Joyce Zhang & Carole Robin, Ph.D.

Human Connection in the Age of AI

Sonar & Extend AI

Expo Welcome Speech

Pamela Fox

Get Started with Models in Microsoft Foundry to Build AI Apps

Gustavo Cordido

From zero to deployed on Azure with AI agents

Pamela Fox

Observe, optimize and protect your hosted agents in Microsoft Foundry

Laurie Voss

From Vibes to Production: Evaluating and Shipping AI Agents That Work 101

Fuad Ali

Building self-learning loops for your agent

Tejas Kumar

Evals in AI: A Deep Dive

Ankur Duggal

Let your agent cook: using skills to evaluate and improve your app

Laurie Voss

From Vibes to Production: Evaluating and Shipping AI Agents That Work 201

Ang Li

The Autonomous Computer: Full-stack Infrastructure for Computer Use Agents

Zach Blumenfeld

AI on Your Lakehouse: Context Comes in Shapes, Not Queries

Nyah Macklin

RAG Needs a Map: Using GraphRAG to Retrieve Connected Context

John Craft & Dan Ndombe

From approval loops to autonomous agents with Docker

Yoni Michael & Brandon Callender

The Data Context Layer: Why Data Engineering Agents Need More Than Code and Databases

Paul Bakaus

The Dark Arts of Skill Engineering

Charlie Guo & Gabriel Chua

Cooking with Codex

Matt Brockman

How I learned to stop worrying and love the sandbox

Harshul Jain & Tanmay Sah

2 hr deep dive on LLM Inference at Scale — Part 1 of 2

Harshul Jain & Tanmay Sah

2 hr deep dive on LLM Inference at Scale — Part 2 of 2

Daniel Han

Special topics in Kernels, RL, Reward Hacking in Agents

Shane Wolf & Andrei Bocan

The best SDLC is the one you build yourself: Why orchestration changes everything

Pamela Fox & Arun Sekhar

The model swap workshop

Kent C. Dodds

Build the Right Thing: Product Engineering for Software Developers (Part 1)

Kent C. Dodds

Build the Right Thing: Product Engineering for Software Developers — Part 2

Mark Lummus & Navinkumar Patil

Burn your flags: How PayPal designs interactive CLI tools for agents

Shubhankar Srivastava

Hill-climbing Skills: How to Improve Agents Without Touching the Model

Javier Garza

AI Security Engineer Foundations + Certificate

Dhruv Nathawani

Teaching Agents to Search: Building Synthetic Training Pipelines with NVIDIA Data Designer

Wolfram Ravenwolf

From Zero to Leaderboard: Building an End-to-End AI Agent Evaluation Pipeline

Michael Forrester & Whitney Lee

Build a Platform, Unleash an Agent on it.... and Watch it Burn!

Micah Silverman

AI Security Engineer Foundations + Certificate

Bereket Habtemeskel & Paola Estefania

Agent Auth

Ignacio Martinez

Total Recall: Agent Memory and Harness Engineering

Ahmad Osman

Local LLMs and workstation agents: Part 1

Ahmad Osman

Local LLMs and workstation agents: Part 2

Killian Carlsen-Phelan

SonarQube + OpenAI: Wiring Your Team for Agentic Development

Louis-François Bouchard & Samridhi Vaid & Omar Solano

Context Engineering in 2026: Compaction, Memory & Cost

Will Brown

The Prime Intellect Stack

Du'an Lightfoot

Agents That Own Their Inference: Building Production AI Agents on Dedicated GPUs

Nnenna Ndukwe

How to Build Quality Gates into Agentic Coding Workflows

Peter Werry

Beyond RAG: Build a Relational Context Engine from Scratch

Palak Agarwal

How Reducto parsed the Epstein Files for the Viral JMail Project: The Secret Complexities of Document

Jeff Vestal

Vector Isn't Enough: Hybrid Search & Retrieval for AI Engineers

Nick Nisi & Zack Proser

Lifestyles of the AI-Native: Voice-coding, agent skills, hooks and scheduled tasks

Zain Hasan & Yubo Wang & Qingyang Wu & Jue Wang

Open-Source Inference Engineering for the Agentic Era

Charles Frye

What is an Inference Engine, Anyway?

Yohan Raju

Building AI Agents with Real-Time Web Data

Filip Makraduli

Turning My Obsidian Vault Into a Local AI Engineer

Emile Baizel & Shruti Arora

Build with Perception Agents

Joel Hooks

The Art and Science of Loopcraft with Pi (and friends)

Doug Ghutrie

Advanced workshop: Mastering AI Observability

Elizabeth Fuentes Leone & Sandhya Subramani

Agent Speedrun: Idea → Code → Deploy → Observe, Fix → Ship

Paige Bailey

Research to Reality with Google DeepMind

Lotte Verheyden & Annabell Schäfer

Continuously improving agents with Langfuse

Zhengyao Jiang & Dixing Xu & Vayum Arora & Dhruv Srikanth

Hands-on AutoResearch: Cracking OpenAI's Parameter Golf

Gagan Bhat & Isabella Kai He

Evolution of agentic surfaces

Idan Gazit

Build agents fast with GitHub Copilot (from idea to working app)

Pamela Fox

Use Copilot across CLI, dev, and cloud workflows to move faster end-to-end

Salil Subbakrishna

Modernize CI/CD using agent-assisted workflows that reduce manual debugging

Maria Bledsoe

Using AI tools to teach old apps new tricks

Harald Kirschner

Surviving Your Own Velocity: How VS Code Ships Weekly with 40 People

Ryan Dahl

Security Firewall for Agents

Vinoth Govindarajan

Your Agent Didn’t Fail. Your Harness Did.

Benjamin Guo & Rob Cheung

Everyone Gets A Software Company

Shu Fang

Tethered: Our Agents Are Us

Jean-Denis Greze

Agents' next frontier: agent-to-agent and network effects

Lance Martin

Claude for long-horizon tasks

Karan Vaidya

From coding to Knowledge work agents

Tanmai Gopal

Your company brain will leak secrets. Here's how we stopped it for big banks and ourselves.

Sam Bhagwat

Every Harness Will Become A Claw

Kenton Varda

Gadgets: Personal app vibe coding that is actually safe

Joseph Nelson

The State of Vision

Jerry Liu

Building the Document Context Layer for AI Agents

Merve Noyan

Skill issue: stop deploying vision language models, use them with Skills to build e2e vision apps on edge

Aditya Gautam

Modality Misalignment and Originality Attribution in Short-Form Video: A Multi-Agent Approach at Platform Scale

Adit Abraham

From Ingestion to Agents: How Leading AI Teams Build on Document Intelligence

Andrew Dai

The Best Models Still Reason Like Toddlers

Cody Menefee

You’re Not Thinking Big Enough: Rebuilding Food Systems from First Principles with AI Agents

Armen Aghajanyan

From VLM/VLA's to Embodied Agents

Krishna Prasad Srinivasan

From Scratch to SOTA: Training a 3B State-Space Vision Model for 1.4 Billion People

Edo Liberty

Pinecone 2.0

Jo Kristian Bergum

The unreasonable effectiveness of BM25 for agentic search

Will Bryk

The Search Engine for the Agentic Web

Liad Yosef

Rebuilding the web for agents

Benjamin Clavié

If we want them to do Knowledge Work, we need to design Knowledge Agents

Hiral Shah & Sean Sodha

Your Agreements Are a Database You Can't Query. We're Fixing That

Simon Eskildsen & Jacob Lauritzen

How to Connect AI to Billions of Legal Documents

Maximilian-David Rumpf & Lotte Seifert

Where RL Will Take Search

Yuval Belfer & Niv Granot

Stop Chunking Like It's 2022

Priyanka Phatak & Gabriel Cemaj

Claude Managed Agents Workshop (Part 1)

Priyanka Phatak & Gabriel Cemaj

Claude Managed Agents workshop (Part 2)

Priyanka Phatak & Gabriel Cemaj

Claude Managed Agents workshop (Part 3)

Priyanka Phatak & Gabriel Cemaj

Claude Managed Agents workshop (Part 4)

Neil Zeghidour

Everybody Gets a Digital Clone! (Part 1 of 3)

Neil Zeghidour

Everybody Gets a Digital Clone! (Part 2 of 3)

Neil Zeghidour

Everybody Gets a Digital Clone! (Part 3 of 3)

Jason Liu

Setting Yourself Up for Success — Part 1

Jason Liu

Setting Yourself Up for Success — Part 2

Jason Liu

Setting Yourself Up for Success — Part 3

Manoj Nair

Through the AI Fog: The architectural decision the next 24 months of agentic security depends on.

Lovina Dmello

Your LLM Stack Is a 2008 Database With Better Marketing: Why ML Security Is Dominated by Misconfiguration, Not Missing Features

Moritz Johner

We Gave an Agent Production Code Access and Then Tried to Sleep at Night

Ezra Tanzer

Agentic Development Security

Eugene Yan

Using LLMs to Secure Source Code

Ethan (Jung Min) Cha

Dual-Surface Architecture: Serving Humans and Agents from the Same Tool Layer

Steve Yegge

Agentic Security: Permissions, Provenance, and the Agent Supply Chain

Kim Maida

It's 10pm. Do You Know Where Your Agents Are?

Aaron Stanley

AI’s Jurassic Park Period

Ethan Sutin

Secure Cloud Compute

Kwindla Kramer

The New Primitives: Building AI-Native Software

Valeria Wu Fon & Tom Ouyang

Speech-to-Speech Model Research at Google DeepMind

Charlie Guo

Voice Agents Can Just Do Things

Neil Zeghidour

Your Voice Agent is Just a Walkie-Talkie

Paula Dozsa

Tolan: Voice-First AI Companion

Venky B & Vyas A

5 Voice Agent Failure Modes You'll Hit in Week One

Sumanyu Sharma

I Monitored Crime Audio. Voice Agents Scare Me More.

Bohan Li

Realtime Voice Agents with Frontier Intelligence

Midam Kim

"My name is... my name is...": A Linguistic Map for Building and Debugging Voice Agents

Amit Desai

Act, Confirm, or Stop? Smarter behavior for AI assistants, wearables & robots

Devansh Tandon

Tokens In, Engagement Out: Training LLM-Recommenders

Jacqueline Wood & Yves Raimond

Spotify LLM Recsys

Raghav Saboo

LLM Recsys at DoorDash

Devansh Tandon

Open Q&A: LLM Recsys

John Craft

From approval loops to autonomous agents with Docker pt1

John Craft

From approval loops to autonomous agents with Docker pt2

John Craft

From approval loops to autonomous agents with Docker pt3

John Craft

From approval loops to autonomous agents with Docker pt4

John Craft

From approval loops to autonomous agents with Docker pt5

Eno Reyes

How Forward Deployed Engineering is done at Factory

Pauline Brunet

How Forward Deployed Engineering is done at Cursor

Vasuman Moza

AI tools for Forward Deployed Engineering

Jia Wu

How Forward Deployed Engineering is done at Cognition

Natalie Meurer

The Dirty Secret of Forward Deployed Engineering

Sunny Rekhi

How Forward Deployed Engineering is done at Decagon

Leo Mehr

How Forward Deployed Engineering is done at Ramp

Kevin Bai

Forward Deployed Engineering 101

Vinoo Ganesh

How Forward Deployed Engineering is done at Kepler

Ari Morcos

Data Quality is the Compute Multiplier

Robert McHardy & Marah Abdin

The Messy Reality of Scale: Synthetic Data and Pre-Training at Poolside

Rayan Garg

Rethinking Environments for Long Horizon Work

David Brumley

Bugcrowd posttraining talk

Varun Singh

The Base Model is Dead

Thais Castello Branco

Ending AI Slop

Ross Taylor & Chengxi Taylor

Scaling to Long-Horizons: Algorithms, Environments, Compute

Nick Heiner

When Will The Benchmaxxing Plague End?

Nicolai Ouporov

Building Worlds for Models

Mahesh Sathiamoorthy

Data and Environment Curation for Post-training LLMs

Dor Sasson

Every AI company is accidentally building a bank.

Owen Halpert

Give your coding agents the power of turbogrep!

Dat Ngo

Your Agent Is Lying to You About Whether It Worked

Vlad Luzin

Every Agent, Everywhere, All at Once

Jim Clark

Who Approved That MCP Server? Governing the Tool Layer

Marina Petzel

Beyond Golden Signals: Monitoring in the Age of GenAI

Varun Krovvidi

6 Pillars of an Agentic Harness That Fixes Production Incidents

Thor 雷神 Schaeff

Can Your Agent Hear You Now?

Pedro Lopez

How We Built the Airbyte Agent MCP Server and CLI

Dan Adler

The Enterprise Agentic Gap: When Developer-Level AI Tools Hit Millions of Lines

Will Lyon

Actionable Knowledge For Agents With Context Graphs

Jess Wang

Agentic vs. Vector Search: An Eval-Driven Approach to Coding Agent Performance

Hossein Niazmandi

Why building building agent quality platforms is hard.

Fuad Ali

Voice Agents Are Mostly Invisible. Here's How to See Them.

Idan Gazit

Build agents fast with GitHub Copilot (from idea to working app)

Rafael Levi

Video Discovery for Agentic World-Model Training

Anders Swanson

From Context to Memory: Your Agents Need a Real Memory Layer

Abhi Arya

From Chatbots to Agents: How Reducto builds for Agent Experience to Enable Real Work

Sam Parsons

How PayPal Enterprise Payments handles agent-initiated payments across ChatGPT and Google AI Mode

Gabriel Martinez

Agents Don't Have Coworkers, They Have Hostages

Simran Arora

Can LLMs write fast multi-GPU kernels? We built a benchmark to find out.

Felipe Blanes

Designing Evals That Earn User Trust

Jeff Ng

Building agents is trivial now, context is the next frontier

Bogdan Gaza

Running a 20T-Token Data Pipeline: Infrastructure Lessons from Production

Charlie Dickens

Towards Reliable Financial Agents: How a 4B Model Outsmarted a 235B Giant

Jakub Hojsan

Agentic Search for Coding Agents

Aditya Khandelwal

Agents, codebases, and teams: what it actually takes to ship together

Andreea Pleşea & Dan Bălăceanu

Would your AI agent get the job? A performance review framework for enterprise agents

Rafal Wilinski

Self-Improving Agents That Teach the Company Back

Greg Pstrucha

Stop prompting

Derek Meegan

Deploying browser agents at scale

Leo Platzer

From raw documents to AI-ready data

Em Shreve

AI Enablement at Automattic: How a Remote Company Builds AI Fluency

Nilofer Rajpurkar

Inside the AI economy: What Stripe’s data reveals

Jesse Lumarie

Building the engine while flying the plane — launching the Figma MCP server

Uday Kiran Medisetty & Adam Huda

Agentic SDLC at Uber: Building Blocks for Uber's Software Factory

Will Bond & Ameya Ketkar

Scaling Code Quality: Building uReview, Uber’s Multi-Agent Code Review Engine

Andrew Orobator

Spin at the Gate Until Green: The Engineering Primitives Behind Self-Driving Codebases

Nachiket Paranjape & Swaroop Chitlur Haridas

AI Evals Platform for Cross-Functional Teams at Scale

Kanish Manuja

Productionizing LLM Gateways: Architecture, Tradeoffs, and Hard Lessons from the Trenches

Clare Liguori

From AI-Assisted to AI-Native: Building a Frontier Development Team

Eyal Blum

How to Get Your Org to Adopt Coding Agents (Without Shipping Garbage)

David Hsu

Governance Is the Real Bottleneck to AI ROI

Ameya Bhatawdekar

Your Agent Evolved. Your Evals Didn't.

Itamar Friedman

The Last Human Code Review: Building Trust in AI-Generated Code

Hursh Agrawal

Prototyping as Leadership: How a CTO Ships with AI Agents

Arek Borucki

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

Sarthak Aggarwal

IT Admin for the AI Workforce: Why Your AI Agents Will Need Their Own IT Department

Kieran Klaassen

The Era of Compound Engineering

Niels Rogge

How I automate my own job at Hugging Face using agents

Dan Bjornn

Your Fine-Tuned Model Is Tech Debt: A 50x ROI House of Cards

Tushar Jain

Unlock Agent Autonomy: The Runtime for AI-Native Systems

swyx

The Highest Loop

Pablo Castro

On AI and Knowledge

Alexander Embiricos & Romain Huet

The Golden Age of AI Engineering

Zixuan Li

GLM-5.2: Frontier Intelligence, Open Weights.

Thom Wolf & Olive Song

Thom Wolf keynote

Manoj Nair

Security Track intro

Jason Liu

Getting the most out of Codex

Tereza Tížková

Rise of the Software Factory

Charlie Holtz

Orchestras, not Factories

Daksh Gupta

What we learned by analyzing 1M AI-generated PRs

Gergely Orosz & Simon Eskildsen

Fireside Chat: Gergely Orosz × Simon Eskildsen

Kevin Hou

Get Out of the Model's Way

Zach Lloyd

Self-Improving software factories: The new open source model"

Ido Salomon

We're the bottleneck, but we don't have to be

Sarah Sachs

Notion's Token Town

Vaibhav Gupta

fighting slop with slop

Kyle Mistele

Loop Engineering from first principles

Dex Horthy

Harness Engineering is not Enough: Why Software Factories Fail

Erik Meijer

In Code They Act, In Proof We Trust

Lee Robinson

Recursive Model Improvement

Tina Manghnani & Keiji Kanazawa

From framework to runtime: running agents with Foundry Agent Service

Arun Sekhar & Pamela Fox

OpenAI, Anthropic, or agent frameworks: choose the right AI stack

Marco Casalaina

Power agents with Microsoft IQ

Ashu Joshi

Deploy agents to users in M365, Teams, and apps

Adam Azzam

Don’t build agents, build environments

Shashank Goyal

Letting the Interns Loose — How We Accelerated AI Adoption.

Ivan Burazin

Kubernetes Is Not Your Sandbox

Samuel Colvin

Your agent needs a sandbox, not a desert

Abhishek Bhardwaj

From fork() to Fleet: Designing an Agent Sandbox Cloud Pt 1

Abhishek Bhardwaj

From fork() to Fleet: Designing an Agent Sandbox Cloud Pt2

Kevin Orellana

1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Write and Run Code

Adi Singh

The Next Trillion Users of the Internet Still Don't Have an Identity

Robert Brennan

Sandboxes Aren't Optional: Runtime Isolation Patterns for Coding Agents at Scale

Jonathan Kelley

Building ambitious software

Christopher Manning

Building the simulation infrastructure for practical world model use

Christopher Manning

Building the simulation infrastructure for practical world model use (Part 2)

Jason Ma

Commercial Grade-Robots for Real World Usage

XiangMing Sun

Unitree: Building Mass Produced Humanoids

Deepak Pathak

Frontier Robotics Research

Suchet Bargoti

From Manual Drones to Autonomous Multi-Agent Missions

Cormac Brick

Why Large? Tiny LMs & Agents on Edge/Robotics

Amit Navindgi

From Self-Driving Monorepo to Self-Driving Cars

Cyrus Clarke

I gave an AI a body

Parth Asawa

Beyond Static Intelligence: Evaluating Continual Learning

Ronak Malde

Scaling up Continual Learning

Jack Morris

Scaling Compute on Context

Yu Su

Intelligence + Continual Learning = Expertise

Sara Hooker

Adaption Labs — Gradient-Free Continual Learning

Vivek Trivedy

Improving Agents is a Data Mining Problem

Samuel Denton

Bringing Continual Learning into Enterprises

Ben Hylak

Designing Agents (The Floor Is the Frontier)

Shlok Khemani

Lessons from Studying Every Memory System

Ben Holmes

LLM Knowledge Bases: a practical guide

Thor 雷神 Schaeff

Build realtime multimodal agents with Gemini Live

Thor 雷神 Schaeff

Build realtime multimodal agents with Gemini Live (continued 2)

Thor 雷神 Schaeff

Build realtime multimodal agents with Gemini Live (continued 3)

Thor 雷神 Schaeff

Build realtime multimodal agents with Gemini Live (continued 4)

John Lindquist

The Agentic Power User's Playbook: Tips and Tricks for Swarm-Style Agentic Development

John Lindquist

The Agentic Power User's Playbook: Tips and Tricks for Swarm-Style Agentic Development (continued 2)

John Lindquist

The Agentic Power User's Playbook: Tips and Tricks for Swarm-Style Agentic Development (continued 3)

Brian Douglas & John McBride

Don't Write Skills, Train Models

Brian Douglas

Don't Write Skills, Train Models (cont. 2/3)

Brian Douglas

Don't Write Skills, Train Models (cont. 3/3)

Lukas Petersson

Vending-Bench: Long-Horizon Agent Evals for a Simulated Vending Business

Jason Lopatecki

From Signal to PR: Anatomy of a Self-Improving Agent

Soumya Gupta & Jai Chopra

Building Closed-Loop Evals for a Multimodal Agent at Uber Scale

Rustem Feyzkhanov

From Agent Traces to Agent Simulations: The next era of agent evaluation

Chris Souza & Preetika Bhateja & Daniel Bump

Model Whisperers: How Evals and Prompts Shape Agent Behavior

Maor Bril

Evaling Video Slop

Mihnea Munteanu

Ask YouTube — Open Q&A

Akele Reed & Dave Revere & Doug Keller

Evals Driven-Development: Engineering a Mental Health AI Coach Ethically & Safely

Philipp Schmid

Don't Ship Skills Without Evals

Alex Shaw & Ryan Marten

Everything Is a Rollout

Geoffrey Litt

Understanding is the new bottleneck

Max Drake

The Spatial Harness: Bringing Agents to the Canvas

Jonathan Gordon

The Design-Code Roundtrip That Isn't

Maximillian Piras

Mousepower: agents that can’t be measured, can’t be managed.

Paul Bakaus

Design at the Speed of Adjectives

Thais Castello Branco

Training Taste

Eve Bouffard

Imagination Engineering

Hassan El Mghari

The Missing Layer: Design Taste in AI Agents // Stop Letting Your Agents Ship Ugly UIs

Jeremiah Lowin

Generative UI... in Python?

Vincent Wendy

One Designer + Al. Hundreds of Deliverables.

Dhruv Batra

Computer-use models will agentify the web, not APIs

Pierluca D'Oro

Computer Use at the Edge of the Statistical Precipice

Paul Klein IV

Bringing agents onto the world wide web

Corey Gallon

The Dark Arts of Web Automation: Teaching Agents to Use Websites Like Humans

Gaurav Mishra

From RL to IRL

Omer Primor

The Rise of CaaS: Context-as-a-Service for Agentic AI

Francesco Bonacci & Dillon DuPont

Computer-Use 2.0: Agents Just Got Multi-Cursor

Ishan Anand

Will AI predict people like we predict the weather? (alternate title “A field guide to synthetic personas for market research”)

Patricija Žemaitytė

How Web Data Infrastructure Powers the Next Generation of AI

Averi Kitsch & Prerna Kakkar

Build-Time vs. Run-Time: Why Your Dev Tools Will Fail in Production

Kevin Madura

It’s Tokens All The Way Down: How RLMs are Different

Ajay Prakash

500 Skills, Zero Fine-Tuning: LinkedIn's Playbook for AI Agents That Actually Know Your Codebase

Brandon Waselnuk

Your agents lack context: Here's how to fix "You're absolutely right!"

Laurie Voss

How long can your skills be before your agent forgets what you told it?

Prukalpa Sankar

WTF Is the Context Layer? The Missing Infrastructure for Production Agents

Liad Yosef & Ido Salomon

MCP Apps - Extending the frontier

Dustin Mihalik

MCP Apps: Give the Model Data, Give the User a UI

Cornelia Davis

MCP Tasks (async)/ Why the heck aren't any agents supporting MCP tasks/async?

Alex Hancock

The Universal Remote Control for AI

Diogo Almeida

What's next after RLHF?

Sean Cai

State of Data

Uri Rolls & Thom Wolf

Training Frontier Models to Out-Think Hackers

Raymond Feng

Learning on the job: the future of post-training

Will Brown

Reinforcement Learning without Verifiable Rewards

Joseph Wang

Emulated: The data for fully autonomous software engineers and companies

Kenny Workman

LatchBio

Olive Song & Dan Fu

Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It

Ali Khial

Benchmarks: The Good, the Bad, and the Ugly

Viren Baraiya

Harnessing Agents: The Durable Runtime for Dynamic Workflows

Dan Farrelly

Your agent architecture has a half-life of 6 months

Thorsten Hans

Edge-Native AI: Building Ultra-Fast Agents and MCP Servers with Spin

Ronak Chokshi

Power agents with Microsoft IQ

Alex Campos & Yunmo Koo

Inference performance as a competitive advantage

Abdul Dakkak

Modular: Taming the AI Hardware Cambrian Explosion

Wallon Walusayi

AI Engineering & Governance 2026 Trends

Justin Reock

AI-Assisted Engineering: 5 Trends We're Seeing From 500+ Organizations

Peter Werry

How to generate mergeable code with a context engine

Rishab Kumar

From Stateless to Stateful: Orchestrating Real-Time Voice & Messaging Agents with Twilio and Amazon Bedrock

Cat Wu & Thariq Shihipar & Simon Willison

This Year in Claude

Harald Kirschner

Surviving Your Own Velocity: How VS Code Ships Weekly with 40 People

Gil Feig

Why your company needs a context graph, and how to build it

Kamalakannan Nandagopal

Beyond Code Generation: API Context for Agentic Engineering

Garrett Galow

Building an Agent Harness for the Business, Not the Builder

Dean Quiñanola

AI Applications in a flash! No Dev Ops. Just code.

Dominik Kundel

Building on the Codex Harness

Gabriel Spencer-Harper

Why AI Didn't Actually Make You Ship Faster

Nixon Dinh

The Death of Keyword Search and the Rise of Agent-Readable Catalogs

James Zou

Harnessing Collective Agent Intelligence for Open Science

Philipp Schmid

Why Agents Should Have Their Own Sandbox

Suraj Gupta

Warp: Building Self-Improving Agent Software Factories

Jesse Hall

Latency Is a Budget. Humanlike Is the Goal.

Dylan Couzon

The Frontier Is Coming Home

Elizabeth Fuentes Leone

The Infinite Context Window Is a Myth: Context Engineering for AI Agents

Jetashree Ravi

Stop Renting Intelligence: The Train-to-Deploy Loop for Specialized AI

TBD — Sonar

Redesigning how software gets built

Matt Lawler

FDE Playbook: Build an AI Support Agent and Give It a Voice

Anant Srivastava

Prompt, Memory, Weights: The Architecture Decisions Most AI Teams Make by Accident

Eli Cohen

Continuous Offensive Security the only approach in an agent-first world

Tarun Sunkaraneni

Ray Actors, Vision Tokens, and the GIL: Engineering an SFT Data Pipeline That Keeps GPUs Busy

Martin Harrysson & Matt Linderman & Prakhar Dixit

Tokenomics: From AI Spend to AI Value

Varun Shenoy

How do you diffuse AI into the real world?

Andrew Garvin

How to avoid disaster when vibe-coding a billing engine

Varun Pant

Your Code Has Bugs. Lean4 Has Proofs. A Practical Guide to Formal Verification for Engineers

Imad Touil

AI-Native Organisations runs on Skills: How to Extract, Structure, evaluate and Scale Them

Ben Kus

The Half Life of Agent Infrastructure

Rachna Srivastava

Guardians of the State: How We Built an Air-Gapped AI Fortress for Consumer Data

Mingsheng Hong

From Tokenmaxxing to Trusted Throughput

Roberto Milev & Uday Kanagala

Agents Are Where Microservices Were in 2015. We're Making All the Same Mistakes.

Carlos Sanchez

Agentic Sites: Building Hyper Personalized Websites

Rania Khalaf

The Chief AI Officer: A framework for the emerging Swiss Army Knife of roles

Alex Volkov

The Z/L Continuum: Should AI Engineers Still Read Code?

Vlad Luzin

Is Orchestration the Future?

Ankit Jain

How to Kill the Code Review

Laurie Voss

The Death of the Code Review

Nicholas Arcolano

Tokenmaxxing is the New "Lines of Code"

Matthew Jewkes

Engineering Agency out of the Happy Path

Keiji Kanazawa

I Let Agents Refactor My Codebase for 3 Weeks. Then I Read the Code.

Tomás Hernando Kofman

Intelligent Model Routing: Frontier Performance Without Frontier Bills

David Corbitt

Inference is the New Training Loop: Architecting High-Reliability Agents and Continuous AI Systems

Justin Reock

The state of AI in software development: Insights across 400+ organizations

Thariq Shihipar

Field Guide to Fable

Tariq Shaukat

In the Land of AI Agents, the Verifiers Are King

Antje Barth

Perception Agents

Benoit Schillings

Research to Reality with Google DeepMind

Laurie Voss & Aparna Dhinakaran

Evals Track Intro

Richard Socher

First Steps Toward Automated AI Research

Han Xiao

Autoresearch for Dense Retrieval: Test-Time Compute with Frozen Embedding Models

Stefania Druga

Memory Harnesses for Long-Running Research Agents

Elie Bakouch

« the era of (auto) research »

Dumitru Erhan & Shane Gu & Nicole Brichtova & swyx

SOTA Generative Media Panel

Tim Sweeney

Closing the Loop: An Autonomous AI Research Agent

Zhengyao Jiang

An AI Agent Became the #1 Contributor in OpenAI's Hiring Challenge

Lakshya Agrawal

Self-Improvement of Context, Harness, and Model Weights through Reflective Optimization

Tejas Bhakta

Autoresearch for Kernels

Roland Gavrilescu & Julian Bright

Autoresearch in the wild

Erina Karati & Arunachalam Manikandan

Autoresearch in a Multi-Agent AI Village

Addy Osmani

Closing Keynote

George Cameron & Micah Hill-Smith

Trends in AI

Wei-Lin Chiang

Closing Keynote

Pamela Fox

Diagnosing agent failures in production

Chang Liu

Tracing and debugging agents across systems with OpenTelemetry

Ross Wollman

Benchmarking VS Code with VSC-Bench: How to measure agent performance

Tina Manghnani

Design multi-agent systems that actually work

Chang Liu

Evaluating and optimizing AI agents: from observability to continuous improvement

Arun Sekhar

Blast Radius Zero: One‑Command OpenClaw Sandboxes in the Cloud

Ashu Joshi

Operate agents safely at scale with enterprise governance

Sangwu Lee

Training Krea 2 - What matters in generative model training.

James Russo

HTML Is All Agents Need

Ekaterina Deyneka

Building an Agentic Video Editor for Mass Consumer

Arturo Nunez

The Next Game Engine Won't Have a Manual

Todd Fisher

While my guitar gently speaks

Lina Colucci

Voice agents with Realtime Video

Keegan McCallum

Generative Video at the Speed of Light

Gabriel

Infra behind Krea 2 - How to train and serve at scale

Ahmed Ahres

The Next Medium: Why Real-Time Interactive Video Changes Everything for Developers

Nidhi Kaushik Vyas

Designing Multimodal Collaborative Agents for Next-Gen Commerce

Harshal Bhangale

Why Your AI Agent Needs a Wallet: Agentic commerce on Arc with USDC and Nanopayments

Anil Nadiminti

When AI Agents Pay and Sellers Monetize: Building x402 Apps for Agentic Commerce on AWS

Jan Curn

x402 isn’t good (yet)

Rodrigo Coelho & Pranav Maheshwari

Agent Spending Without Controls: The Missing Infrastructure Layer for AI Pa…

Anna Spysz

Teaching agents to pay

Ahnaf Prio

The Agentic Commerce Stack

Jay Mok

Your Agent Just Authorized What?!

Gus Iwanaga

The End of the Static Screen: Architecting Intent-Driven UX with Agentic Orchestration

David Levine

Beyond the Lethal Trifecta: Agentic Commerce on the Open Internet at Machine Speed

Brendan Rappazzo

ALPHALAB: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs

Udi Menkes

Why Off-the-Shelf AI Doesn't Understand Money

Divakar Kumar

Let's integrate AI Agents in Event-Sourced Systems

Vinoo Ganesh

How Kepler Built Verifiable AI for Financial Services

Shawn Chan

Build for the Memo, Not the Demo — Notes from 200 Investment Committees

Lucas Palma

We Vetted 2,000 AI Skills Before They Reached Developers

Ramana Siddanth Emani

Your Finance Agent's Bottleneck Is You

Shreya Rajpal & Aman Gupta

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

Yogendra Miraje

Skills are new features: Building Skill-Centric Harness for Agentic Products

Sai Krishna Rallabandi

Wearing the Agent: Engineering a Family-and-Friends Personal Agent, from Group Chats to Glasses

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

State of the Union: Why Local, Why Now

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

State of the Union: Why Local, Why Now

Ahmad Osman

Demo: GLM 5.2 on DGX Station — Frontier Intelligence Under Your Desk

Carter Abdallah & Vincent Weisser & Lucas Atkins & Chris Alexiuk

Local Models: Trust, Control, Optimization

Carter Abdallah & Vincent Weisser & Lucas Atkins & Chris Alexiuk

Local Models: Trust, Control, Optimization

Chris Alexiuk & Daniel Han & Asma Beevi & Merve Noyan & Parth Sareen

Compression at the Edge

Chris Alexiuk & Daniel Han & Asma Beevi & Merve Noyan & Parth Sareen

Compression at the Edge

Nader Khalil & Walden Yan & Tanay Varshney & Alex Atallah

Model Routing

Nader Khalil & Walden Yan & Tanay Varshney & Alex Atallah

Model Routing

Stephen Chin

CrabRAG: Why Automated Assistants Need Graph Memory, Not More Tokens

Yohei Nakajima

Active Graph Agent Runtime (BabyAGI 4)

Mike Phipps

Your Moat Is Your Data Model

Omri Bruchim

From Systems of Record to Systems of Context

Ritvik Pandya

AI : Learned Execution Graphs for Real-Time Anomaly Detection & Drift Classification in APIs

Frank Coyle

Why Agentic Systems Need Ontologies

James Le

Video Has No Memory. Here's How We Built One.

Shafik Quoraishee & Joanne Song

On-Device Agentic AI for the New York Times Games

Daniel Chalef

Citation Needed: Provenance for LLM-Built Knowledge Graphs

Subbiah Sethuraman & Abhilash Asokan

Why We Killed Our Multi-Agent Pipeline: Lessons From Pharma Commercial Intelligence

Everett Berry

GTM Engineering: The Technical Bits

Aliisa Rosenthal

Reverse-Engineering the AI Buyer

Flora Liu

AI in GTM at Notion

Arman Vaziri

The Building Blocks of GTM Orchestration

Alex Bauer

How Juries and Librarians Can Solve GTM's AI Trust Problem

Christopher Burns

How We Got LLMs to Recommend Our Open Source Library (Without Paying or Plug-ins)

Jeffrey Wang

Knowledge Systems: The New GTM Stack

Justin Joyce

How AI Agents Let GTM Teams Scale

Sait Izmit

Building GTM AI Agents: Lessons from Deploying to 6,000 Users

Stephanie Jarmak

The Death of Developer Advocates

Chaitanya Asawa

From Ambient Documentation to Clinical Intelligence

Rashi Agrawal

Guardrails First: Engineering Member-Facing Health AI

Jared Joselowitz

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

Vivek Muppalla

200 Million Patient Interactions Later: What the Generic Voice Stack Misses

Clay Cockrell & Tony Fabrikant

Al is becoming the World's largest Relationship Therapist. We Can't Afford to Get it Wrong.

Vasant Kearney

Healthcare’s Agent Bytecode: X12 as the Harness for AI Agents

Ayush Bhardwaj

Trading Desks to Clinical Trials: Parallels in Applied Vertical AI

Dan Feng

How to build an AI-Native Health Company

Anuj Iravane

Don't be data poor

Christopher Lovejoy & Saul Howard

Why Your Enterprise Tech Stack Isn't Ready for AI Agents - And What to Build Instead

Serena Ge

DeepSWE: expert code datasets

Frank Coyle

Anthropic's CCA Exam as a Field-Guide for Agentic Engineering

Anirban Chatterjee

Guide, Verify, Solve: The Engineering Discipline Agentic Development Demands

Denys Linkov

Benchmarking Coding Agents on New vs Legacy Code bases

Dominik Kundel

Codex, Behind the Harness

Arjun Singh

Multiplayer agentic engineering: enabling your whole team and your best agents to work together

Justin Smith

Always-on agents run production without the on-call tax

Idan Gazit

Realtime multiplayer, automation, and you!

Matt Dailey

Velocity Sickness: What Happens When Your Whole Team Gets 10x Faster

Saoud Rizwan

Open Source Is Dead. Long Live Open Source.

Nishant Gupta & Naman Ahuja

Operating Distributed Inference Systems at Scale

Qianru Lao & Lu Zhang

Routing LLM Inference in Production: From Engine Signals to Policy

Ashok Chandrasekar & Jason Kramberger

Are LLM Performance Benchmarks Reliable?

Rita Zhang & Sitanshu Gupta

Vertical Mobility: Building an AI Inference Platform That Scales from MVP to Trillion-Parameter Workloads

Philip Kiely

What's New in Inference Engineering

Daniel Svonava

Large clusters for small models

Byung-Gon (Gon) Chun

The Frontier AI Inference Cloud for Agents

Yuchen Fama & Ashish Kamra

KV Cache-Aware Routing and P/D Disaggregation on Kubernetes: The Parts Public Benchmarks Don't Show

Asaf Gardin & Yuval Belfer

Two Bugs That Hid in Plain Sight: A vLLM Debugging Detective Story

Filip Makraduli

Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards

Wallon Walusayi

AI Engineering & Governance 2026 Trends

Peter Werry

Beyond RAG: See a relational context engine reduce token burn

Miguel González Fernández & Corby Rosset

The Art of Building Verifiers for Computer Use Agents

Giedrius Steimantas

The Missing Layer in Agentic AI

Michael Liendo

Trust, But Verify: Human-in-the-Loop for Agents That Actually Matter

Sujee Maniyam & Dylan Bristot

Optimizing Open Models for Production Grade Inference

Dru Knox

Harness Engineering: The New Core Skill for Agentic Developers

Karthik Ranganathan & Heather Downing

Agent Memory Is a Solved Problem. Agent Learning Is Not.

Nan Jiang

Taking Reinforcement Learning Cross Datacenter

Willem Pienaar

Your Agent Can't Tell If It's Right

Zubin Aysola

ARIA, how we built autoresearch with autoresearch

Sheilah Kirui

Seeing the Plumbing: Profiling vLLM Speculative Decoding on NVIDIA Blackwell

Ali Adl-Tabatabai

While You Were Generating: The Verification Gap Nobody Talked About

swyx & Rob Wachen

Latent Space Live: the Inference Inflection from First Principles

Rowan Christmas

YOLO Mode, Safely: microVM Sandboxes for Any Agent

Jan Curn

MCP doesn’t suck — your agent does

swyx

Improving AIE: Q&A and Feedback Session

swyx

Improving AIE: Q&A and Feedback Session (repeat)

Sarah Simionescu

Dashboards are Dead

Ryan Cooke

No, That's Not a Software Factory

Michael Patterson

The Lethal Trifecta Is Already on Your Developers' Laptops

Kwindla Kramer & Neil Zeghidour

Voice is the universal interface

Ben Dicken

Move fast and (don’t) break things

Joshua Mo

Your Model is Private. Your System Isn't.

Melanie Warrick

The Human Is an Async API

Jeremy Adams

Small Claws Are Beautiful: Edge Agents with NanoClaw, Raspberry Pi, and Graph Memory

Ivan Leo

An Interaction Is All You Need

Matt Gibiec

Your AI Agent Has No Nervous System

Jake Broekhuizen

The Next Run Should Be Better

Sandhya Subramani

Agents That Forge Their Own Tools: Self-Modifying AI in the Wild

Rafael Levi

Video Discovery for Agentic World-Model Training

George He

Everyone talks about document search, but what about results?

Remy Guercio

An AI Future Without the Lock-In

Martin Harrysson & Matt Linderman & Prakhar Dixit

The Agentic Product Development Organization

Jennifer Lee

Building safe payment infrastructure for machine-to-machine commerce

Dmitry Buykin

Tribal Dungeons of Global Shipping: AI Agents at Global Scale

Daniel Kim & Michelle Nguyen

All the Things We Have to Do to Satisfy Your Insatiable Need for Tokens

Pranay Bhatia

Stop Model Shopping: Why Ownership Beats Choice in the Agent Stack

Josh Leavitt

From Zero to AI-Native: Scaling AI Across the Org

Brian Lewis

Which AI startups actually land enterprise contracts? Lessons from evaluating 100+ AI startups at Millennium Management

Kunal Lanjewar

Your Hero Agent Needs a Party

Salman Munaf

AI Agents Are Just Distributed Systems Now

Lena Hall

The Signal Layer: What to Build When Anything Can Be Built

Sandhya Subramani

Tell the Robot What You Want

Safia Abdalla

The Agent Behind the Curtain: Building the Oz Cloud Agent Platform

Tisha Chawla & Susheem Koul

FinOps for AI Agents: Who Spent All the Tokens?

Khaled Alashmouny & Abduallah Mohamed

What If Your Chip Design Team Moved Like a Single Body?

Archana Kamath & Tyler Gillam

Preferences > Benchmarks: Model Routing for How Teams Actually Build

Patrick Debois

Coding Agents Don't Scale Themselves. Neither Do Your Teams.The Rise of Agent Enablement.

Rémi Louf

Agent Frameworks Considered Harmful

Sebastian Fox

Inside 847 Production Clinical AI Notes

Sachin Malhotra

Give the Agent a Budget, Not a Token

Barr Yaron

The 2026 State of AI Engineering

John Ousterhout

TCP and RDMA are Killing Inference Throughput; Homa can Fix It

Maxime Rivest & Isaac Miller

The Unreasonable Effectiveness of Separating the Task from the Model

Mike Krieger & swyx

How Anthropic Builds: Lessons from Labs

Emil Eifrem

Thinner Agents on a Smarter Substrate: The Ontology-based Semantic Layer

Katelyn Lesse & Angela Jiang

Tokens Should Have Jobs

Nikita Kothari

MCPs, CLIs, and Skills: Choosing the Right Tooling Layer for Agentic Development

Michael Grinich

Auth for Agents: Unblock Autonomous AI with auth.md

Mike Chambers

Harness Engineering: Building the Production Cage for Powerful Domain Agents

Dex Horthy & Ian Livingstone & Allie Howe

The Great Loops Debate

Brendan Rappazzo

Loophole - Adversarial Agents To Stress Test Your Morality

Giselle van Dongen

🎵 Every step you take, every call you make - the reliable agent stack

Sarah Sanders

We let an AI agent execute Bash and lived to talk about it

Kay Malcolm

No Memory, No Harness: Why the Database Is the Last Line of Defense

Andrew Qu

How we Solved Agent Building

Philipp Schmid

Agents Without Code: How Skills, YAML, and Filesystems Replaced Python

Theo Browne

Closing Keynote — Theo Browne

Garry Tan

Closing Keynote: Garry Tan

Howie Liu & Joshua Xu & swyx

Startup Battlefield

Howie Liu

$100,000 AIE Startup Battlefield — presented by Hyperagent

Theo Browne

AMA with Theo Browne (@t3.gg)