The talk archive.

What We Learned Deploying AI within Bloomberg’s Engineering Organization

Lei Zhang

Observability and reliability · Leadership · Coding and developer tools

What We Learned From A Year of Building With LLMs

Eugene Yan · Hamel Husain · Jason Liu · Dr Bryan Bischof · Charles Frye · Shreya Shankar

Leadership · Infrastructure and deployment · Reasoning and models

What We Learned from Using LLMs in Pinterest

Mukuntha Narayanan · Han Wang

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

When Agents Meet Physical Data: The Other Physics of Agent Harnesses

Dmitry Petrov

Agent engineering · Data and model adaptation · RAG, context, and search

When all context matters: Extended Cache Augmented Generation (ECAG)

Luis Romero-Sevilla

RAG, context, and search · Agent engineering

When Vectors Break Down: Graph-Based RAG for Dense Enterprise Knowledge

Sam Julien

RAG, context, and search · Evals

When Will The Benchmaxxing Plague End?

Nick Heiner

Architecture · Evals · RAG, context, and search

Where AI is superhuman: The right jobs to automate with LLMs

Andy Triedman

Reasoning and models · Safety and governance · Other / unclassified

Which Jobs Can Be Replaced Today

Fryderyk Wiatrowski · Peter Albert

Agent engineering · RAG, context, and search · APIs, MCP, and protocols

While my guitar gently speaks

Todd Fisher

Creative and generative media · Speech and audio

Why Agent Engineering

swyx (Shawn Wang)

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

Why Agent Hype can fall short of reality – Joel Becker, METR

Joel Becker

Evals · Enterprise · APIs, MCP, and protocols

Why, and how you need to sandbox AI-Generated Code? — Harshil Agrawal, Cloudflare

Harshil Agrawal

Coding and developer tools · Other / unclassified · RAG, context, and search

Why Bolt.new Won and Most DevTools AI Pivots Failed - Victoria Melnikova

Victoria Melnikova

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

Why building eval platforms is hard

Phil Hetzel

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

Why Can't Anyone Answer Questions About the Business?

Garrett Galow

Agent engineering · RAG, context, and search · Enterprise

Why ChatGPT Keeps Interrupting You

Tom Shapland, PhD

Vision and video · Architecture · Reasoning and models

Why Eval++ Is the Next Great Compute Primitive — Sunil Pai & Matt Carey, Cloudflare

Sunil Pai · Matt Carey

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

Why Large? Tiny LMs & Agents on Edge/Robotics

Cormac Brick

Infrastructure and deployment · Speech and audio · Robotics and world models

Why MCP and ChatGPT Apps Use Double Iframes — Frédéric Barthelet, Alpic

Frédéric Barthelet

Safety and governance · APIs, MCP, and protocols

Why MLX

Infrastructure and deployment · Speech and audio · Vision and video

Why More Context Makes Your Agent Dumber and What to Do About It

Nupur Sharma

Architecture · RAG, context, and search · Agent engineering

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

Udi Menkes

Evals · Finance · Data and model adaptation

Why Rust is the Ideal Language for Vibe-Coding

Daniel Szoke

Coding and developer tools · Other / unclassified · Evals

Why (Senior) Engineers Struggle to Build AI Agents

Philipp Schmid

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

Why should anyone care about Evals?

Manu Goyal

RAG, context, and search · Evals

Why the Best AI Agents Are Built Without Frameworks (Primitives over Frameworks)

Ahmad Awais

RAG, context, and search · Agent engineering · Coding and developer tools

Why TTS Models Now Look Like LLMs — Samuel Humeau, Mistral

Samuel Humeau

Speech and audio

Why We Don’t Need More Data Centers

Dr. Jasper Zhang

Infrastructure and deployment · Other / unclassified

Why We Killed Our Multi-Agent Pipeline — Subbiah Sethuraman and Abhilash Asokan, ZS Associates

Subbiah Sethuraman · Abhilash Asokan

Agent engineering · RAG, context, and search · Enterprise

Why you should care about AI interpretability

Mark Bissell

Industry applications · Infrastructure and deployment · Safety and governance

Why Your Agent Disagrees With Itself (And What To Do About It)

Diane Lin

Agent engineering · Other / unclassified · Safety and governance

Why Your Agent’s Brain Needs a Playbook: Practical Wins from Using Ontologies

Jesús Barrasa

RAG, context, and search · Finance

Why your agents need decision traces, not just documents — Zach Blumenfeld, Neo4j

Zach Blumenfeld

Architecture · Observability and reliability · APIs, MCP, and protocols

Why Your AI UX Is Broken (and It's Not the Model's Fault)

Mike Christensen

Architecture · Agent engineering · Other / unclassified

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

Christopher Lovejoy · Saul Howard

Healthcare · Enterprise · Safety and governance