The talk archive.

Cooking with Codex — Charlie Guo & Gabriel Chua, OpenAI

Charlie Guo · Gabriel Chua

Coding agents · Agent orchestration · Long-horizon tasks

Realtime Voice Agents with Frontier Intelligence — Bohan Li, EliseAI

Bohan Li

Building the Engine While Flying the Plane: Launching the Figma MCP Server — Jesse Lumarie, Figma

Jesse Lumarie

Your Coding Agent Is 6 Months Out of Date — Jakub Hojsan, Exa

Jakub Hojsan

Coding agents · Knowledge freshness · Code review and verification

From Scratch to SOTA: Training a 3B State-Space Vision Model — Krishna Prasad Srinivasan, Sarvam

Krishna Prasad Srinivasan

Why 80% Reliability Isn't Good Enough — Felipe Blanes, Amazon AGI Lab

Felipe Blanes

Evals · User feedback loops · Observability and reliability

Are LLM Performance Benchmarks Reliable? — Ashok Chandrasekar & Jason Kramberger, Google

Ashok Chandrasekar · Jason Kramberger

From Tokenmaxxing to Trusted Throughput — Mingsheng Hong, Ironclad

Mingsheng Hong

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

Paula Dozsa

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

Gabriel Spencer-Harper

Code review and verification · Developer workflows and testing · Visual regression testing

How We Solved Agent Building — Andrew Qu, Vercel

Andrew Qu

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

Dylan Bristot · Sujee Maniyam

Infrastructure and deployment · Data and model adaptation · Open weights

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

Tejas Kumar

Evals · Agent engineering · Developer workflows and testing

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

Yuval Belfer

RAG, context, and search · Query-dependent chunking · Oracle retrieval evaluation

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

Cody Menefee

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

Kent C. Dodds

Product engineering · Jobs to Be Done · Kano model

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

Andrew Garvin

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

Eyal Blum

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

Ryan Cooke

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

Brandon Waselnuk

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

Elie Bakouch

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

Fuad Ali

Speech and audio · Observability and reliability · Evals

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

Kevin Madura

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

Marc Klingen

Agent engineering · Observability and reliability · Evals

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

Aliisa Rosenthal

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

Jeff Koss · Leo Platzer

Knowledge curation · RAG, context, and search · Knowledge freshness

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

Ajay Prakash

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

Harshul Jain · Tanmay Sah

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

Jan Curn

APIs, MCP, and protocols · Agent engineering · Context windows

Stop Prompting — Greg Pstrucha, Sentry

Greg Pstrucha

Coding agents · Developer workflows and testing · Custom lint rules

Giving AI Agents Memory That Learns — Jake Broekhuizen, LangChain

Jake Broekhuizen

Agent engineering · Agent memory · Skill improvement loops

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

Connor Guerrero · Young Jeong · Nikhil Gupta

Infrastructure and deployment · Observability and reliability · Architecture

Dashboards Are Dead — Sarah Simionescu, Composio

Sarah Simionescu

APIs, MCP, and protocols · Agent engineering · Context windows

Agent Frameworks Considered Harmful — Rémi Louf, .txt

Rémi Louf

I Gave an AI a Body — Cyrus Clarke, MIT Media Lab

Cyrus Clarke

AI embodiment · Shape displays · Gesture vocabulary

Voice Agents Can Just Do Things — Charlie Guo, OpenAI

Charlie Guo