The talk archive.

How to Build Trustworthy AI

Allie Howe

Healthcare · Coding and developer tools · Safety and governance

How to build world-class AI products — Sarah Sachs (Notion) and Carlos Esteban (Braintrust)

Sarah Sachs · Carlos Esteban · Doug Guthrie

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

How to Build Your Own AI Data Center in 2025

Paul Gilbert

APIs, MCP, and protocols · Infrastructure and deployment · Architecture

How to construct domain-specific LLM evaluation systems.

Hamel Husain · Emil Sedgh

Evals · Developer workflows and testing · RAG, context, and search

How to defend your sites from AI bots

David Mytton

Infrastructure and deployment · Safety and governance · RAG, context, and search

How to evaluate a model for your use case

Emmanuel Turlay

Evals

How to Hire AI Engineers When Everyone Is Cheating With AI

Beth Glenfield

Leadership · Agent engineering · Evals

How to Improve Your Agents: Academic Lit Review

Zhou Yu

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

How to Improve your Vibe Coding — Ian Butler

Ian Butler

Safety and governance · Coding and developer tools · APIs, MCP, and protocols

How to Kill the Code Review

Ankit Jain

Developer workflows and testing · Safety and governance · Coding and developer tools

How to Leverage Domain Expertise — Chris Lovejoy, Notius Labs

Christopher Lovejoy

Evals · Leadership · Healthcare

How to look at your data; what to look for, how to measure

Jeff Huber · Jason Liu

Other / unclassified · RAG, context, and search · Agent engineering

How to Quantify AI ROI in Software Engineering (Stanford Study / 120k Devs)

Yegor Denisov-Blanch

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

How to Run Evals at Scale: Thinking Beyond Accuracy or Similarity

Muktesh Mishra

Coding and developer tools · Evals

How to Secure Agents using OAuth

Jared Hanson

APIs, MCP, and protocols · Safety and governance · Speech and audio

How to talk to statues — Joe Reeve, ElevenLabs

Joe Reeve

Speech and audio · Coding and developer tools · Vision and video

How to Train Your Agent: Building Reliable Agents with RL

Kyle Corbitt

Reasoning and models · Data and model adaptation · Enterprise

How Transformers Finally Ate Vision

Isaac Robinson

Vision and video · Infrastructure and deployment · Architecture

How We Built Zeta2: Training an Edit Prediction Model in Production — Ben Kunkle, Zed

Ben Kunkle

Coding and developer tools · Infrastructure and deployment · Evals

How we hacked YC Spring 2025 batch’s AI agents

Rene Brandel

Safety and governance · Architecture · RAG, context, and search

How we scaled 500m AI agents in production with 2 engineers

Mustafa Ali · Kyle Corbitt

Data and model adaptation · Finance · RAG, context, and search

How We Solved Context Management in Agents — Sally-Ann DeLucia

Sally-Ann DeLucia

Observability and reliability · Coding and developer tools · RAG, context, and search

How we taught agents to use good retrieval - Hanna Lichtenberg, Mixedbread AI

Hanna Lichtenberg · Aamir Shakir

RAG, context, and search

How Web Data Infrastructure Powers the Next Generation of AI

Patricija Žemaitytė

Vision and video · Architecture · Data and model adaptation

How Zapier Builds AI Products and Features With the Help of Braintrust

Ankur Goyal · Olmo Maldonado

Coding and developer tools · Observability and reliability · Evals

HTML Is All Agents Need

James Russo

Creative and generative media · Reasoning and models

HTML is All You Need (for Agents to Make Graphics)

Amol Kapoor

RAG, context, and search · Agent engineering · Reasoning and models

Human seeded Evals — Samuel Colvin, Pydantic

Samuel Colvin

RAG, context, and search · Observability and reliability · Evals

HybridRAG: A Fusion of Graph and Vector Retrieval to Enhance Data Interpretation

Mitesh Patel

RAG, context, and search · Finance

Hypermode Launch

Kevin Van Gundy

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

Hyperspace: More Nodes Is All You Need

Nicolas Schlaepfer

RAG, context, and search · Infrastructure and deployment · Reasoning and models

I Gave an AI Agent the Keys to My Life (Here's What Happened)

Radek Sienkiewicz

RAG, context, and search · Reasoning and models · Safety and governance

I Run a Fleet of AI Agents Across Three Machines. Here's What Broke.

Kyle Jaejun Lee

Infrastructure and deployment · Coding and developer tools · RAG, context, and search

"I've never seen anything scarier than an LLM with tool calls." — Erik Meijer aka @HeadinTheBox

Erik Meijer

Safety and governance · Agent engineering · Evals

Identity for AI Agents

Safety and governance · APIs, MCP, and protocols

Imagination Engineering

Eve Bouffard

Other / unclassified · Creative and generative media · Agent engineering