The talk archive.

Your Support Team Should Ship Code

Lisa Orr

Developer workflows and testing · Leadership · APIs, MCP, and protocols

Your Voice Agent Doesn't Need a Frontier Model

Joel Allou · Ornella Bahidika

Speech and audio · Agent engineering · Safety and governance

ACP: The Universal Remote Control for AI Agents — Alex Hancock, Block

Alex Hancock

The Human Is an Async API — Melanie Warrick, Temporal

Melanie Warrick

Agent engineering · Agent orchestration · Human-in-the-loop validation

I Monitored Crime Audio. Voice Agents Scare Me More. — Sumanyu Sharma, Hamming AI

Sumanyu Sharma

Agents Without Code: Skills, YAML, and Filesystems Replaced Python — Philipp Schmid, Google DeepMind

Philipp Schmid

The unreasonable effectiveness of BM25 for agentic search — Jo Kristian Bergum, Hornet.dev

Jo Kristian Bergum

Agentic search · BM25 and top-K retrieval · BrowseComp+

Your company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL

Tanmai Gopal

Mousepower: agents that can’t be measured, can’t be managed. — Maximillian Piras, Yutori

Maximillian Piras

AI-Generated Code Is Already Competing With Human Code — Daksh Gupta, Greptile

Daksh Gupta

How I Learned to Stop Worrying and Love the Sandbox — Matt Brockman, E2B

Matt Brockman

MicroVM isolation · Infrastructure and deployment · Observability and reliability

MCP Apps: Give the Model Data, Give the User a UI — Dustin Mihalik, Indeed

Dustin Mihalik

Agents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, Navan

Roberto Milev · Uday Kanagala

Long-Horizon Agents Need Experiments, Not Just Prompts — Erina Karati

Erina Karati

The Search Engine for the Agentic Web — Will Bryk, Exa

Will Bryk

Agent search · RAG, context, and search · Search latency

Tribal Dungeons of Global Shipping: AI Agents at Global Scale — Dmitry Buykin, Maersk

Dmitry Buykin

KV Cache-Aware Routing and P/D Disaggregation on Kubernetes — Yuchen Fama & Ashish Kamra, Red Hat

Yuchen Fama · Ashish Kamra

Building GTM AI Agents: Lessons from Deploying to 6,000 Users — Sait Izmit, Snowflake

Sait Izmit

Why LLM Recommenders Will Be AI's Biggest Consumer App — Devansh Tandon, Meta

Devansh Tandon

Vertical Mobility: Inference from MVP to Trillion-Parameter Workloads — Sitanshu Gupta, CoreWeave

Sitanshu Gupta

Autoresearch Made Our Models 3x Faster — Tejas Bhakta, Morph

Tejas Bhakta

One Designer + AI. Hundreds of Deliverables. — Vincent Wendy, AI Engineer

Vincent Wendy

The Missing Layer in Agentic AI — Giedrius Šteimantas, Oxylabs

Giedrius Šteimantas

Stop Fine-Tuning to Fix Retrieval Problems — Anant Srivastava

Anant Srivastava

Architecture · RAG and knowledge systems · Fine-tuning

AI in GTM at Notion — Flora Liu

Flora Liu

Generative UI... in Python? — Jeremiah Lowin, Prefect

Jeremiah Lowin

Pinecone 2.0 — Edo Liberty, Pinecone

Edo Liberty

Theory of mind · Tribal knowledge · RAG and knowledge systems

The Building Blocks of GTM Orchestration — Arman Vaziri, Ramp

Arman Vaziri

Every step you take, every call you make: the reliable agent stack — Giselle van Dongen, Restate

Giselle van Dongen

The Agentic Commerce Stack — Ahnaf Prio, Best Buy

Ahnaf Prio

Your Agreements Are a Database You Can't Query — Hiral Shah, Docusign & Sean Sodha, NVIDIA

Hiral Shah · Sean Sodha

Enterprise agreement data · Nemotron Parse · Contract table extraction

The Spatial Harness: Bringing Agents to the Canvas — Max Drake, tldraw

Max Drake

Tokens Should Have Jobs — Katelyn Lesse & Angela Jiang, Anthropic

Katelyn Lesse · Angela Jiang

Which AI startups actually land enterprise contracts? — Brian Lewis, Millennium

Brian Lewis

Large clusters for small models — Daniel Svonava, Superlinked

Daniel Svonava

No Memory, No Harness: Why the Database Is the Last Line of Defense — Kay Malcolm, Oracle

Kay Malcolm