AI Engineer World's Fair 2025

ComfyUI

Tue 3 Jun, 09:00 – 09:50·Salons 2-6: Workshops

Quick introduction to ComfyUI and what's new followed by a QA session.

• CA Comfy Anonymous Original creator of ComfyUI

Advanced: Reinforcement Learning, Kernels, Reasoning, Quantization & Agents

Tue 3 Jun, 09:00 – 12:00·Foothill C: Workshops

Why is Reinforcement Learning (RL) suddenly everywhere, and is it truly effective? Have LLMs hit a plateau in terms of intelligence and capabilities, or is RL the breakthrough they… Show more

• DH Daniel Han CEO

Intro to GraphRAG

Tue 3 Jun, 09:00 – 10:20·Golden Gate Ballroom C: Workshops

Learn the foundations of GraphRAG, starting with knowledge graph construction and then common retrieval patterns.

• ZB Zach Blumenfeld Graph Data Science & AI Specialist, Neo4j

A2A & MCP: Automating Business Processes with LLMs

Tue 3 Jun, 09:00 – 10:20·Foothill G1&2: Workshops

Ever wished your webhooks could think for themselves? Join us to discover how A2A agents can transform passive webhook endpoints into intelligent workflow processors. In this… Show more

• DM Damien Murphy Founding Engineer

Introduction to LLM serving with SGLang

Tue 3 Jun, 09:00 – 10:20·SOMA: Workshops

Do you want to learn how to serve models like DeepSeek and Qwen with SOTA speeds on launch day? SGLang is an open-source fast serving framework for LLMs and VLMs that generates… Show more

• PK Philip Kiely Head of Developer Relations
• YZ Yineng Zhang Inference lead at SGLang

Beyond Benchmarks: Strategies for Evaluating LLMs in Production

Tue 3 Jun, 09:00 – 10:20·Nobhill A&B: Workshops

Accuracy scores and leaderboard metrics look impressive—but production-grade AI requires evals that reflect real-world performance, reliability, and user happiness. Traditional… Show more

• TJ Taylor Jordan Smith Senior Developer Advocate

Useful General Intelligence

Tue 3 Jun, 09:30 – 10:30·Golden Gate Ballroom B: Workshops

We’re all hearing that AI agents will enable AGI, but they can’t yet reliably perform even basic computer tasks. It turns out that getting AI to click, type, and scroll is more… Show more

• DP Danielle Perszyk Cognitive Scientist, PhD

Forget RAG Pipelines—Build Production-Ready AI Agents in 15 Minutes

Tue 3 Jun, 09:45 – 10:45·Golden Gate Ballroom A: Workshops

Want to take advantage of your data, but don't want to reinvent RAG infrastructure? Join our workshop and see how you can deploy Agentic RAG in minutes using Contextual AI's… Show more

• NL Nina Lopatina Lead Developer Advocate
• RS Rajiv Shah Chief Evangelist

The AI Engineer’s Guide to Raising VC

Tue 3 Jun, 09:55 – 10:20·Salons 2-6: Workshops

A no fluff, all tactics discussion. More AI engineers should build startups, the world needs more software. But there’s a way to raise VC and it’s hard to do it if you’ve never… Show more

• DG Dani Grant CEO
• CT Chelcie Taylor Investor

Mastering AI Evaluation: From Playground to Production with Braintrust

Tue 3 Jun, 10:40 – 12:00·Golden Gate Ballroom C: Workshops

This hands-on workshop will guide participants through the complete AI evaluation lifecycle using Braintrust, from initial prompt testing to production monitoring. Attendees will… Show more

• DG Doug Guthrie Solutions Engineer, Braintrust

Automating Escrow with USDC and AI

Tue 3 Jun, 10:40 – 12:00·Golden Gate Ballroom B: Workshops

This workshop explores how USDC, AI, and smart contracts can streamline escrow by automating fund release based on task or process verification. By using AI to interpret off-chain… Show more

• CC Corey Cooper Developer Relations Manager @ Circle

Solving for the hardest Eval challenge: Building Metrics that actually work

Tue 3 Jun, 10:40 – 12:00·Foothill G1&2: Workshops

One of the biggest challenges in building evals you can trust is building metrics that reliably measure goodness in your application; metrics that are highly accurate, rapid fast,… Show more

• DK David Karam CEO

Ship Agents that Ship: A Hands-On Workshop for SWE Agent Builders

Tue 3 Jun, 10:40 – 12:00·Nobhill A&B: Workshops

Coding agents are transforming how software gets built, tested, and deployed, but engineering teams face a critical challenge: how to embrace this automation wave without… Show more

• KP Kyle Penfound Solutions Engineer at Dagger
• JA Jeremy Adams Head of Ecosystem

Piloting agents in GitHub Copilot

Tue 3 Jun, 10:40 – 12:00·Nobhill C&D: Microsoft

The agent capabilities added to GitHub Copilot have enhanced its ability to act as a peer programmer. Copilot can now discover and generate code based on existing standards, run… Show more

• CH Christopher Harrison Senior Developer Advocate

Building Multimodal AI Agents (From Scratch)

Tue 3 Jun, 10:40 – 12:00·SOMA: Workshops

In this hands-on workshop, you will build a multimodal AI agent capable of processing mixed-media content—from analyzing charts and diagrams to extracting insights from documents… Show more

• AJ Apoorva Joshi Senior AI Developer Advocate, MongoDB

Building Voice Agents with Gemini and Pipecat

Tue 3 Jun, 11:00 – 12:00·Golden Gate Ballroom A: Workshops

Voice AI Agents are being deployed today in a wide range of business contexts. For example: - handling an increasing variety of call center tasks, - collecting patient data… Show more

• SB Shrestha Basu Mallick Product lead, Gemini Developer API
• KK Kwindla Kramer CEO

Build multilingual Conversational AI Agents

Tue 3 Jun, 11:15 – 12:15·Salons 2-6: Workshops

In this workshop you will learn how to build multilingual Conversational AI agents that can automatically detect your user's spoken language and can seamlessly switch to their… Show more

• T雷 Thor 雷神 Schaeff DX at ElevenLabs

How LLMs work for Web Devs: GPT in 600 lines of Vanilla JS

Tue 3 Jun, 12:00 – 13:00·Golden Gate Ballroom A: Workshops

Don't be intimidated. Modern AI can feel like magic, but underneath the hood are principles that web developers can understand, even if you don't have a machine learning… Show more

• IA Ishan Anand AI Consultant and educator

AI Engineering with the Google Gemini 2.5 Model Family

Tue 3 Jun, 13:00 – 15:00·SOMA: Workshops

Hands on Workshop on learning to use Gemini 2.5 Pro in combination with Agentic tooling and MCP Servers.

• PS Philipp Schmid AI Developer Experience

Information Retrieval from the Ground Up

Tue 3 Jun, 13:00 – 15:00·Foothill G1&2: Workshops

Vector search is only a feature. Search engines and information retrieval have retaken their position as the foundation of RAG. This workshop takes you through decades of research,… Show more

• PK Philipp Krenn Code and conference monkey

From Mixture of Experts to Mixture of Agents … with Super Fast Inference

Tue 3 Jun, 13:00 – 15:00·Nobhill A&B: Workshops

Our hands-on workshop will walk you through how to build your own Mixture of Agents (MoA) system using the fastest, and most capable open models available: Qwen3-32B and Llama… Show more

• DK Daniel Kim Head of Growth, Cerebras
• DS Daria Soboleva Head Research Scientist, Cerebras

Real-World Development with GitHub Copilot and VS Code

Tue 3 Jun, 13:00 – 15:00·Salons 2-6: Workshops

Join us for a hands-on workshop designed to demonstrate how VS Code and GitHub Copilot's expanding suite of AI features can match or even surpasses the benefits of other popular AI… Show more

• HK Harald Kirschner VS Code Team Member
• CH Christopher Harrison Senior Developer Advocate

Model-Maxxing: RFT, DPO, SFT (Fine-tuning with OpenAI)

Tue 3 Jun, 13:00 – 15:00·Golden Gate Ballroom B: Workshops

Covering all forms of fine-tuning and prompt engineering, like SFT, DPO, RFT, prompt engineering / optimization, and agent scaffolding.

• IB Ilan Bigio Developer Experience

Building Agents with Amazon Nova Act and MCP

Tue 3 Jun, 13:00 – 15:00·Golden Gate Ballroom A: Workshops

In this 2-hour workshop, participants will gain practical hands-on experience building sophisticated AI agents using Amazon's agent technologies. You'll learn to build agents that… Show more

• DL Duan Lightfoot AWS, Sr. Cloud Networking Developer Advocate

Graph Intelligence: Enhance Reasoning and Retrieval Using Graph Analytics

Tue 3 Jun, 13:00 – 15:00·Golden Gate Ballroom C: Workshops

Advanced GraphRAG techniques apply graph ML and algorithms, wrapped into tidy notebooks.

• AC Alison Cossette Data Science Strategist, Advocate, Educator
• AK Andreas Kollegger GenAI Lead

Case Study + Deep Dive: Telemedicine Support Agents with LangGraph/MCP

Tue 3 Jun, 13:00 – 15:00·Foothill C: Workshops

We've all seen website chat bots which can look up an order or answer a basic question -- but what does it take to build autonomous agents which manage long, delicate processes… Show more

• DM Dan Mason Principal, Head of AI

AI Red-Teaming and Prompt Engineering

Tue 3 Jun, 15:30 – 17:30·SOMA: Workshops

Learn about learnprompting.org and HackAPrompt, the first guide on prompt engineering in the world and the first competition on prompt injection respectively. I will give a… Show more

• SS Sander Schulhoff CEO

AI Pipelines and Agents in Pure TypeScript with Mastra.ai

Tue 3 Jun, 15:30 – 17:30·Salons 2-6: Workshops

This hands-on workshop introduces Mastra.ai, a TypeScript framework that streamlines the development of agentic AI systems compared to traditional approaches using LangChain and… Show more

• NN Nick Nisi Software developer and panelist on the JS Party podcast
• ZP Zack Proser Open source hacker. Dev Education at WorkOS

Agentic Coding with Windsurf

Tue 3 Jun, 15:30 – 17:30·Golden Gate Ballroom A: Workshops

Agentic coding marks a new era in software development, where AI agents take on autonomous roles in coding tasks. The Windsurf IDE embodies this shift by integrating intelligent… Show more

• NB Numair Baseer Deployed Engineer, Windsurf

Building voice agents with OpenAI

Tue 3 Jun, 15:30 – 17:30·Golden Gate Ballroom B: Workshops

We'll walk through the differences between chained and speech-to-speech powered voice agents, how to approach them, best practices and transform a text-based agent into our first… Show more

• DK Dominik Kundel Developer Experience

How to build world-class AI products (featuring Sarah Sachs, AI lead @ Notion)

Tue 3 Jun, 15:30 – 17:30·Golden Gate Ballroom C: Workshops

Join us for a hands-on workshop where you'll learn practical strategies to evaluate AI applications throughout their lifecycle—from initial testing of prompts to ongoing monitoring… Show more

• CE Carlos Esteban Solutions Engineer, Braintrust

Navigating deep context in legacy code with Augment Agent

Tue 3 Jun, 15:30 – 17:30·Foothill C: Workshops

Attendees will learn to use an AI coding agent as a fast and intuitive part of navigating and working with complex, production-grade legacy code bases. We will drop directly into… Show more

• FB Forrest Brazeal Speaker and Workshop Organizer
• MB Matt Ball Empowering Developers with AI

VoiceVision RAG - Integrating Visual Document Intelligence with Voice Response

Tue 3 Jun, 15:30 – 17:30·Foothill G1&2: Workshops

In this workshop we will explore the integration of Colpali, a cutting-edge Vision based Retrieval Model, with voice synthesis for next-generation RAG systems. We'll demonstrate… Show more

• SD Suman Debnath Principal Developer Advocate, AI/ML, AWS

Shipping AI That Works: An Evaluation Framework for PMs

Tue 3 Jun, 15:30 – 17:30·Nobhill A&B: Workshops

GenAI is reshaping the product landscape, creating huge opportunities (along with new expectations) for product managers. Yet while prompt engineering and model tuning get the… Show more

• AK Aman Khan Director of Product

Spark to System: Building the Open Agentic Web

Wed 4 Jun, 09:20 – 09:40·Keynote/General Session (Yerba Buena 7&8)

AI builders no longer ask whether to use agents—but how many and how fast. In this kickoff keynote, Microsoft’s Asha Sharma shows what happens when natural language creation meets… Show more

• AS Asha Sharma CVP, Head of Product, Microsoft AI Platform

Conviction Session

Wed 4 Jun, 09:40 – 10:00·Keynote/General Session (Yerba Buena 7&8)

Please Fill in

• SG Sarah Guo

Simon Willison Keynote

Wed 4 Jun, 10:00 – 10:20·Keynote/General Session (Yerba Buena 7&8)

• SW Simon Willison

Realtime conversational video with Pipecat and Tavus

Wed 4 Jun, 10:40 – 10:55·Juniper: Expo Sessions

Tavus shipped the world's first realtime video avatar platform last year. Developers use Tavus' conversational video APIs to create education, social, and customer support agents.… Show more

• CB Chad Bailey Senior Voice Bots Engineer, Daily
• BJ Brian Johnson Staff Engineer, Tavus

Architecting Agent Memory: Principles, Patterns, and Best Practices

Wed 4 Jun, 10:40 – 10:55·Willow: Expo Sessions

In the rapidly evolving landscape of agentic systems, memory management has emerged as a key pillar for building intelligent, context-aware AI Agents. Inspired by the complexity of… Show more

• RA Richmond Alake Staff Developer Advocate, AI/ML at MongoDB

AI-powered entomology: Lessons from millions of AI code reviews

Wed 4 Jun, 10:40 – 10:55·Nobhill A&B: Expo Sessions

This talk will explore insights from millions of automated code reviews, revealing trends in bugs, vulnerabilities, and code health that Graphite’s AI code review agent have… Show more

• TR Tomas Reimers Graphite CPO & Co-founder

Vibe Coding in Production

Wed 4 Jun, 10:55 – 11:10·Juniper: Expo Sessions

What's the role of vibe coding in a production-grade applications? Join Augment Code's Matt McClernan as he speaks to engineering leaders about building with AI.

• CK Chris Kelly All Things Developer @ Augment Code

What does Enterprise Ready MCP mean?

Wed 4 Jun, 10:55 – 11:10·Willow: Expo Sessions

Everyone is building MCP servers: from Slack integrations to personal data tools. They're good demos, but not ready to turn into production. So, what does it take to make MCP… Show more

• TS Tobin South Secure AI Agents & MCP, WorkOS

Mastering Engineering Flow with Windsurf

Wed 4 Jun, 10:55 – 11:10·Nobhill A&B: Expo Sessions

As experienced engineers, especially senior and staff engineers, our focus shifts towards complex problem-solving, architectural decisions, and mentoring. While AI tools promise… Show more

• ES Eashan Sinha Deployed Engineer, Windsurf

AI Automation that actually works: $100M, messy data, zero surprises

Wed 4 Jun, 11:15 – 11:35·Foothill C: Agent Reliability

We will review the different kinds of automation use-cases, and the approach we used, that will drive over a $100M of expected annual impact by deploying AI for business critical… Show more

• TG Tanmai Gopal CEO, Co-founder

[PM Keynote] Everything is ugly so go build something that isn't

Wed 4 Jun, 11:15 – 11:35·Foothill G 1&2: Product Management

We're in an awkward adolescent phase of AI product (design). But what if this chaotic moment is actually our greatest opportunity? Enter the rebuilding revolution. In this talk,… Show more

• RM Raiza Martin CEO & Co-Founder Huxe || Previously NotebookLM

What every AI engineer needs to know about GPUs

Wed 4 Jun, 11:15 – 11:35·Foothill F: Infrastructure

Every programmer needs to know a few things about hardware, like processors, memory, and disks. Due to AI systems' extreme demand for mathematical processing power, AI engineers… Show more

• CF Charles Frye Developer Advocate, Modal Labs

[Voice Keynote] Your realtime AI is ngmi

Wed 4 Jun, 11:15 – 11:35·Foothill E: Voice

Sean DuBois of OpenAI and Pion, and Kwindla Hultman Kramer of Daily and Pipecat, will talk about why you have to design realtime AI systems from the network layer up. Most… Show more

• KK Kwindla Kramer CEO
• SD Sean DuBois WebRTC and Realtime API

MCP Origins & RFS

Wed 4 Jun, 11:15 – 11:35·Yerba Buena Ballroom Salons 7-8: MCP

Learn more about the latest updates on MCP and get ideas for what startups to build.

• TC Theodora Chu Product Manager for MCP @ Anthropic

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

Wed 4 Jun, 11:15 – 11:35·Golden Gate Ballroom B: GraphRAG

Interpreting complex information from unstructured text data poses significant challenges to Large Language Models (LLM), with difficulties often arising from specialized… Show more

• MP Mitesh Patel Developer Advocate Manager

Recsys Keynote: Improving Recommendation Systems & Search in the Age of LLMs

Wed 4 Jun, 11:15 – 11:35·Golden Gate Ballroom A: LLM RecSys

Recommendation systems and search have long adopted advances in language modeling, from early adoption of Word2vec for embedding-based retrieval to the transformative impact of… Show more

• EY Eugene Yan Principal Applied Scientist

From Copilot to Colleague: Building Trustworthy Productivity Agents for High-Stakes Work

Wed 4 Jun, 11:15 – 11:35·Golden Gate Ballroom C: AI in the Fortune 500

This keynote will explore what it takes to move from basic generative assistants to fully agentic AI—systems that don’t just suggest but plan, act, and adapt—all within the… Show more

• JH Joel Hron CTO

Rise of the AI Architect

Wed 4 Jun, 11:15 – 11:35·SOMA: AI Architects

As the amount of consumer facing AI products grows, the most forward leaning enterprises have created a new role: the AI Architect. These leaders are responsible for helping… Show more

• AF Alessio Fanelli Co-Host, Latent Space
• CB Clay Bavor Cofounder, Sierra

12 Factor Agents - Principles of Reliable LLM Applications

Wed 4 Jun, 11:35 – 11:55·Foothill C: Agent Reliability

Hi, I'm Dex. I've been hacking on AI agents for a while. I've tried every agent framework out there, from the plug-and-play crew/langchains to the "minimalist" smolagents of the… Show more

• DH Dexter Horthy Founder

What we learned from shipping remote MCP support at Anthropic

Wed 4 Jun, 11:35 – 11:55·Yerba Buena Ballroom Salons 7-8: MCP

We recently released remote MCP support for both claude.ai and the Anthropic API. This talk will cover architectural decisions we made in our implementation, remote MCP… Show more

• JW John Welsh Member of technical staff, Anthropic

The New Lean Startup

Wed 4 Jun, 11:35 – 11:55·Yerba Buena Ballroom Salons 2-6: Tiny Teams

In this session, I will be presenting a case study of Oleve's journey, revealing how we've scaled a profitable multi-product portfolio with a tiny team. I'll walk you through the… Show more

• SB Sid Bendre Co-Founder

What We Learned from Using LLMs in Pinterest Search

Wed 4 Jun, 11:35 – 11:55·Golden Gate Ballroom A: LLM RecSys

Pinterest Search integrates Large Language Models (LLMs) to enhance relevance scoring by combining search queries with rich multimodal content, including visual captions,… Show more

• MN Mukuntha Narayanan Machine Learning Engineer
• HW Han Wang Machine Learning Engineer

Wisdom Discovery at Scale: Code Less KAG with n8n MultiAI Agents

Wed 4 Jun, 11:35 – 11:55·Golden Gate Ballroom B: GraphRAG

"Wisdom Discovery at Scale: Code Less KAG with n8n MultiAI Agents"

• CK Chin Keong Lam AI Engineer & Co-Founder

Accelerating Investment Operations: How BlackRock Builds Custom Knowledge Apps at Scale.

Wed 4 Jun, 11:35 – 11:55·Golden Gate Ballroom C: AI in the Fortune 500

Investment Operations teams are the backbone of asset and investment management firms. Their day-to-day work not only enables portfolio managers to respond swiftly to market events… Show more

• VP Vaibhav Page Principal Engineer
• IV Infant Vasanth Senior Director of Engineering

Building Applications with AI Agents

Wed 4 Jun, 11:35 – 11:55·SOMA: AI Architects

Generative AI has dramatically shortened the distance between ideas and implementation, enabling faster prototyping and deployment than ever before. But while language models can… Show more

• MA Michael Albada Principal Applied Scientist

Why your product needs an AI product manager, and why it should be you

Wed 4 Jun, 11:35 – 11:55·Foothill G 1&2: Product Management

So you've built another cool demo. Now what? You have hype, but not impact. You have kudos but no users. Ultimately you have a demo, but not a product. The unique uncertainty of… Show more

• JL James Lowe Head of AI Engineering

Why We Don’t Need More Data Centers

Wed 4 Jun, 11:35 – 11:55·Foothill F: Infrastructure

AI infrastructure today is caught in an endless cycle: build more data centers, deploy more GPUs, repeat. But this approach is fundamentally flawed—expensive, inefficient, and… Show more

• DJ Dr. Jasper Zhang, PhD CEO

Shipping an Enterprise Voice AI Agent in 100 Days

Wed 4 Jun, 11:35 – 11:55·Foothill E: Voice

What does it take to go from blank page to live enterprise voice agent in 100 days? That’s the challenge we took on with Fin Voice at Intercom. Enterprise customer service… Show more

• PB Peter Bar Product Lead, Voice AI

Using OSS models to build AI apps with millions of users

Wed 4 Jun, 11:55 – 12:15·Yerba Buena Ballroom Salons 2-6: Tiny Teams

In this talk, Hassan will go over how he builds open source AI apps that get millions of users like roomGPT.io (2.9 million users), restorePhotos.io (1.1 million users),… Show more

• HE Hassan El Mghari DevRel lead

360Brew LLM-based Foundation Model for Personalized Ranking and Recommendation

Wed 4 Jun, 11:55 – 12:15·Golden Gate Ballroom A: LLM RecSys

We will give a talk about our journey of building a foundation model for solving ranking and recommendation tasks across LinkedIn platform

• HF Hamed Firooz Principal Scientist -- LinkedIn Core AI
• MS Maziar Sanjabi LinkedIn AI, Principal Scientist

How agents will unlock the $500B promise of AI

Wed 4 Jun, 11:55 – 12:15·Golden Gate Ballroom C: AI in the Fortune 500

AI agents are on the cusp of revolutionizing work as we know it. The number of use cases software can tackle is set to explode as AI handles tasks requiring real judgment. But to… Show more

• DH Donald Hruska Engineering lead for Retool Agents

The Rise of Open Models in the Enterprise

Wed 4 Jun, 11:55 – 12:15·SOMA: AI Architects

This year kicked off with the DeepSeek-R1 news cycle breaking out of our AI Engineering bubble into the mainstream tech and business world. Leaders at the highest levels of the… Show more

• AH Amir Haghighat CTO

Scaling AI agents without breaking reliability

Wed 4 Jun, 11:55 – 12:15·Foothill C: Agent Reliability

As AI agents move from prototypes to production, developers are running into new challenges with orchestration, failure handling, and infrastructure. This session will unpack… Show more

• PS Preeti Somal SVP Engineering

Shipping something to someone always wins

Wed 4 Jun, 11:55 – 12:15·Foothill G 1&2: Product Management

Learnings from building products at Stripe and applying them in an AI native word

• KA Kenneth Auchenberg Partner at AlleyCorp l, ex Product Lead at Stripe, Microsoft (VS Code)

Large Scale AI on Apple Silicon using EXO

Wed 4 Jun, 11:55 – 12:15·Foothill F: Infrastructure

The hardware lottery: when a research idea wins because it is better suited to current hardware and software, and not because it is universally superior. Machine learning… Show more

• AC Alex Cheema Co-Founder

What we can learn from self driving in autonomous voice agents

Wed 4 Jun, 11:55 – 12:15·Foothill E: Voice

The reliability challenges facing voice & chat AI deployment today mirror those that the autonomous vehicle industry confronted years ago. This talk explores how evaluation… Show more

• BH Brooke Hopkins Founder

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

Wed 4 Jun, 11:55 – 12:15·Golden Gate Ballroom B: GraphRAG

Enterprise knowledge bases are filled with "dense mapping," thousands of documents where similar terms appear repeatedly, causing traditional vector retrieval to return the wrong… Show more

• SJ Sam Julien Director of Developer Relations

Full Spectrum MCP: Uncovering Hidden Servers and Clients Capabilities

Wed 4 Jun, 11:55 – 12:15·Yerba Buena Ballroom Salons 7-8: MCP

The true power of Model Context Protocol emerges when clients and servers collaborate across the full spectrum of the specification. This talk presents practical examples of how VS… Show more

• HK Harald Kirschner VS Code Team Member

Stop Using RAG as Memory

Wed 4 Jun, 12:15 – 12:35·Golden Gate Ballroom B: GraphRAG

RAG is great for static knowledge retrieval—but terrible at memory. Vectorstore-based systems sold as memory lack relational and temporal awareness, leading agents astray with… Show more

• DC Daniel Chalef Founder, Zep AI

3 ingredients for building reliable enterprise agents

Wed 4 Jun, 12:15 – 12:35·Golden Gate Ballroom C: AI in the Fortune 500

It's easy to build a prototype of an agent, but hard to put an agent in production - especially in an enterprise setting. In this section, will talk about three ingredients for… Show more

• HC Harrison Chase CEO

Production software keeps breaking and it will only get worse. Here’s how Traversal is fixing it.

Wed 4 Jun, 12:15 – 12:35·Foothill C: Agent Reliability

Software is eating the world. AI is eating software. AI-powered SWE means a whole lot more software is going to be written that powers mission critical systems in the coming years,… Show more

• AA Anish Agarwal CEO and Co-founder
• MS Matthew Schoenbauer Founding Engineer
• RA Raj Agrawal CTO, Cofounder
• RD Raaz Dwivedi Chief Scientist

Survive the AI Knife-Fight: Building Products That Win

Wed 4 Jun, 12:15 – 12:35·Foothill G 1&2: Product Management

If you’ve ever been blocked by vague specs, shifting goals, or chasing “vibes,” things have only gotten messier in the age of AI. Everyone is obsessing over engineers doing PM work… Show more

• BB Brian Balfour Founder & CEO, Reforge

Serving Voice AI at $1/hr: Open-source, LoRAs, Latency, Load Balancing

Wed 4 Jun, 12:15 – 12:35·Foothill E: Voice

This is a talk that goes over our experience deploying Orpheus (Emotive, Realtime TTS) to production. It will cover topics: - Latency and optimizations - High fidelity voice… Show more

• ND Neil Dwyer CTO
• JD Jack Dwyer CEO @ Gabber - End to End Backend For Realtime AI

MCP isn’t good, yet.

Wed 4 Jun, 12:15 – 12:35·Yerba Buena Ballroom Salons 7-8: MCP

You’ve heard a lot about MCP, probably been given an AI mandate or two, and are trying to figure out what’s real and what’s make believe. This session will give practical… Show more

• DC David Cramer Founder, Sentry

Gumloop's Path to be a 10 person unicorn

Wed 4 Jun, 12:15 – 12:35·Yerba Buena Ballroom Salons 2-6: Tiny Teams

An overview of how Gumloop is scaling automation across companies like Instacart, Webflow and Shopify with less than 10 people.

• MB Max Brodeur-Urbas Founder and CEO of Gumloop

AI Red Teaming Agent: Accelerate your AI safety and security journey with Azure AI Foundry

Wed 4 Jun, 12:45 – 13:05·Nobhill C&D: Microsoft

In the age of autonomous AI agents, ensuring their safety and reliability is paramount. But how can we proactively uncover vulnerabilities before they impact real-world scenarios?… Show more

• NA Nagkumar Arkalgud Senior Software Engineer
• KK Keiji Kanazawa Product @ Azure AI Foundry

How fast are LLM inference engines anyway?

Wed 4 Jun, 12:45 – 13:00·Juniper: Expo Sessions

Open weights models and open source inference servers have made massive strides in the year since we last got together at AIE World's Fair. Where once we had only pirated LLaMA… Show more

• CF Charles Frye Developer Advocate, Modal Labs

How to trust an agent with software delivery

Wed 4 Jun, 12:45 – 13:00·Willow: Expo Sessions

AI-powered agents promise faster, easier software delivery, but their unpredictable behavior often makes engineers hesitant to fully trust them with critical workflows. Sam Alba,… Show more

• SA Sam Alba Co-Founder of Dagger

Events are the Wrong Abstraction for Your AI Agents

Wed 4 Jun, 13:00 – 13:15·Willow: Expo Sessions

AI Agents are distributed systems. Agents need to connect and communicate with tools, data repositories, other agents, etc., all over a network. Event-Driven Architecture is a… Show more

• ME Mason Egger Sr. Developer Advocate - Temporal

Effective agent design patterns in production

Wed 4 Jun, 13:00 – 13:15·Juniper: Expo Sessions

At LlamaIndex we see a lot of agents built every day, and we've got a sense of what works and what doesn't. We've distilled those learnings down into a series of patterns and best… Show more

• LV Laurie Voss VP Developer Relations, LlamaIndex

Agentic Excellence: Mastering Evaluation of AI Agents with Azure AI Evaluation SDK

Wed 4 Jun, 13:10 – 13:30·Nobhill C&D: Microsoft

As AI agents transition from experimental assistants to critical components of enterprise workflows, reliably evaluating their performance becomes essential. But how do you… Show more

• CV Cedric Vidal Principal AI Advocate

Revenue Engineering: How to Price (and Reprice) Your AI Product

Wed 4 Jun, 13:15 – 13:30·Juniper: Expo Sessions

You’ve trained the model—now it’s time to train the business. This talk dives into the engineering behind pricing systems that can evolve as fast as your AI stack. Orb CTO… Show more

• KG Kshitij Grover Co-Founder & CTO, Orb Inc.

Agentic GraphRAG: AI’s Logical Edge

Wed 4 Jun, 13:30 – 13:45·Willow: Expo Sessions

AI models are getting tasked to do increasingly complex and industry specific tasks where different retrieval approaches provide distinct advantages in accuracy, explainability,… Show more

• SC Stephen Chin VP of Developer Relations

One model to rule recommendations: Netflix's Big Bet

Wed 4 Jun, 14:00 – 14:20·Golden Gate Ballroom A: LLM RecSys

Discuss the foundation model strategy for personalization at Netflix based on this post https://netflixtechblog.com/foundation-model-for-personalized-recommendation-1a0bd8e02d39… Show more

• YF Yesu Feng Netflix, Staff Research Scientist

Practical GraphRAG - Making LLMs smarter with Knowledge Graphs

Wed 4 Jun, 14:00 – 14:20·Golden Gate Ballroom B: GraphRAG

RAG has become one standard architecture component for GenAI applications to address hallucinations and integrate factual knowledge. While vector search over text is common,… Show more

• MH Michael Hunger VP of Product Innovation
• JB Jesús Barrasa AI Field CTO
• SC Stephen Chin VP of Developer Relations

Building an Agentic Platform

Wed 4 Jun, 14:00 – 14:20·Golden Gate Ballroom C: AI in the Fortune 500

Explore the technical evolution of metadata extraction at Box and how it shaped the foundation of our AI platform. We’ll walk through our transition to an agentic-first design—why… Show more

• BK Ben Kus CTO

AI That Pays: Lessons from Revenue Cycle

Wed 4 Jun, 14:00 – 14:20·SOMA: AI Architects

While much of the AI innovation in healthcare has centered on clinical and patient-facing applications, Revenue Cycle Management (RCM) remains an underexplored yet critical domain.… Show more

• NW Nathan Wan Head of AI

How to build Enterprise-aware agents

Wed 4 Jun, 14:00 – 14:20·Foothill C: Agent Reliability

While LLMs demonstrated impressive reasoning capabilities, their out-of-the-box reasoning is akin to hiring a brilliant but brand-new employee who doesn’t have the enterprise… Show more

• CT Chau Tran Technical Lead Delete

Shipping Products When You Don’t Know What they Can Do

Wed 4 Jun, 14:00 – 14:20·Foothill G 1&2: Product Management

A customer recently asked me: “Hey, can I tag your AI agent in a Google Doc comment?” The honest answer: I have no idea! We never designed our agents to handle Google Doc… Show more

• BS Ben Stein CEO

[Infra Keynote] Geopolitics of AI Infrastructure

Wed 4 Jun, 14:00 – 14:20·Foothill F: Infrastructure

As AI reshapes the global balance of power, the infrastructure behind it—chips, data centers, power, and supply chains—has become a new arena for geopolitical competition. This… Show more

• DP Dylan Patel Chief Analyst

Building the Voice-First Future: Omnipresent Agents that Listen, Talk and Act

Wed 4 Jun, 14:00 – 14:20·Foothill E: Voice

We’re entering a world where talking to machines feels as natural as talking to people. Voice is about to become the dominant interface for technology - ambient, always-on, and… Show more

• JD Jordan Dearsley CEO

Tiny Teams

Wed 4 Jun, 14:00 – 14:20·Yerba Buena Ballroom Salons 2-6: Tiny Teams

Sean reached out on X, happy to do a talk on how to build a tiny team

• GL Grant Lee CEO

MCP is all you need

Wed 4 Jun, 14:00 – 14:20·Yerba Buena Ballroom Salons 7-8: MCP

Everyone is talking about agents, and right after that, they’re talking about agent-to-agent communications. Not surprisingly, various nascent, competing protocols are popping up… Show more

• SC Samuel Colvin Founder of Pydantic

Instacart’s LLM-driven approach to Search and Discovery

Wed 4 Jun, 14:20 – 14:40·Golden Gate Ballroom A: LLM RecSys

• TT Tejaswi Tenneti Director of Machine Learning
• VG Vinesh Gudla Staff Machine Learning Engineer, Instacart

Multi-Agent AI and Network Knowledge Graphs for Change Management and Network Testing

Wed 4 Jun, 14:20 – 14:40·Golden Gate Ballroom B: GraphRAG

Traditional ticketing and testing workflows for change management and network operations often operate independently and lack critical real-world context and adaptive decision… Show more

• OM Ola Mabadeje Product Leader

The Billable Hour is Dead; Long Live the Billable Hour?

Wed 4 Jun, 14:20 – 14:40·Golden Gate Ballroom C: AI in the Fortune 500

If software was eating the world before, knowledge work will soon be devoured by AI. In corporate America there are thousands of hours spent on rote tasks every day by employees,… Show more

• KM Kevin Madura Director, Advanced Technologies
• MB Mo Bhasin Director of AI Products

Structuring a modern AI team

Wed 4 Jun, 14:20 – 14:40·SOMA: AI Architects

You've been given an AI mandate but don't have additional headcount, what next? Re-skilling, up-skilling and team augmentation become essential to delivering on a new mandate. In… Show more

• DL Denys Linkov Head of ML

Agents vs Workflows: Why Not Both?

Wed 4 Jun, 14:20 – 14:40·Foothill C: Agent Reliability

One current hot debate is should you make your top-level abstraction a ReAct type agent running in a loop? or should you make it a structured workflow graph? OpenAI is launching… Show more

• SB Sam Bhagwat Co-founder

Make your LLM app a Domain Expert: How to Build an LLM-Native Expert System

Wed 4 Jun, 14:20 – 14:40·Foothill G 1&2: Product Management

Vertical AI is a multi-trillion-dollar opportunity. But you can't build a domain-expert application simply by grabbing the latest LLMs off-the-shelf: you need a system for… Show more

• CL Christopher Lovejoy Head of Clinical AI

Hacking the Inference Pareto Frontier for Cheaper and Faster Tokens Without Breaking SLAs

Wed 4 Jun, 14:20 – 14:40·Foothill F: Infrastructure

Your model works! It aces the evals! It even passes the vibe check! All that’s required is inference, right? Oops, you’ve just stepped into a minefield: -Not low-latency enough?… Show more

• KK Kyle Kranen US Engineering Manager - Deep Learning Algorithms

Why ChatGPT Keeps Interrupting You

Wed 4 Jun, 14:20 – 14:40·Foothill E: Voice

ChatGPT Advanced Voice Mode isn’t interrupting just you. Interruptions, and turn-taking in general, are unsolved problems for all Voice AI agents. Nobody likes being cut short –… Show more

• TS Tom Shapland, PhD Product Manager

Observable tools - the state of MCP observability

Wed 4 Jun, 14:20 – 14:40·Yerba Buena Ballroom Salons 7-8: MCP

AI Engineers deserve observable tools! MCP getting adoption means that less and less of your agents code is running under your control, and this has DX and observability… Show more

• AV Alex Volkov AI Evangelist
• SM Steve Manuel CEO
• BE Benjamin Eckel Co-Founder of Dylibso

Building Small AI Teams with Huge Impact

Wed 4 Jun, 14:20 – 14:40·Yerba Buena Ballroom Salons 2-6: Tiny Teams

tbd

• VP Vikas Paruchuri CEO

Build Dynamic Products, and Stop the AI Sideshow

Wed 4 Jun, 14:40 – 15:00·Golden Gate Ballroom C: AI in the Fortune 500

AI across product, GTM, and strategy was a great approach in 2023, but by now, we all already know that AI is disrupting the global landscape and how business gets done. Now is the… Show more

• JS Jeremy Silva Product Lead
• EC Eliza Cabrera Principal AI Product Manager @ Workday

The rise of the agentic economy on the shoulders of MCP

Wed 4 Jun, 14:40 – 15:00·Yerba Buena Ballroom Salons 7-8: MCP

Thanks to MCP and all the MCP server directories, agents can now autonomously discover new tools and other agents. This lays down the foundation for the future agentic economy,… Show more

• JC Jan Curn CEO

Benchmarks Are Memes: How What We Measure Shapes AI—and Us

Wed 4 Jun, 14:40 – 15:00·Yerba Buena Ballroom Salons 2-6: Tiny Teams

Benchmarks shape more than just AI models—they shape our future. The things we choose to measure become self-fulfilling prophecies, guiding AI toward specific abilities and,… Show more

• AD Alex Duffy Head of AI

Teaching Gemini to Speak YouTube: Adapting LLMs for Video Recommendations to 2B+ DAU

Wed 4 Jun, 14:40 – 15:00·Golden Gate Ballroom A: LLM RecSys

YouTube recommendations drive the majority of video watch time for billions of daily users. Traditionally powered by large embedding models (LEMs), we're undertaking a fundamental… Show more

• DT Devansh Tandon Principal Product Manager

Beyond Documents: Implementing Knowledge Graphs in Legal Agents

Wed 4 Jun, 14:40 – 15:00·Golden Gate Ballroom B: GraphRAG

Structured Representations are pretty important in the law, where the relationships between clauses, documents, entities, and multiple parties matter. Structured Representation… Show more

• TS Tom Smoker Technical Founder

Building Effective Voice Agents

Wed 4 Jun, 14:40 – 15:00·SOMA: AI Architects

How to build production voice applications and learnings from working with customers along the way

• AK Anoop Kotha Applied AI

Vibe Coding, with Confidence

Wed 4 Jun, 14:40 – 15:00·Foothill C: Agent Reliability

Everyone wants to do Vibe Code, even large Enterprises. But how can we ensure that the generated code is well-grounded with the dev team's code and software development standards?… Show more

• IF Itamar Friedman CEO

Building the platform for agent coordination

Wed 4 Jun, 14:40 – 15:00·Foothill G 1&2: Product Management

Learn how we're evolving Linear into an operating system for engineering teams to ship product with agents as a first class citizen.

• TM Tom Moor Head of Engineering

Flipping the Inference Stack: Why GPUs Bottleneck Real-Time AI at Scale

Wed 4 Jun, 14:40 – 15:00·Foothill F: Infrastructure

AI inference today is stuck in a loop: throw more GPUs at the problem, scale horizontally, rinse and repeat. But that playbook is hitting a wall. Latency, cost, and energy grids… Show more

• RW Robert Wachen Co-founder of Etched

Milliseconds to Magic: Real‑Time Workflows using the Gemini Live API and Pipecat

Wed 4 Jun, 14:40 – 15:00·Foothill E: Voice

The Gemini Live API GA is now powered by Google's best cost-effective thinking model Gemini 2.5 Flash. We will do a deep dive on the capabilities that the Gemini Live API combined… Show more

• KK Kwindla Kramer CEO
• SB Shrestha Basu Mallick Product lead, Gemini Developer API

Taming Rogue AI Agents with Observability-Driven Evaluation

Wed 4 Jun, 15:15 – 15:30·Nobhill A&B: Expo Sessions

LLM agents often drift into failure when prompts, retrieval, external data, and policies interact in unpredictable ways. This session introduces a repeatable, metric-driven… Show more

• JB Jim Bennett Principal Developer Advocate at Galileo

Vector Search Benchmark[eting]

Wed 4 Jun, 15:15 – 15:30·Willow: Expo Sessions

Every vector database out there is both faster and slower than any other competitor — if you believe all the benchmarketing out there. Let's turn the marketing into useful… Show more

• PK Philipp Krenn Code and conference monkey

Data is Your Differentiator: Building Secure and Tailored AI Systems

Wed 4 Jun, 15:30 – 15:45·Juniper: Expo Sessions

As organizations seek to harness their proprietary data while maintaining security and compliance, Amazon Bedrock provides a comprehensive framework for building tailored AI… Show more

• MK Mani Khanuja Principal ML Services SA

Polar Signals Expo Session

Wed 4 Jun, 15:30 – 15:45·Willow: Expo Sessions

• ML Matthias Loibl Director of Cloud at Polar Signals

Windsurf everywhere, doing everything, all at once

Wed 4 Jun, 16:25 – 16:45·Keynote/General Session (Yerba Buena 7&8)

abstract tbd

• KH Kevin Hou Head of Product, Windsurf

#define AI Engineer

Wed 4 Jun, 16:45 – 17:25·Keynote/General Session (Yerba Buena 7&8)

Greg Brockman's career and advice for AI Engineers

• GB Greg Brockman Cofounder, OpenAI
• S. swyx . Curator, smol.ai

A year of Gemini progress + what comes next

Thu 5 Jun, 09:05 – 09:25·Keynote/General Session (Yerba Buena 7&8)

Over the last year, Google and Gemini models have shown rapid progress across all dimensions (model, product, etc). Let's highlight all the work that has happened, how we got the… Show more

• LK Logan Kilpatrick Product, Google Deepmind

Thinking Deeper in Gemini

Thu 5 Jun, 09:25 – 09:45·Keynote/General Session (Yerba Buena 7&8)

Progress towards general intelligence has been marked by identifying fundamental intelligence bottlenecks within existing models and developing solutions that improve the… Show more

• JR Jack Rae Principal Research Scientist

Why should anyone care about Evals?

Thu 5 Jun, 09:45 – 09:50·Keynote/General Session (Yerba Buena 7&8)

An introduction to the evals track

• MG Manu Goyal Founding Engineer, Braintrust

Containing Agent Chaos

Thu 5 Jun, 09:50 – 10:10·Keynote/General Session (Yerba Buena 7&8)

AI agents promise breakthroughs but often deliver operational chaos. Building reliable, deployable systems with unpredictable LLMs feels like wrestling fog – testing outputs alone… Show more

• SH Solomon Hykes CEO & Co-founder of Dagger, creator of Docker

The infrastructure for the singularity

Thu 5 Jun, 10:10 – 10:30·Keynote/General Session (Yerba Buena 7&8)

We're at an inflection point where AI agents are transitioning from experimental tools to practical coworkers. This new world will demand new infrastructure for RL training,… Show more

• JH Jesse Han Founder

Introducing Strands Agents, an Open Source AI Agents SDK

Thu 5 Jun, 10:45 – 11:00·Nobhill A&B: Expo Sessions

Building AI agents used to require complex orchestration, extensive scaffolding, and months of tuning. With Strands Agents, an open source SDK from AWS. You can now build, test,… Show more

• SD Suman Debnath Principal Developer Advocate, AI/ML, AWS

The fastest software dev workflow in the world: AI meets stacked diffs

Thu 5 Jun, 10:45 – 11:00·Willow: Expo Sessions

Learn the secrets behind the workflows that engineers at the fastest moving companies in the world are using to build software for billions of users worldwide. This workshop will… Show more

• KD Kenneth DuMez DevRel Lead, Graphite

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

Thu 5 Jun, 10:45 – 11:00·Juniper: Expo Sessions

You're trying to guide how your agents think and act. Code-orchestrated workflows are too rigid, but LLMs charting their own course feel too chaotic. When you need a middle ground,… Show more

• JB Jesús Barrasa AI Field CTO

The State of AI-Powered Search and Retrieval

Thu 5 Jun, 11:00 – 11:15·Juniper: Expo Sessions

In this talk, we examine the state-of-the-art in AI-powered search and retrieval. We detail techniques for enhancing performance beyond base embedding models, including hybrid… Show more

• FL Frank Liu Staff Product Manager, MongoDB

The Build-Operate Divide: Bridging Product Vision and AI Operational Reality

Thu 5 Jun, 11:00 – 11:15·Willow: Expo Sessions

Product leaders see AI possibilities. Operations teams see implementation chaos. That disconnect can kill promising AI features before they ever reach users. In this session,… Show more

• CH Chris Hernandez Manager of AI Speech Analytics at Chime

Pipecat Cloud: Enterprise Voice Agents Built On Open Source

Thu 5 Jun, 11:00 – 11:15·Nobhill A&B: Expo Sessions

Voice AI agents today can conduct natural, human-like conversations and perform a wide variety of tasks: customer support, lead qualification, healthcare patient intake, market… Show more

• MB Mark Backman Head of Product, Daily

Training Agentic Reasoners

Thu 5 Jun, 11:15 – 11:35·Yerba Buena Ballroom 2-6: Reasoning + RL

This talk will be a technical deep dive into RL for agentic reasoning via multi-turn tool calling, similar to OpenAI's o3 and Deep Research. In particular, we'll cover: - When,… Show more

• WB Will Brown Research Engineering Lead

From Hype to Habit: How We’re Building an AI-First SaaS Company—While Still Shipping the Roadmap

Thu 5 Jun, 11:15 – 11:35·Golden Gate Ballroom C: AI in the Fortune 500

What does it really take to move a modern SaaS company from AI experimentation to becoming truly AI-first? At Sprout Social, we’re in the midst of that… Show more

• RB Rossella Blatt Vital VP of Engineering - AI
• DM Deepsha Menghani Director of Engineering – AI

Monetizing AI: From Zero to Profit

Thu 5 Jun, 11:15 – 11:35·SOMA: AI Architects

As AI continues to transform industries, companies are faced with the critical challenge of effectively monetizing AI-driven products in a way that captures value, ensures customer… Show more

• AM Alvaro Morales CEO

Devin 2.0 and the Future of SWE

Thu 5 Jun, 11:15 – 11:35·Yerba Buena Ballroom 7&8: SWE Agents

A talk on the future of software engineering with Scott Wu of Cognition AI, the makers of Devin.

• SW Scott Wu CEO, Cognition AI

Building AI Agents that actually automate Knowledge Work

Thu 5 Jun, 11:15 – 11:35·Golden Gate Ballroom A: Retrieval + Search

Agents are all the rage in 2025, and every single b2b SaaS startup/incumbent promises AI agents that can "automate work" in some way. But how do you actually build this? The… Show more

• JL Jerry Liu CEO

On Engineering AI Systems that Endure The Bitter Lesson

Thu 5 Jun, 11:15 – 11:35·Golden Gate Ballroom B: Evals

Will discuss the principles for building AI software that underpin DSPy, highlighting the differences between conventional prompting (or finetuning/RL) versus the design and… Show more

• OK Omar Khattab Databricks Research Scientist

Safety and security for code-executing agents

Thu 5 Jun, 11:15 – 11:35·Foothill C: Security

Code is the lingua franca for both software engineers and highly capable AI models. As we give agents the ability to build, test, and run code that they generate, the command line… Show more

• FM Fouad Matin Member of Technical Staff, OpenAI

UX Design Principles for (Semi) Autonomous Multi-Agent Systems

Thu 5 Jun, 11:15 – 11:35·Foothill G 1&2: Design Engineering

Autonomous or semi-autonomous multi-agent systems (MAS) involve exponentially complex configurations (system config, agent configs, task management and delegation, etc.). These… Show more

• VD Victor Dibia Principal Research Engineer

The State of Generative Media Today

Thu 5 Jun, 11:15 – 11:35·Foothill F: Generative Media

Generative AI is reshaping the creative landscape, enabling the production of images, audio, and video with unprecedented speed and sophistication. This session offers an in-depth… Show more

• GY Gorkem Yurtseven CTO

Robotics: why now?

Thu 5 Jun, 11:15 – 11:35·Foothill E: Autonomy + Robotics

Sharing recent progress from Physical Intelligence and why it is an exciting time to push the frontier in general purpose robotics

• QV Quan Vuong Co-founder, Physical Intelligence
• JT Jost Tobias Springenberg Research Scientist, Physical Intelligence

Your Coding Agent Just Got Cloned And Your Brain Isn't Ready

Thu 5 Jun, 11:35 – 11:55·Yerba Buena Ballroom 7&8: SWE Agents

Will the future engineer code alongside a single coding agent, or will they spend their day orchestrating many agents? Traditional development rewards synchronous focus. This… Show more

• RB Rustin Banks Product Manager, AI Coding

Measuring AGI: Interactive Reasoning Benchmarks

Thu 5 Jun, 11:35 – 11:55·Yerba Buena Ballroom 2-6: Reasoning + RL

ARC Prize Foundation is building the North Star for AGI—rigorous, open benchmarks that track reasoning progress in modern AI. We'll show why static AGI evaluations are useful, but… Show more

• GK Greg Kamradt President

Scaling Enterprise-Grade RAG Systems: Lessons from the Legal Frontier

Thu 5 Jun, 11:35 – 11:55·Golden Gate Ballroom A: Retrieval + Search

In domains like law, compliance, and tax, building enterprise-grade RAG means very large scale, spikey workloads, a focus on accuracy, and non-negotiable privacy. In this talk,… Show more

• CS Chang She CEO
• CQ Calvin Qi Tech Lead Manager

Turning Fails into Features: Zapier’s Hard-Won Eval Lessons

Thu 5 Jun, 11:35 – 11:55·Golden Gate Ballroom B: Evals

Every agent failure can be a roadmap to your next breakthrough. This talk reveals how Zapier's evaluation system transforms frustrating user experiences into targeted improvements,… Show more

• RW Rafal Wilinski AI Agents Lead
• VB Vitor Balocco Staff AI Engineer

The Unofficial Guide to Apple’s Private Cloud Compute

Thu 5 Jun, 11:35 – 11:55·Foothill C: Security

In October 2024, Apple released a new private AI technology onto millions of devices called “Private Cloud Compute”. It brings the same level of privacy and security a local device… Show more

• JM Jonathan Mortensen CEO

Good design hasn’t changed with AI

Thu 5 Jun, 11:35 – 11:55·Foothill G 1&2: Design Engineering

Bad designs are still bad. AI doesn’t make it good. The novelty of AI makes the bad things tolerable, for a short time. Building great designs and experiences with AI have the same… Show more

• JP John Pham Head of Design

Veo 3 for developers

Thu 5 Jun, 11:35 – 11:55·Foothill F: Generative Media

This talk will briefly trace the history of video generation models before diving into Veo 3, Google DeepMind's latest state-of-the-art model that marks a significant leap by… Show more

• PB Paige Bailey Engineering Lead - Developer Relations @ Google DeepMind

Real-time Experiments with an AI Co-Scientist

Thu 5 Jun, 11:35 – 11:55·Foothill E: Autonomy + Robotics

The sheer volume of data and complexity of modern scientific challenges necessitate tools that go beyond mere analysis. The vision of an "AI Co-scientist" – a true collaborative… Show more

• SD Stefania Druga AI Research Scientist

CIOs and Industry Leaders: Do You Trust Your AI’s Inferences?

Thu 5 Jun, 11:35 – 11:55·SOMA: AI Architects

Enterprise AI adoption is accelerating, but with it comes a hard question: Do we trust the model’s decisions? In this 18-minute talk, I’ll explore the invisible risks behind… Show more

• SY Sahil Yadav Head of AI Products (Sr. Director, Product Management)
• HG Hariharan Ganesan Sr. Solutions Architect

Machines of Buying & Selling Grace

Thu 5 Jun, 11:35 – 11:55·Golden Gate Ballroom C: AI in the Fortune 500

How to go beyond browser automation to truly agentic commerce, where AI can buy, sell and negotiate on behalf of users and merchants.

• AB Adam Behrens CEO

Post-Training Open Models with RL for Autonomous Coding

Thu 5 Jun, 11:55 – 12:15·Yerba Buena Ballroom 2-6: Reasoning + RL

The models and techniques to build fully autonomous coding agents - not just coding copilots - are already here. In this talk, former Google DeepMind staff research scientist, now… Show more

• ML Misha Laskin CEO & co-founder

Evaluating AI Search: A Practical Framework for Augmented AI Systems

Thu 5 Jun, 11:55 – 12:15·Golden Gate Ballroom A: Retrieval + Search

AI search is becoming the front door to information, whether through Retrieval-Augmented Generation (RAG), Search-Augmented Generation (SAG), or custom agents that synthesize… Show more

• JN Julia Neagu CEO
• DE Deanna Emery Founding AI Researcher
• MA Maitar Asher Head of Engineering

Evals Are Not Unit Tests

Thu 5 Jun, 11:55 – 12:15·Golden Gate Ballroom B: Evals

How to think about evaluating a non-deterministic system — and how to actually succeed at it.

• IP Ido Pesok AI Engineer, v0

Fuzzing in the GenAI Era

Thu 5 Jun, 11:55 – 12:15·Foothill C: Security

"Evaluation" is one of those concepts that every AI practitioner vaguely knows is important, but few practitioners truly understand. Is "eval" the dataset for measuring the quality… Show more

• LT Leonard Tang Founder & CEO

The Bitter Layout or: How I Learned to Love the Model Picker

Thu 5 Jun, 11:55 – 12:15·Foothill G 1&2: Design Engineering

Are conversational interfaces the future or, as many designers have suggested, a lazy solution that is bottlenecking AI-HCI? Despite well-documented usability issues, the design of… Show more

• MP Maximillian Piras Product Designer

Magic Editor Under the Hood: Weaving Generative AI into a Billion-User App

Thu 5 Jun, 11:55 – 12:15·Foothill F: Generative Media

Go behind the scenes of Google Photos' Magic Editor. Explore the engineering feats required to integrate complex CV and cutting-edge generative AI models into a seamless mobile… Show more

• KM Kelvin Ma Software Engineer

What Is a Humanoid Foundation Model? An Introduction to GR00T N1

Thu 5 Jun, 11:55 – 12:15·Foothill E: Autonomy + Robotics

Foundation models don’t just write or draw anymore—they’re starting to move. GR00T N1 is NVIDIA’s open Vision-Language-Action (VLA) foundation model for humanoid robots. Built… Show more

• AB Annika Brundyn GenAI Architect
• AJ Aastha Jhunjhunwala Solutions Architect

How Intuit uses LLMs to explain taxes to millions of taxpayers

Thu 5 Jun, 11:55 – 12:15·Golden Gate Ballroom C: AI in the Fortune 500

I will talk about how Intuit uses LLMs to explain tax situations to Turbotax users. Users want explanations of their tax situations - this drives confidence in the product. Over… Show more

• JS Jaspreet Singh Senior Staff Software Engineer

Does AI Actually Boost Developer Productivity? (Stanford / 100k Devs Study)

Thu 5 Jun, 11:55 – 12:15·SOMA: AI Architects

Forget vendor hype: Is AI actually boosting developer productivity, or just shifting bottlenecks? Stop guessing. Our study at Stanford cuts through the noise, analyzing… Show more

• YD Yegor Denisov-Blanch Developer Productivity Researcher at Stanford University

AI and Game Theory: A Case Study on NYT's Connections

Thu 5 Jun, 12:15 – 12:35·Foothill G 1&2: Design Engineering

This session will examine the interplay between human intuition and artificial intelligence in puzzle-solving, using the popular New York Times Connections game as a practical case… Show more

• SQ Shafik Quoraishee AI Game Engineer

Ship it! Building Production-Ready Agents

Thu 5 Jun, 12:15 – 12:35·Golden Gate Ballroom C: AI in the Fortune 500

Explore the practical challenges and solutions for deploying AI agents in real-world production environments. Through detailed technical analysis and practical examples, we'll… Show more

• MC Mike Chambers AI/ML Specialist DA AWS

AX is the only Experience that Matters

Thu 5 Jun, 12:15 – 12:35·SOMA: AI Architects

If you’re building devtools for humans, you’re building for the past. Already a quarter of Y Combinator’s latest batch used AI to write 95% or more of their code. AI agents are… Show more

• IB Ivan Burazin CEO

Don’t get one-shotted: Leveraging AI to test, review, merge, and deploy code

Thu 5 Jun, 12:15 – 12:35·Yerba Buena Ballroom 7&8: SWE Agents

As AI tools like GitHub Copilot and ChatGPT help engineers generate code at an unprecedented rate, the “outer loop”—reviewing, testing, merging, and deploying—becomes more vital… Show more

• TR Tomas Reimers Graphite CPO & Co-founder

OpenThinker - Unreasonably Effective Reasoning Distillation at Scale

Thu 5 Jun, 12:15 – 12:35·Yerba Buena Ballroom 2-6: Reasoning + RL

Peel back the curtain on state of the art model post-training through the story of OpenThinker, a SOTA small reasoning model (outperforming DeepSeek distill), built in the open.… Show more

• RM Ryan Marten Founding Engineer at Bespoke Labs

RAG in 2025: State of the Art and the Road Forward

Thu 5 Jun, 12:15 – 12:35·Golden Gate Ballroom A: Retrieval + Search

The talk will have three parts 1.Roadmap debate: RAG vs. finetuning vs. long-context 2.RAG today: benefits, challenges, and current solutions 3.RAG tomorrow: AI models do more… Show more

• TM Tengyu Ma Chief AI Scientist, MongoDB

Securing Agents with Open Standards

Thu 5 Jun, 12:15 – 12:35·Foothill C: Security

Shipping AI agents that are safe for production means solving some tough identity and authorization challenges that are not always obvious at the prototype stage. In practice, this… Show more

• BT Bobby Tiernay Auth0, Principal Architect
• KS Kam Sween Auth0, Staff Engineer, AIFS

Small, sharp tools in the era of generative AI

Thu 5 Jun, 12:15 – 12:35·Foothill F: Generative Media

Replicate makes it easy to run thousands of AI models in the cloud without any machine learning expertise. In this session, we'll show how to make those models available to LLMs as… Show more

• ZS Zeke Sikelianos Founding Designer

Agents, Access, and the Future of Machine Identity

Thu 5 Jun, 12:45 – 13:00·Willow: Expo Sessions

AI agents are calling APIs, submitting forms, and sending emails—but how do you control what they’re allowed to do? As agents act on behalf of users or organizations, traditional… Show more

• NN Nick Nisi Software developer and panelist on the JS Party podcast

Building Protected MCP Servers

Thu 5 Jun, 12:45 – 13:05·Nobhill C&D: Microsoft

Join us to see how VS Code and GitHub Copilot's expanding suite of AI features can match or even surpasses the benefits of other popular AI developer tools. We'll focus on… Show more

• DD Den Delimarsky (DEVDIV) Principal Product Engineer
• JK Julia Kasper Program Manager

Building CISO-approved agent fleet architecture

Thu 5 Jun, 12:45 – 13:00·Juniper: Expo Sessions

Security is the biggest blocker for agent orchestration adoption in regulated industries for SWE agents. Gitpod's agent orchestration went from an originally self-hosted kubernetes… Show more

• LB Lou Bichard Product Manager, Gitpod

Conquering Agent Chaos

Thu 5 Jun, 13:00 – 13:15·Willow: Expo Sessions

Agent deployments can be dicey, especially at first. This session goes over all the things that cause headache with deployments from serverless issues to networking issues - and… Show more

• RB Rick Blalock Founder, Agentuity

Serving Voice AI at Scale

Thu 5 Jun, 13:15 – 13:30·Nobhill A&B: Expo Sessions

Real-Time Voice AI applications demand the lowest possible latencies to enhance user experiences with more advanced reasoning and agentic capabilities. AWS is hosting Arjun… Show more

• RT Rohit Talluri Senior Worldwide Generative AI Specialist BD - Foundation Model Training & Inference
• AD Arjun Desai Co-Founder, Cartesia

Prompt Engineering is Dead

Thu 5 Jun, 13:15 – 13:30·Juniper: Expo Sessions

Manual prompt crafting doesn't scale. In this session, we'll explore how to replace it with a test-driven, automated approach. You'll see how to define output evaluators, write… Show more

• NG Nir Gazit CEO @ Traceloop, OpenLLMetry co-creator

Optimizing inference for voice models in production

Thu 5 Jun, 13:15 – 13:30·Willow: Expo Sessions

How do you get time to first byte (TTFB) below 150 milliseconds for voice models -- and scale it in production? As it turns out, open-source TTS models like Orpheus have an LLM… Show more

• PK Philip Kiely Head of Developer Relations

Building Alice’s Brain: How We Built an AI Sales Rep that Learns Like a Human

Thu 5 Jun, 14:00 – 14:20·Golden Gate Ballroom A: Retrieval + Search

AI agents are becoming essential tools for teams of all sizes and industries - but training them to become experts in your product, business, and customerbase remains a challenge.… Show more

• SC Sherwood Callaway Tech Lead, Alice
• SS Satwik Singh Member of Technical Staff

Introducing Claude Code

Thu 5 Jun, 14:00 – 14:20·Yerba Buena Ballroom 7&8: SWE Agents

Hear about Claude Code directly from its creator: origin story, getting your team set up, and practical tips for getting more out of Code.

• BC Boris Cherny Member of Technical Staff & Creator of Claude Code

CIAM for AI: Who Are Your Agents and What Can They Do?

Thu 5 Jun, 14:00 – 14:20·SOMA: AI Architects

AI agents are changing the way modern SaaS products operate. Whether automating workflows, integrating with APIs, or acting on behalf of users, AI-driven assistants and autonomous… Show more

• MG Michael Grinich Founder & CEO, WorkOS

[Evals Keynote] tba

Thu 5 Jun, 14:00 – 14:20·Golden Gate Ballroom B: Evals

tbc

• AG Ankur Goyal CEO, Braintrust

How to defend your sites from AI bots

Thu 5 Jun, 14:00 – 14:20·Foothill C: Security

Constantly seeing CAPTCHAs? It used to be easy to detect the humans from the droids, but what else can we do when synthetic clients make up nearly half of all web requests.… Show more

• DM David Mytton Founder

AI and Human Whiteboarding Partnership

Thu 5 Jun, 14:00 – 14:20·Foothill G 1&2: Design Engineering

Covid sent everybody home and created the space of virtual whiteboards. At first the experience reused the physical constraints but soon it became better than a physical whiteboard… Show more

• CC Christopher Chedeau Frenchy Front-end Engineer

General Intelligence is Multimodal

Thu 5 Jun, 14:00 – 14:20·Foothill F: Generative Media

Talking about Luma AI, our mission, and how our ML infrastructure enables SOTA multimodal model development

• KM Keegan McCallum Head of ML infrastructure at Luma AI

Teaching Cars to Think: Language Models and Autonomous Vehicles

Thu 5 Jun, 14:00 – 14:20·Foothill E: Autonomy + Robotics

This session explores Waymo's latest research on the End-to-End Multimodal Model for Autonomous Driving (EMMA) and advanced sensor simulation techniques. Jyh-Jing Hwang will… Show more

• JH Jyh-Jing Hwang Research Scientist & TLM

How to Build Agents without losing control

Thu 5 Jun, 14:00 – 14:20·Golden Gate Ballroom C: AI in the Fortune 500

Planning agents help solve complex tasks by breaking them into steps. They work across enterprise systems where data lives in many places. These agents are powerful but can be hard… Show more

• YM Yogi Miraje Lead AI Engineer

How to Train Your Agent: Building Reliable Agents with RL

Thu 5 Jun, 14:00 – 14:20·Yerba Buena Ballroom 2-6: Reasoning + RL

Have you ever launched an awesome agentic demo, only to realize no amount of prompting will make it reliable enough to deploy in production? Agent reliability is a famously… Show more

• KC Kyle Corbitt CEO

A taxonomy for next-generation reasoning models

Thu 5 Jun, 14:20 – 14:40·Yerba Buena Ballroom 2-6: Reasoning + RL

Current AI models are extremely skilled, which was seen as the step change in evaluation scores across the industry in the first half of 2025, but often fail when presented with… Show more

• NL Nathan Lambert Research Lead

POC to PROD: Hard Lessons from 200+ Enterprise GenAI Deployments

Thu 5 Jun, 14:20 – 14:40·Golden Gate Ballroom C: AI in the Fortune 500

The transition from experimental GenAI demonstrations to robust, production-grade systems involves significant technical and organizational complexities. Humans provide a ceiling… Show more

• RH Randall Hunt CTO at Caylent

Testing the Un-Testable: Monitoring AI Products in the Wild

Thu 5 Jun, 14:20 – 14:40·SOMA: AI Architects

Evals are straightforward—like unit tests, they confirm your model got specific test cases right. But in the real world, your AI encounters millions of unpredictable… Show more

• BH Ben Hylak Co-Founder
• SB Sid Bendre Co-Founder

Software Development Agents: What Works and What Doesn't

Thu 5 Jun, 14:20 – 14:40·Yerba Buena Ballroom 7&8: SWE Agents

The adoption of AI into software development has been bumpy. While autocomplete tools like Copilot have gone mainstream, autonomous agents like Devin and OpenHands have generated… Show more

• RB Robert Brennan CEO

Building a Smarter AI Agent with Neural RAG

Thu 5 Jun, 14:20 – 14:40·Golden Gate Ballroom A: Retrieval + Search

RAG quality for AI agents is critical, and traditional keyword-based search engines consistently underperform in agentic or multi-step tasks, where semantic grounding and… Show more

• WB Will Bryk CEO & Co-founder, building perfect search at Exa

2025 is the Year of Evals! Just like 2024, and 2023, and …

Thu 5 Jun, 14:20 – 14:40·Golden Gate Ballroom B: Evals

AI is getting deployed without guardrails, without governance, without due diligence. Surely this is the year we’ll see a Fortune 500 CEO fired because of a preventable AI… Show more

• JD John Dickerson CEO, Mozilla AI

How to Secure Agents using OAuth

Thu 5 Jun, 14:20 – 14:40·Foothill C: Security

We all know sharing passwords is bad (unless you want free TV), so why are we sharing API keys with AI? We shouldn't, and that’s why we need to talk about OAuth. In this talk,… Show more

• JH Jared Hanson Co-Founder

tldraw computer

Thu 5 Jun, 14:20 – 14:40·Foothill G 1&2: Design Engineering

Learn about tldraw's latest experiments with AI on an infinite canvas. In 2024, we created tldraw computer, a loose visual programming environment where arrows and LLMs powered… Show more

• SR Steve Ruiz Founder and CEO, tldraw

Good demos are important

Thu 5 Jun, 14:20 – 14:40·Foothill F: Generative Media

Creating and sharing demos is the easiest way to influence the future. It gets people to think about what's possible. A good tech demo doesn't have to be fully fleshed out. It… Show more

• SS Sharif Shameem Lexica Founder

General purpose robots as professional Chefs

Thu 5 Jun, 14:20 – 14:40·Foothill E: Autonomy + Robotics

How we converted a bimanual robot into a professional chef that works in novel kitchens and learn new recipes from a single demonstration.

• NA Nikhil Abraham CEO

Beyond the Prototype: Using AI to Write High-Quality Code

Thu 5 Jun, 14:40 – 15:00·Yerba Buena Ballroom 7&8: SWE Agents

In this case study-based keynote, Josh Albrecht, CTO of Imbue, examines the critical engineering challenges in building AI coding systems that create more than just prototypes.… Show more

• JA Josh Albrecht CTO and Co-founder

Towards Verified Superintelligence

Thu 5 Jun, 14:40 – 15:00·Yerba Buena Ballroom 2-6: Reasoning + RL

I describe a new paradigm towards open-endedly self-improving intelligence by scaling verification to remove the human data and supervision bottleneck. The objective is to achieve… Show more

• CS Christian Szegedy Former co-founder of xAI, discoverer of adversarial examples

Layering every technique in RAG, one query at a time

Thu 5 Jun, 14:40 – 15:00·Golden Gate Ballroom A: Retrieval + Search

Start with the simplest Search - in-memory embeddings with relevance ranking. End with the most complex planet-scale Search - 70+ corpus mix of token, embeddings, and knowledge… Show more

• DK David Karam CEO

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

Thu 5 Jun, 14:40 – 15:00·Golden Gate Ballroom B: Evals

By the end of this talk, you'll understand what it takes to apply clustering techniques and data analysis to understand what is the valuable work that your AI application is doing… Show more

• JH Jeff Huber CEO
• JL Jason Liu Principal

How we hacked YC Spring 2025 batch’s AI agents

Thu 5 Jun, 14:40 – 15:00·Foothill C: Security

We hacked 7 of the16 publicly-accessible YC X25 AI agents. This allowed us to leak user data, execute code remotely, and take over databases. All within 30 minutes each. In this… Show more

• RB Rene Brandel CEO

Form factors for your new AI coworkers

Thu 5 Jun, 14:40 – 15:00·Foothill G 1&2: Design Engineering

Designing user experiences for AI means moving beyond traditional interfaces. Designers are grappling with how to create intuitive and effective interactions for these new AI… Show more

• CW Craig Wattrus AI Design Engineer

Why you should care about AI interpretability

Thu 5 Jun, 14:40 – 15:00·Foothill F: Generative Media

The goal of mechanistic interpretability is to reverse engineer neural networks. Having direct, programmable access to the internal neurons of models unlocks new ways for… Show more

• MB Mark Bissell Applied Interpretability Research

The Web Browser Is All You Need

Thu 5 Jun, 14:40 – 15:00·SOMA: AI Architects

With the rise of MCP servers, A2A, and our trusty friend, OpenAPI, it turns out the web browser may be the default MCP server for the rest of the internet. In this talk, we'll… Show more

• PK Paul Klein IV Founder

Building Agents (the hard parts!)

Thu 5 Jun, 14:40 – 15:00·Golden Gate Ballroom C: AI in the Fortune 500

AI workloads are rapidly shifting from AI being used for augmentation (co-pilots), to AI becoming responsible for full, end-to-end automation (agents). But building effective… Show more

• RK Rita Kozlov vp developers & ai, cloudflare

Ship Production Software in Minutes, Not Months

Thu 5 Jun, 15:00 – 15:20·Yerba Buena Ballroom 7&8: SWE Agents

Planning, coding, testing, monitoring—the endless cycle that spans 10+ tools that fragment our focus and slows delivery to a crawl. Vibe coding doesn't work when you've got 10TB of… Show more

• ER Eno Reyes CTO

CI in the Era of AI: From Unit Tests to Stochastic Evals

Thu 5 Jun, 15:15 – 15:30·Juniper: Expo Sessions

Software engineers have long understood that high-quality code requires comprehensive automated testing. For decades, our industry has relied on deterministic tests with clear… Show more

• NS Nathan Sobo CEO & Co-founder of Zed, co-creator of Atom and Electron

Cattle, not genies: building AI agents from first principles

Thu 5 Jun, 15:15 – 15:30·Willow: Expo Sessions

As magical as they may seem, AI agents should be treated like any other software system. This talk will cover the best practices in designing and building AI systems including… Show more

• KD Kenneth DuMez DevRel Lead, Graphite

To the moon! Navigating deep context in legacy code with Augment Agent

Thu 5 Jun, 15:15 – 15:30·Nobhill A&B: Expo Sessions

Shortened presentation-only version of our Apollo 11 workshop

• FB Forrest Brazeal Speaker and Workshop Organizer
• MB Matt Ball Empowering Developers with AI

The Eyes Are The (Context) Window to The Soul: How Windsurf Gets to Know You

Thu 5 Jun, 15:30 – 15:45·Nobhill A&B: Expo Sessions

Sometimes it seems like Windsurf knows you a little too well. It's one thing to generate generic code, but to predict your next intent? From matching existing code patterns and… Show more

• SF Sam Fertig Deployed Engineer, Windsurf

The emerging skillset of wielding coding agents

Thu 5 Jun, 15:30 – 15:45·Willow: Expo Sessions

It's raining coding agents. But while many are saying they're feeling the AGI, others say they're not that useful for serious programming. How much is hype and how much is a skill… Show more

• BL Beyang Liu Co-founder and CTO, Sourcegraph

Trends Across the AI Frontier

Thu 5 Jun, 16:00 – 16:20·Keynote/General Session (Yerba Buena 7&8)

The entire AI stack is developing faster than ever - from chips to infrastructure to models. How do you sort the signal from the noise? Artificial Analysis an independent… Show more

• MH Micah Hill-Smith CEO
• GC George Cameron CPO

Evals Closing Keynote

Thu 5 Jun, 16:20 – 16:25·Keynote/General Session (Yerba Buena 7&8)

The final word on Evals

• AG Ankur Goyal CEO, Braintrust

State of AI Engineering 2025

Thu 5 Jun, 16:25 – 16:35·Keynote/General Session (Yerba Buena 7&8)

Come hear the results of the 2025 State of AI Engineering.

• BY Barr Yaron Partner at Amplify Partners

fun stories from building OpenRouter and where all this is going

Thu 5 Jun, 16:35 – 16:55·Keynote/General Session (Yerba Buena 7&8)

How the first LLM aggregator got started, some of the weird moments in its early growth, architecture challenges, and where we'll be taking it down the road

• AA Alex Atallah CEO OpenRouter, co-founder of OpenSea

Prompt Engineering is Dead - Everything is a Spec

Thu 5 Jun, 16:55 – 17:15·Keynote/General Session (Yerba Buena 7&8)

[!!Subject to change!!] Large models are trained through mountains of data and learned reward functions, yet - quis custodiet ipsos custodes? - what exactly are those amorphous… Show more

• SG Sean Grove Member of Technical Staff