The talk archive.

Decoupling the Brain from the Hands: Claude Managed Agents (Part 1 of 4) — Anthropic

Priyanka Phatak · Gabe Cemaj

Agent engineering · Infrastructure & deployment · Agent orchestration

Tolan: Voice-First AI Companion — Paula Dozsa, Tolan

Paula Dozsa

Voice AI · Personal agents · Agent memory

Why AI Didn't Actually Make You Ship Faster — Gabriel Spencer-Harper, Meticulous

Gabriel Spencer-Harper

Code review & verification · Developer workflows & testing · Browser agents & WebMCP

How We Solved Agent Building — Andrew Qu, Vercel

Andrew Qu

Agent engineering · Agent skills · Natural-language database queries

Build Your Own Team of Managed Agents - Jack Wotherspoon, Google DeepMind

Jack Wotherspoon

Agent engineering · Coding agents · Infrastructure & deployment

What Makes Open Models Fast in Production — Sujee Maniyam, Nebius

Dylan Bristot · Sujee Maniyam

Infrastructure & deployment · Fine-tuning · Open-weight models

Evals in AI: A Deep Dive — Tejas Kumar, IBM

Tejas Kumar

Evals · Agent engineering · Developer workflows & testing

Stop Chunking Like It's 2022 — Yuval Belfer, AI21 Labs

Yuval Belfer

Retrieval-augmented generation · Search & retrieval · Evals

You’re Not Thinking Big Enough: Rebuilding Food Systems with AI Agents — Cody Menefee, Firecrawl

Cody Menefee

Agent engineering · Vision & video · Human-in-the-loop validation

Build the Right Thing: Product Engineering (Part 2) — Kent C. Dodds, EpicProduct.engineer

Kent C. Dodds

Product engineering · AI interface design · Infrastructure & deployment

How to avoid disaster when vibe-coding a billing engine — Andrew Garvin, Stripe

Andrew Garvin

Coding agents · Agent skills · Developer workflows & testing

From Zero to Leaderboard: Agent Evaluation — Wolfram Ravenwolf, Weights & Biases

Wolfram Ravenwolf

Evals · Coding agents · Observability & reliability

How to Get Your Org to Adopt Coding Agents (Without Shipping Garbage) — Eyal Blum, Figma

Eyal Blum

Coding agents · AI engineering leadership · Code review & verification

How We Mapped a 35-Million-Line Mainframe in 4 Days - Stephen Chin, Neo4j & Neeraj Deshmukh, Blitzy

Stephen Chin · Neeraj Deshmukh

How to Write Your First AI Eval - SallyAnn DeLucia, Arize AI

Sally-Ann DeLucia

Evals · Observability & reliability · Prompting & in-context learning

No, That's Not a Software Factory — Ryan Cooke, WorkOS

Ryan Cooke

Software factories · Developer productivity · Human-in-the-loop validation

Does Code Quality Still Matter? It Depends on This — Max Kanat-Alexander, Capital One

Max Kanat-Alexander

Developer workflows & testing · Coding agents · Sandboxes & isolation

Your agents lack context: Here's how to fix "You're absolutely right!" — Brandon Waselnuk, Unblocked

Brandon Waselnuk

Context engineering · Coding agents

We Let Claude Code and Codex Race Human Researchers — Elie Bakouch, Prime Intellect

Elie Bakouch

Autoresearch · Coding agents · Benchmarks

A Valid Key Let an AI Agent Delete Production - Sagar Batchu, Speakeasy

Sagar Batchu

The Transcript Looked Fine. The Call Wasn't. — Debugging Voice Agents, Arize

Fuad Ali

Voice AI · Observability & reliability · Evals

It’s Tokens All The Way Down: How RLMs are Different — Kevin Madura, AlixPartners

Kevin Madura

Context engineering · Agent orchestration

The Self-Improving OSS Agent Stack — Marc Klingen, Langfuse

Marc Klingen

Agent engineering · Observability & reliability · Evals

Is a Faster Model Actually Faster? Test the Whole Job — Morgan Suo, MiniMax

Morgan Suo

AI cost & performance · Evals · Transformers & attention

Reverse-Engineering the AI Buyer — Aliisa Rosenthal, Acrew Capital

Aliisa Rosenthal

Enterprise AI · AI startups & small teams

From Raw Documents to AI-Ready Data — Leo Platzer & Jeff Koss

Jeff Koss · Leo Platzer

Data quality & curation · Retrieval-augmented generation · Enterprise AI

Why Waiting for the Next AI Model Can Pay Off - John Stecher, Blackstone & Scott Worland, Norm AI

John Stecher · Scott Worland

The AI Bill Is Too Damn High: Tokenomics 101 — Eugene Cheah, Featherless AI

Eugene Cheah

AI cost & performance · Inference · Coding agents

An Interaction Is All You Need — Ivan Leo, Google DeepMind

Ivan Leo

Agent engineering · Context engineering · Multimodal AI

500 Skills, Zero Fine-Tuning: LinkedIn's Playbook for AI Agents — Ajay Prakash, LinkedIn

Ajay Prakash

Agent skills · MCP · Context engineering

Deep dive on LLM Inference at Scale — Harshul Jain, Audible & Tanmay Sah, Independent AI Researcher

Harshul Jain · Tanmay Sah

Inference · KV caching & prefix reuse · Quantization

MCP Doesn't Suck. Your Agent Does. — Jan Čurn, Apify

Jan Curn

MCP · Agent engineering · Context engineering

Stop Prompting — Greg Pstrucha, Sentry

Greg Pstrucha

Coding agents · Developer workflows & testing · Code review & verification

Robots Will Be Trained on Video Games - Pim de Witte, General Intuition

Pim de Witte

Giving AI Agents Memory That Learns — Jake Broekhuizen, LangChain

Jake Broekhuizen

Agent engineering · Agent memory · Continual learning

GPU Died. Training Didn't: Self-Healing Training at Scale — Crusoe

Connor Guerrero · Young Jeong · Nikhil Gupta

Infrastructure & deployment · Observability & reliability