Tuesday, June 3, 2025

Keynote/General Session (Yerba Buena 7&8) Salons 2-6: Workshops Golden Gate Ballroom A: Workshops Golden Gate Ballroom B: Workshops Golden Gate Ballroom C: Workshops Foothill C: Workshops SOMA: Workshops Foothill G1&2: Workshops Nobhill A&B: Workshops Nobhill C&D: Microsoft

9:00 am

Golden Gate Ballroom A: Workshops
9:00 am - 12:00 pm

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

  • Workshop
Golden Gate Ballroom B: Workshops
9:00 am → 80 min

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

Golden Gate Ballroom C: Workshops
9:00 am → 80 min

Intro to GraphRAG

Foothill C: Workshops
9:00 am - 12:00 pm

Kernels, RL, Reasoning, Reward Functions & Quantization

  • Workshop
SOMA: Workshops
9:00 am → 80 min

Introduction to LLM serving with SGLang

  • Workshop
Foothill G1&2: Workshops
9:00 am → 80 min

Shipping AI That Works: An Evaluation Framework for PMs

  • Workshop
Nobhill A&B: Workshops
9:00 am → 80 min

Beyond Benchmarks: Strategies for Evaluating LLMs in Production

  • Workshop

10:00 am

Keynote/General Session (Yerba Buena 7&8)
10:00 am - 5:00 pm

Rehearsals/Tech Check

10:40 am

Golden Gate Ballroom B: Workshops
10:40 am → 80 min

Circle Workshop

Foothill G1&2: Workshops
10:40 am → 80 min

Scoring models beat LLM judges any day of the week

  • Workshop
Nobhill A&B: Workshops
10:40 am → 80 min

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

  • Workshop
Nobhill C&D: Microsoft
10:40 am → 80 min

Piloting agents in GitHub Copilot

12:40 pm

Golden Gate Ballroom B: Workshops
12:40 pm → 20 min

Useful General Intelligence

1:00 pm

Salons 2-6: Workshops
1:00 pm → 120 min

Every Way to Optimize Your Models with OpenAI

  • Workshop
Golden Gate Ballroom A: Workshops
1:00 pm → 120 min

Real-World Development with GitHub Copilot and VS Code

Golden Gate Ballroom B: Workshops
1:00 pm → 120 min

Building Agents with Amazon Nova Act and MCP

Foothill C: Workshops
1:00 pm → 120 min

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

  • Workshop
SOMA: Workshops
1:00 pm → 120 min

AI Engineering with the Google Gemini 2.5 Model Family

  • Workshop
Foothill G1&2: Workshops
1:00 pm → 120 min

Information Retrieval from the Ground Up

  • Workshop
Nobhill C&D: Microsoft
1:00 pm → 120 min

Building Code-First AI Agents with Azure AI Agent Service: A Practical introduction

3:30 pm

Salons 2-6: Workshops
3:30 pm → 120 min

AI Pipelines and Agents in Pure TypeScript with Mastra.ai

Golden Gate Ballroom B: Workshops
3:30 pm → 120 min

AI agents & deep context in legacy codebases - to the moon!

Foothill C: Workshops
3:30 pm → 120 min

Building voice agents with OpenAI

  • Workshop
Foothill G1&2: Workshops
3:30 pm → 120 min

VoiceVision RAG - Integrating Visual Document Intelligence with Voice Response

Wednesday, June 4, 2025

Keynote/General Session (Yerba Buena 7&8) Yerba Buena Ballroom Salons 7-8: MCP Yerba Buena Ballroom Salons 2-6: Tiny Teams Golden Gate Ballroom A: LLM RecSys Golden Gate Ballroom B: GraphRAG Golden Gate Ballroom C: AI in the Fortune 500 SOMA: AI Architects Foothill C: Agent Reliability Foothill G 1&2: Product Management Foothill F: Infrastructure Foothill E: Voice Nobhill A&B: Expo Sessions Willow: Expo Sessions Juniper: Expo Sessions

7:45 am

Keynote/General Session (Yerba Buena 7&8)
7:45 am → 60 min

Rehearsals/Tech Check

8:45 am

Keynote/General Session (Yerba Buena 7&8)
8:45 am → 15 min

Doors

9:20 am

Keynote/General Session (Yerba Buena 7&8)
9:20 am → 20 min

Spark to System: Building the Open Agentic Web

9:40 am

Keynote/General Session (Yerba Buena 7&8)
9:40 am → 20 min

Conviction Session

10:00 am

Keynote/General Session (Yerba Buena 7&8)
10:00 am → 20 min

Simon Willison Keynote

10:30 am

Keynote/General Session (Yerba Buena 7&8)
10:30 am → 45 min

Break

10:45 am

Nobhill A&B: Expo Sessions
10:45 am → 15 min

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

Willow: Expo Sessions
10:45 am → 15 min

Architecting Agent Memory: Principles, Patterns, and Best Practices

Juniper: Expo Sessions
10:45 am → 15 min

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

11:00 am

Willow: Expo Sessions
11:00 am → 15 min

What does Enterprise Ready MCP mean?

Juniper: Expo Sessions
11:00 am → 15 min

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

11:15 am

Yerba Buena Ballroom Salons 7-8: MCP
11:15 am → 20 min

[Placeholder] MCP Origins

  • MCP (02)
Yerba Buena Ballroom Salons 2-6: Tiny Teams
11:15 am → 20 min

Bolt: The Dawn of the VibeCoder

  • Tiny Teams (01)
Golden Gate Ballroom A: LLM RecSys
11:15 am → 20 min

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

  • LLM RecSys (03)
Golden Gate Ballroom B: GraphRAG
11:15 am → 20 min

Graph Intelligence: Enhance Reasoning and Retrieval Using Graph Analytics

  • GraphRAG (08)
Golden Gate Ballroom C: AI in the Fortune 500
11:15 am → 20 min

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

  • AI in the Fortune 500 (L2)
SOMA: AI Architects
11:15 am → 20 min

The Rise of the AI Architect

  • AI Architects (L1)
Foothill C: Agent Reliability
11:15 am → 20 min

[Reliability Keynote] AI Automation that actually works: $100M, messy data, zero surprises

  • Agent Reliability (04)
Foothill G 1&2: Product Management
11:15 am → 20 min

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

  • Product Management (06)
Foothill F: Infrastructure
11:15 am → 20 min

What every AI engineer needs to know about GPUs

Foothill E: Voice
11:15 am → 20 min

[Voice Keynote] Your realtime AI is ngmi

  • Voice (07)

11:35 am

Golden Gate Ballroom C: AI in the Fortune 500
11:35 am → 20 min

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

  • AI in the Fortune 500 (L2)
SOMA: AI Architects
11:35 am → 20 min

Building Applications with AI Agents

  • AI Architects (L1)
Foothill E: Voice
11:35 am → 20 min

Shipping an Enterprise Voice AI Agent in 100 Days

  • Voice (07)

11:40 am

Yerba Buena Ballroom Salons 7-8: MCP
11:40 am → 20 min

[PLACEHOLDER] Anthropic MCP team talk 2

  • MCP (02)
Yerba Buena Ballroom Salons 2-6: Tiny Teams
11:40 am → 20 min

The New Lean Startup

  • Tiny Teams (01)
Golden Gate Ballroom A: LLM RecSys
11:40 am → 20 min

What We Learned from Using LLMs in Pinterest Search

Golden Gate Ballroom B: GraphRAG
11:40 am → 20 min

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

  • GraphRAG (08)
Foothill C: Agent Reliability
11:40 am → 20 min

Scaling AI agents without breaking reliability

  • AI Infrastructure (05)
Foothill G 1&2: Product Management
11:40 am → 20 min

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

  • Product Management (06)
Foothill F: Infrastructure
11:40 am → 20 min

Building Hyperbolic: The On-Demand AI Cloud for GPUs, Inference, and AI Services

  • AI Infrastructure (05)

11:55 am

Golden Gate Ballroom C: AI in the Fortune 500
11:55 am → 20 min

How agents will unlock the $500B promise of AI

  • AI in the Fortune 500 (L2)
SOMA: AI Architects
11:55 am → 20 min

The Rise of Open Models in the Enterprise

  • AI Architects (L1)
Foothill E: Voice
11:55 am → 20 min

What we can learn from self driving in autonomous voice agents

  • Voice (07)

12:00 pm

Keynote/General Session (Yerba Buena 7&8)
12:00 pm → 120 min

Break

12:05 pm

Yerba Buena Ballroom Salons 7-8: MCP
12:05 pm → 20 min

Full Spectrum MCP: Uncovering Hidden Servers and Clients Capabilities

Yerba Buena Ballroom Salons 2-6: Tiny Teams
12:05 pm → 20 min

Using OSS models to build AI apps with millions of users

  • Tiny Teams (01)
Golden Gate Ballroom A: LLM RecSys
12:05 pm → 20 min

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

Golden Gate Ballroom B: GraphRAG
12:05 pm → 20 min

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

  • GraphRAG (08)
Foothill C: Agent Reliability
12:05 pm → 20 min

12 Factor Agents - Principles of Reliable LLM Applications

  • Agent Reliability (04)
Foothill G 1&2: Product Management
12:05 pm → 20 min

Survive the AI Knife-Fight: Building Products That Win

  • Product Management (06)
Foothill F: Infrastructure
12:05 pm → 20 min

Large Scale AI on Apple Silicon using EXO

12:15 pm

Golden Gate Ballroom C: AI in the Fortune 500
12:15 pm → 20 min

3 ingredients for building reliable enterprise agents

SOMA: AI Architects
12:15 pm → 20 min

Mentoring the Machine

Foothill E: Voice
12:15 pm → 20 min

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

12:45 pm

Nobhill A&B: Expo Sessions
12:45 pm → 15 min

Agentic GraphRAG: AI’s Logical Edge

Willow: Expo Sessions
12:45 pm → 15 min

How to trust an agent with software delivery

Juniper: Expo Sessions
12:45 pm → 15 min

How fast are LLM inference engines anyway?

1:05 pm

Nobhill A&B: Expo Sessions
1:05 pm → 15 min

"Data readiness" is a myth: Make AI Reliabile with an Agentic Semantic Layer

Willow: Expo Sessions
1:05 pm → 15 min

Events are the Wrong Abstraction for Your AI Agents

Juniper: Expo Sessions
1:05 pm → 15 min

Effective agent design patterns in production

1:25 pm

Nobhill A&B: Expo Sessions
1:25 pm → 15 min

Data is Your Differentiator: Building Secure and Tailored AI Systems

Juniper: Expo Sessions
1:25 pm → 15 min

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

2:00 pm

Yerba Buena Ballroom Salons 7-8: MCP
2:00 pm → 20 min

MCP is all you need

  • MCP (02)
Yerba Buena Ballroom Salons 2-6: Tiny Teams
2:00 pm → 20 min

Tiny Teams

  • Tiny Teams (01)
Golden Gate Ballroom A: LLM RecSys
2:00 pm → 20 min

One model to rule recommendations: Netflix's Big Bet

Golden Gate Ballroom B: GraphRAG
2:00 pm → 20 min

Practical GraphRAG - Making LLMs smarter with Knowledge Graphs

  • GraphRAG (08)
Golden Gate Ballroom C: AI in the Fortune 500
2:00 pm → 20 min

Building an Agentic Platform

  • AI in the Fortune 500 (L2)
SOMA: AI Architects
2:00 pm → 20 min

AI That Pays: Lessons from Revenue Cycle

  • AI Architects (L1)
Foothill C: Agent Reliability
2:00 pm → 20 min

How to build Enterprise-aware agents

  • Agent Reliability (04)
Foothill G 1&2: Product Management
2:00 pm → 20 min

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

  • Product Management (06)
Foothill F: Infrastructure
2:00 pm → 20 min

[Infra Keynote] Geopolitics of AI Infrastructure

  • AI Infrastructure (05)
Foothill E: Voice
2:00 pm → 20 min

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

  • Voice (07)

2:25 pm

Yerba Buena Ballroom Salons 7-8: MCP
2:25 pm → 20 min

Observable tools - the state of MCP observability

  • MCP (02)
Yerba Buena Ballroom Salons 2-6: Tiny Teams
2:25 pm → 20 min

Building Small AI Teams with Huge Impact

Golden Gate Ballroom A: LLM RecSys
2:25 pm → 20 min

Instacart’s LLM-driven approach to Search and Discovery

  • LLM RecSys (03)
Golden Gate Ballroom B: GraphRAG
2:25 pm → 20 min

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

  • GraphRAG (08)
Golden Gate Ballroom C: AI in the Fortune 500
2:25 pm → 20 min

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

  • AI in the Fortune 500 (L2)
SOMA: AI Architects
2:25 pm → 20 min

Structuring a modern AI team

  • AI Architects (L1)
Foothill C: Agent Reliability
2:25 pm → 20 min

Agents vs Workflows: Why Not Both?

  • Agent Reliability (04)
Foothill G 1&2: Product Management
2:25 pm → 20 min

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

  • Product Management (06)
Foothill F: Infrastructure
2:25 pm → 20 min

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

  • AI Infrastructure (05)
Foothill E: Voice
2:25 pm → 20 min

Why ChatGPT Keeps Interrupting You

2:50 pm

Yerba Buena Ballroom Salons 7-8: MCP
2:50 pm → 20 min

The rise of the agentic economy on the shoulders of MCP

  • MCP (02)
Yerba Buena Ballroom Salons 2-6: Tiny Teams
2:50 pm → 20 min

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

  • AI Architects (L1)
Golden Gate Ballroom A: LLM RecSys
2:50 pm → 20 min

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

  • LLM RecSys (03)
Golden Gate Ballroom B: GraphRAG
2:50 pm → 20 min

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

  • GraphRAG (08)
Golden Gate Ballroom C: AI in the Fortune 500
2:50 pm → 20 min

From Hunch to Handoff: How AI PMs Can Help Turn Ideas Into Shippable Features Quickly

  • AI in the Fortune 500 (L2)
SOMA: AI Architects
2:50 pm → 20 min

Building Effective Voice Agents

  • AI Architects (L1)
Foothill C: Agent Reliability
2:50 pm → 20 min

Vibe Coding, with Confidence

  • Agent Reliability (04)
Foothill F: Infrastructure
2:50 pm → 20 min

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

  • AI Infrastructure (05)
Foothill E: Voice
2:50 pm → 20 min

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

3:00 pm

Keynote/General Session (Yerba Buena 7&8)
3:00 pm → 45 min

Break

3:15 pm

Nobhill A&B: Expo Sessions
3:15 pm → 15 min

Taming Rogue AI Agents with Observability-Driven Evaluation

Willow: Expo Sessions
3:15 pm → 15 min

Vector Search Benchmark[eting]

Juniper: Expo Sessions
3:15 pm → 15 min

Conquering Agent Chaos

3:45 pm

Keynote/General Session (Yerba Buena 7&8)
3:45 pm → 15 min

Doors

4:00 pm

Keynote/General Session (Yerba Buena 7&8)
4:00 pm → 20 min

Building Agents at Cloud-Scale

4:20 pm

Keynote/General Session (Yerba Buena 7&8)
4:20 pm → 20 min

Windsurf everywhere, doing everything, all at once

4:40 pm

Keynote/General Session (Yerba Buena 7&8)
4:40 pm → 40 min

#define AI Engineer

Thursday, June 5, 2025

Keynote/General Session (Yerba Buena 7&8) Golden Gate Ballroom C: AI in the Fortune 500 SOMA: AI Architects Yerba Buena Ballroom 7&8: SWE Agents Yerba Buena Ballroom 2-6: Reasoning + RL Golden Gate Ballroom A: Retrieval + Search Golden Gate Ballroom B: Evals Foothill C: Security Foothill G 1&2: Design Engineering Foothill F: Generative Media Foothill E: Autonomy + Robotics Nobhill A&B: Expo Sessions Willow: Expo Sessions Juniper: Expo Sessions

7:45 am

Keynote/General Session (Yerba Buena 7&8)
7:45 am → 60 min

Rehearsals/Tech Check

8:40 am

Keynote/General Session (Yerba Buena 7&8)
8:40 am → 25 min

Doors

9:05 am

Keynote/General Session (Yerba Buena 7&8)
9:05 am → 20 min

A year of Gemini progress + what comes next

9:25 am

Keynote/General Session (Yerba Buena 7&8)
9:25 am → 20 min

Jack Rae Keynote

9:50 am

Keynote/General Session (Yerba Buena 7&8)
9:50 am → 20 min

Containing Agent Chaos

10:10 am

Keynote/General Session (Yerba Buena 7&8)
10:10 am → 20 min

The infrastructure for the singularity

10:30 am

Keynote/General Session (Yerba Buena 7&8)
10:30 am → 45 min

Break

10:45 am

Nobhill A&B: Expo Sessions
10:45 am → 15 min

Introducing Strands Agents, an Open Source AI Agents SDK

Willow: Expo Sessions
10:45 am → 15 min

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

Juniper: Expo Sessions
10:45 am → 15 min

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

11:00 am

Nobhill A&B: Expo Sessions
11:00 am → 15 min

Pipecat Cloud: Enterprise Voice Agents Built On Open Source

Willow: Expo Sessions
11:00 am → 15 min

The Build-Run Divide: How Chime Bridges Product Vision and AI Operational Reality

Juniper: Expo Sessions
11:00 am → 15 min

The State of AI-Powered Search and Retrieval

11:15 am

Golden Gate Ballroom C: AI in the Fortune 500
11:15 am → 20 min

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

SOMA: AI Architects
11:15 am → 20 min

Monetizing AI: From Zero to Profit

  • AI Architects (L1)
Yerba Buena Ballroom 7&8: SWE Agents
11:15 am → 20 min

Devin 2.0 and the Future of SWE

Yerba Buena Ballroom 2-6: Reasoning + RL
11:15 am → 20 min

Training Agentic Reasoners

  • Reasoning + RL (15)
Golden Gate Ballroom A: Retrieval + Search
11:15 am → 20 min

Building AI Agents that actually automate Knowledge Work

Golden Gate Ballroom B: Evals
11:15 am → 20 min

On Engineering AI Systems that Endure The Bitter Lesson

Foothill C: Security
11:15 am → 20 min

Safety and security for code-executing agents

Foothill G 1&2: Design Engineering
11:15 am → 20 min

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

  • Design Engineering (10)
Foothill F: Generative Media
11:15 am → 20 min

The State of Generative Media Today

  • Generative Media (14)
Foothill E: Autonomy + Robotics
11:15 am → 20 min

Robotics: why now?

11:35 am

Golden Gate Ballroom C: AI in the Fortune 500
11:35 am → 20 min

Machines of Buying & Selling Grace

SOMA: AI Architects
11:35 am → 20 min

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

Yerba Buena Ballroom 7&8: SWE Agents
11:35 am → 20 min

Ship Production Software in Minutes, Not Months

  • SWE Agents (11)
Golden Gate Ballroom A: Retrieval + Search
11:35 am → 20 min

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

  • Retrieval + Search (09)
Foothill C: Security
11:35 am → 20 min

The Unofficial Guide to Apple’s Private Cloud Compute

  • Security (13)

11:40 am

Yerba Buena Ballroom 2-6: Reasoning + RL
11:40 am → 20 min

Inside ARC Prize, Scaling Reasoning, and Dynamic Evals

  • Reasoning + RL (15)
Golden Gate Ballroom B: Evals
11:40 am → 20 min

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

Foothill G 1&2: Design Engineering
11:40 am → 20 min

Good design hasn’t changed with AI

  • Design Engineering (10)
Foothill F: Generative Media
11:40 am → 20 min

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

  • Generative Media (14)
Foothill E: Autonomy + Robotics
11:40 am → 20 min

Real-time Experiments with an AI Co-Scientist

  • Autonomy + Robotics (16)

11:55 am

Golden Gate Ballroom C: AI in the Fortune 500
11:55 am → 20 min

How Intuit uses LLMs to explain taxes to millions of taxpayers

  • AI in the Fortune 500 (L2)
SOMA: AI Architects
11:55 am → 20 min

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

  • AI Architects (L1)
Yerba Buena Ballroom 7&8: SWE Agents
11:55 am → 20 min

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

  • SWE Agents (11)
Golden Gate Ballroom A: Retrieval + Search
11:55 am → 20 min

Evaluating AI Search: A Practical Framework for Augmented AI Systems

  • Retrieval + Search (09)
Foothill C: Security
11:55 am → 20 min

Fuzzing in the GenAI Era

  • Security (13)

12:00 pm

Keynote/General Session (Yerba Buena 7&8)
12:00 pm → 120 min

Break

12:05 pm

Yerba Buena Ballroom 2-6: Reasoning + RL
12:05 pm → 20 min

Post-Training Open Models with RL for Autonomous Coding

  • Reasoning + RL (15)
Foothill G 1&2: Design Engineering
12:05 pm → 20 min

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

  • Design Engineering (10)
Foothill E: Autonomy + Robotics
12:05 pm → 20 min

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

  • Autonomy + Robotics (16)

12:15 pm

Golden Gate Ballroom C: AI in the Fortune 500
12:15 pm → 20 min

Ship it! Building Production-Ready Agents

SOMA: AI Architects
12:15 pm → 20 min

AX is the only Experience that Matters

  • AI Architects (L1)
Yerba Buena Ballroom 7&8: SWE Agents
12:15 pm → 20 min

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

Golden Gate Ballroom A: Retrieval + Search
12:15 pm → 20 min

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

Foothill C: Security
12:15 pm → 20 min

Building with Open Standards for Agents

12:30 pm

Nobhill A&B: Expo Sessions
12:30 pm → 15 min

Serving Voice AI at Scale

Willow: Expo Sessions
12:30 pm → 15 min

Optimizing inference for voice models in production

Juniper: Expo Sessions
12:30 pm → 15 min

Prompt Engineering is Dead

12:45 pm

Nobhill A&B: Expo Sessions
12:45 pm → 15 min

Agentic GraphRAG: Simplifying Retrieval Across Structured & Unstructured Data

Willow: Expo Sessions
12:45 pm → 15 min

Agents, Access, and the Future of Machine Identity

Juniper: Expo Sessions
12:45 pm → 15 min

Building CISO-approved agent fleet architecture

2:00 pm

Golden Gate Ballroom C: AI in the Fortune 500
2:00 pm → 20 min

How to Build Planning Agents without losing control

  • AI in the Fortune 500 (L2)
SOMA: AI Architects
2:00 pm → 20 min

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

Yerba Buena Ballroom 7&8: SWE Agents
2:00 pm → 20 min

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

  • SWE Agents (11)
Yerba Buena Ballroom 2-6: Reasoning + RL
2:00 pm → 20 min

How to Train Your Agent: Building Reliable Agents with RL

  • Reasoning + RL (15)
Golden Gate Ballroom A: Retrieval + Search
2:00 pm → 20 min

Ingest, Chunk, Retrieve: How We Built an AI Sales Rep that Trains Herself

  • Retrieval + Search (09)
Golden Gate Ballroom B: Evals
2:00 pm → 20 min

[Evals Keynote] tba

  • Evals (12)
Foothill C: Security
2:00 pm → 20 min

How to defend your sites from AI bots

  • Security (13)
Foothill G 1&2: Design Engineering
2:00 pm → 20 min

AI and Human Whiteboarding Partnership

  • Design Engineering (10)
Foothill F: Generative Media
2:00 pm → 20 min

General Intelligence is Multimodal

  • Generative Media (14)
Foothill E: Autonomy + Robotics
2:00 pm → 20 min

Teaching Cars to Think: Language Models and Autonomous Vehicles

  • Autonomy + Robotics (16)

2:25 pm

Golden Gate Ballroom C: AI in the Fortune 500
2:25 pm → 20 min

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

  • AI in the Fortune 500 (L2)
SOMA: AI Architects
2:25 pm → 20 min

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

  • AI Architects (L1)
Yerba Buena Ballroom 7&8: SWE Agents
2:25 pm → 20 min

Software Development Agents: What Works and What Doesn't

  • SWE Agents (11)
Yerba Buena Ballroom 2-6: Reasoning + RL
2:25 pm → 20 min

What Reinforcement Learning with Verifiable Rewards Changed

Golden Gate Ballroom A: Retrieval + Search
2:25 pm → 20 min

Building a Smarter AI Agent with Neural RAG

  • Retrieval + Search (09)
Golden Gate Ballroom B: Evals
2:25 pm → 20 min

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

  • Evals (12)
Foothill C: Security
2:25 pm → 20 min

How to Secure Agents using OAuth

  • Security (13)
Foothill G 1&2: Design Engineering
2:25 pm → 20 min

tldraw.computer

  • Design Engineering (10)

2:50 pm

Golden Gate Ballroom C: AI in the Fortune 500
2:50 pm → 20 min

Building Agents (the hard parts!)

  • AI in the Fortune 500 (L2)
SOMA: AI Architects
2:50 pm → 20 min

The Web Browser Is All You Need

  • AI Infrastructure (05)
Yerba Buena Ballroom 7&8: SWE Agents
2:50 pm → 20 min

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

  • SWE Agents (11)
Golden Gate Ballroom A: Retrieval + Search
2:50 pm → 20 min

Layering every technique in RAG, one query at a time

  • Retrieval + Search (09)
Golden Gate Ballroom B: Evals
2:50 pm → 20 min

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

  • Evals (12)
Foothill C: Security
2:50 pm → 20 min

How we hacked YC Spring 2025 batch’s AI agents

  • Security (13)
Foothill F: Generative Media
2:50 pm → 20 min

Operationalizing AI Interpretability

  • Generative Media (14)

3:00 pm

Keynote/General Session (Yerba Buena 7&8)
3:00 pm → 45 min

Break

3:15 pm

Willow: Expo Sessions
3:15 pm → 15 min

Cattle, not genies: building AI agents from first principles

Juniper: Expo Sessions
3:15 pm → 15 min

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

3:30 pm

Willow: Expo Sessions
3:30 pm → 15 min

Amping it up: an experimental research demo of coding agents to uplevel humans building software

3:40 pm

Keynote/General Session (Yerba Buena 7&8)
3:40 pm → 20 min

Doors

4:00 pm

Keynote/General Session (Yerba Buena 7&8)
4:00 pm → 20 min

Alex Atallah Keynote

4:20 pm

Keynote/General Session (Yerba Buena 7&8)
4:20 pm → 20 min

Trends Across the AI Frontier

4:40 pm

Keynote/General Session (Yerba Buena 7&8)
4:40 pm → 20 min

Prompt Engineering is Dead - Everything is a Spec

5:00 pm

Keynote/General Session (Yerba Buena 7&8)
5:00 pm → 20 min

AI Engineer World's Fair Hackathon - Grand Prize

Session and Speaker Management powered by Sessionize.com