June 29 – July 2, 2026 · San Francisco, CA · imported from ai.engineer's public schedule feed
AI Engineer World's Fair 2026 — unofficial import demo Unofficial demo. This programme was imported from the AI Engineer World's Fair's own public schedule feed to show vibeboard at real conference scale. Not affiliated with, or endorsed by, the organisers.
Sessions Speakers Agenda Itinerary Gallery Thursday, July 2 · 171 sessions
Expo Stage 1 NE
Expo Stage 2 NW
Expo Stage 3 SW
Expo Stage 4 SE
Leadership 1
Leadership 2
Leadership Lounge
Main Stage
Networking Room
OpenAI Booth
Track 1
Track 2
Track 3
Track 4
Track 5
Track 6
Track 7
Track 8
Track 9
Track M
8am
9am
10am
11am
12pm
1pm
2pm
3pm
4pm
5pm
AI Engineering & Governance 2026 Trends
Beyond RAG: See a relational context engine reduce token burn
The Art of Building Verifiers for Computer Use Agents
The Missing Layer in Agentic AI
Trust, But Verify: Human-in-the-Loop for Agents That Actually Matter
Optimizing Open Models for Production Grade Inference
Harness Engineering: The New Core Skill for Agentic Developers
Agent Memory Is a Solved Problem. Agent Learning Is Not.
Taking Reinforcement Learning Cross Datacenter
Your Agent Can't Tell If It's Right
ARIA, how we built autoresearch with autoresearch
Seeing the Plumbing: Profiling vLLM Speculative Decoding on NVIDIA Blackwell
While You Were Generating: The Verification Gap Nobody Talked About
12:30 PM – 1:30 PM
Latent Space Live: the Inference Inflection from First Principles
swyx swyx, Rob Wachen
YOLO Mode, Safely: microVM Sandboxes for Any Agent
MCP doesn’t suck — your agent does
Improving AIE: Q&A and Feedback Session
Improving AIE: Q&A and Feedback Session (repeat)
No, That's Not a Software Factory
The Lethal Trifecta Is Already on Your Developers' Laptops
Voice is the universal interface
Move fast and (don’t) break things
Your Model is Private. Your System Isn't.
The Human Is an Async API
Small Claws Are Beautiful: Edge Agents with NanoClaw, Raspberry Pi, and Graph Memory
An Interaction Is All You Need
Vector Isn't Enough: Hybrid Search & Retrieval for AI Engineers
Your AI Agent Has No Nervous System
The Next Run Should Be Better
Agents That Forge Their Own Tools: Self-Modifying AI in the Wild
Video Discovery for Agentic World-Model Training
Everyone talks about document search, but what about results?
An AI Future Without the Lock-In
Building safe payment infrastructure for machine-to-machine commerce
Tribal Dungeons of Global Shipping: AI Agents at Global Scale
All the Things We Have to Do to Satisfy Your Insatiable Need for Tokens
Stop Model Shopping: Why Ownership Beats Choice in the Agent Stack
From Zero to AI-Native: Scaling AI Across the Org
Which AI startups actually land enterprise contracts? Lessons from evaluating 100+ AI startups at Millennium Management
Your Hero Agent Needs a Party
AI Agents Are Just Distributed Systems Now
The Signal Layer: What to Build When Anything Can Be Built
Tell the Robot What You Want
The Agent Behind the Curtain: Building the Oz Cloud Agent Platform
FinOps for AI Agents: Who Spent All the Tokens?
What If Your Chip Design Team Moved Like a Single Body?
Preferences > Benchmarks: Model Routing for How Teams Actually Build
Coding Agents Don't Scale Themselves. Neither Do Your Teams.The Rise of Agent Enablement.
Agent Frameworks Considered Harmful
Inside 847 Production Clinical AI Notes
Give the Agent a Budget, Not a Token
11:00 AM – 12:00 PM
The Agentic Product Development Organization
Martin Harrysson, Matt Linderman, Prakhar Dixit
The 2026 State of AI Engineering
TCP and RDMA are Killing Inference Throughput; Homa can Fix It
The Unreasonable Effectiveness of Separating the Task from the Model
How Anthropic Builds: Lessons from Labs
Thinner Agents on a Smarter Substrate: The Ontology-based Semantic Layer
MCPs, CLIs, and Skills: Choosing the Right Tooling Layer for Agentic Development
Auth for Agents: Unblock Autonomous AI with auth.md
Harness Engineering: Building the Production Cage for Powerful Domain Agents
Loophole - Adversarial Agents To Stress Test Your Morality
🎵 Every step you take, every call you make - the reliable agent stack
We let an AI agent execute Bash and lived to talk about it
No Memory, No Harness: Why the Database Is the Last Line of Defense
How we Solved Agent Building
Agents Without Code: How Skills, YAML, and Filesystems Replaced Python
Closing Keynote — Theo Browne
Closing Keynote: Garry Tan
8:30 AM – 10:30 AM
8:30 AM
10:45 AM – 1:00 PM
$100,000 AIE Startup Battlefield — presented by Hyperagent
Howie Liu
AMA with Theo Browne (@t3.gg)
Theo Browne
Training Krea 2 - What matters in generative model training.
Building an Agentic Video Editor for Mass Consumer
The Next Game Engine Won't Have a Manual
While my guitar gently speaks
Voice agents with Realtime Video
Generative Video at the Speed of Light
Infra behind Krea 2 - How to train and serve at scale
The Next Medium: Why Real-Time Interactive Video Changes Everything for Developers
Designing Multimodal Collaborative Agents for Next-Gen Commerce
Why Your AI Agent Needs a Wallet: Agentic commerce on Arc with USDC and Nanopayments
When AI Agents Pay and Sellers Monetize: Building x402 Apps for Agentic Commerce on AWS
Agent Spending Without Controls: The Missing Infrastructure Layer for AI Pa…
The Agentic Commerce Stack
Your Agent Just Authorized What?!
The End of the Static Screen: Architecting Intent-Driven UX with Agentic Orchestration
Beyond the Lethal Trifecta: Agentic Commerce on the Open Internet at Machine Speed
ALPHALAB: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs
Why Off-the-Shelf AI Doesn't Understand Money
Let's integrate AI Agents in Event-Sourced Systems
How Kepler Built Verifiable AI for Financial Services
Build for the Memo, Not the Demo — Notes from 200 Investment Committees
We Vetted 2,000 AI Skills Before They Reached Developers
Your Finance Agent's Bottleneck Is You
Simulation-Maxxing: How Nubank ships agents 20× faster with simulations
Skills are new features: Building Skill-Centric Harness for Agentic Products
Wearing the Agent: Engineering a Family-and-Friends Personal Agent, from Group Chats to Glasses
State of the Union: Why Local, Why Now
State of the Union: Why Local, Why Now
Demo: GLM 5.2 on DGX Station — Frontier Intelligence Under Your Desk
Local Models: Trust, Control, Optimization
Local Models: Trust, Control, Optimization
CrabRAG: Why Automated Assistants Need Graph Memory, Not More Tokens
Active Graph Agent Runtime (BabyAGI 4)
Your Moat Is Your Data Model
From Systems of Record to Systems of Context
AI : Learned Execution Graphs for Real-Time Anomaly Detection & Drift Classification in APIs
Why Agentic Systems Need Ontologies
Video Has No Memory. Here's How We Built One.
On-Device Agentic AI for the New York Times Games
Citation Needed: Provenance for LLM-Built Knowledge Graphs
Why We Killed Our Multi-Agent Pipeline: Lessons From Pharma Commercial Intelligence
GTM Engineering: The Technical Bits
Reverse-Engineering the AI Buyer
The Building Blocks of GTM Orchestration
How Juries and Librarians Can Solve GTM's AI Trust Problem
How We Got LLMs to Recommend Our Open Source Library (Without Paying or Plug-ins)
Knowledge Systems: The New GTM Stack
How AI Agents Let GTM Teams Scale
Building GTM AI Agents: Lessons from Deploying to 6,000 Users
The Death of Developer Advocates
From Ambient Documentation to Clinical Intelligence
Guardrails First: Engineering Member-Facing Health AI
Shipping AI to a Million Patients Without an A/B Test
200 Million Patient Interactions Later: What the Generic Voice Stack Misses
Al is becoming the World's largest Relationship Therapist. We Can't Afford to Get it Wrong.
Healthcare’s Agent Bytecode: X12 as the Harness for AI Agents
Trading Desks to Clinical Trials: Parallels in Applied Vertical AI
How to build an AI-Native Health Company
Why Your Enterprise Tech Stack Isn't Ready for AI Agents - And What to Build Instead
DeepSWE: expert code datasets
Anthropic's CCA Exam as a Field-Guide for Agentic Engineering
Guide, Verify, Solve: The Engineering Discipline Agentic Development Demands
Benchmarking Coding Agents on New vs Legacy Code bases
Codex, Behind the Harness
Multiplayer agentic engineering: enabling your whole team and your best agents to work together
Always-on agents run production without the on-call tax
Realtime multiplayer, automation, and you!
Velocity Sickness: What Happens When Your Whole Team Gets 10x Faster
Open Source Is Dead. Long Live Open Source.
Operating Distributed Inference Systems at Scale
Routing LLM Inference in Production: From Engine Signals to Policy
Are LLM Performance Benchmarks Reliable?
Vertical Mobility: Building an AI Inference Platform That Scales from MVP to Trillion-Parameter Workloads
What's New in Inference Engineering
Large clusters for small models
The Frontier AI Inference Cloud for Agents
KV Cache-Aware Routing and P/D Disaggregation on Kubernetes: The Parts Public Benchmarks Don't Show
Two Bugs That Hid in Plain Sight: A vLLM Debugging Detective Story
Weight Folding, CUDA Streams, and the Bug That Made My Model Speak Backwards
Diagnosing agent failures in production
Tracing and debugging agents across systems with OpenTelemetry
Benchmarking VS Code with VSC-Bench: How to measure agent performance
Design multi-agent systems that actually work
Evaluating and optimizing AI agents: from observability to continuous improvement
Blast Radius Zero: One‑Command OpenClaw Sandboxes in the Cloud
Operate agents safely at scale with enterprise governance