A Brain the Size of A Planet — Steven Willmott, Safe Intelligence

Steven Willmott

Reasoning and models · Evals · Agent engineering

Special topics in Kernels, RL, Reward Hacking in Agents

Daniel Han

Evals · Safety and governance · Infrastructure and deployment

Spreadsheets-are-all-you-need: Decoding the Decoder LLM without de code

Ishan Anand

Reasoning and models · Architecture · RAG, context, and search

State of Data

Sean Cai

Enterprise · Agent engineering · Infrastructure and deployment

State of Startups and AI 2025

Sarah Guo

RAG, context, and search · Leadership · Coding and developer tools

State of the Union: Why Local, Why Now

Nader Khalil · Alex Cheema · Matthew Berman · Ahmad Osman · Joseph Nelson

Vision and video · Infrastructure and deployment · Leadership

State Space Models for Realtime Multimodal Intelligence

Karan Goel

Vision and video · Architecture · Speech and audio

Stateful Agents — Full Workshop with [REDACTED:username] Packer of Letta and MemGPT

Developer workflows and testing · RAG, context, and search · Coding and developer tools

Stateful environments for vertical agents — Josh Purtell, Synth Labs

Josh Purtell

RAG, context, and search · Enterprise · Evals