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 Wednesday, July 1 · 166 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
Track 1
Track 2
Track 3
Track 4
Track 5
Track 6
Track 7
Track 8
Track 9
Track M
9am
10am
11am
12pm
1pm
2pm
3pm
4pm
5pm
Harnessing Agents: The Durable Runtime for Dynamic Workflows
Fault-Tolerant Training at Scale: Making Hardware Failures a Non-Event
Your agent architecture has a half-life of 6 months
Edge-Native AI: Building Ultra-Fast Agents and MCP Servers with Spin
Power agents with Microsoft IQ
Inference performance as a competitive advantage
The Self-Improving OSS Agent Stack
Modular: Taming the AI Hardware Cambrian Explosion
AI Engineering & Governance 2026 Trends
AI-Assisted Engineering: 5 Trends We're Seeing From 500+ Organizations
How to generate mergeable code with a context engine
From Stateless to Stateful: Orchestrating Real-Time Voice & Messaging Agents with Twilio and Amazon Bedrock
Surviving Your Own Velocity: How VS Code Ships Weekly with 40 People
Why your company needs a context graph, and how to build it
Beyond Code Generation: API Context for Agentic Engineering
Building an Agent Harness for the Business, Not the Builder
AI Applications in a flash! No Dev Ops. Just code.
Building on the Codex Harness
Why AI Didn't Actually Make You Ship Faster
The Death of Keyword Search and the Rise of Agent-Readable Catalogs
Harnessing Collective Agent Intelligence for Open Science
Why Agents Should Have Their Own Sandbox
Warp: Building Self-Improving Agent Software Factories
Latency Is a Budget. Humanlike Is the Goal.
The Frontier Is Coming Home
The Infinite Context Window Is a Myth: Context Engineering for AI Agents
Stop Renting Intelligence: The Train-to-Deploy Loop for Specialized AI
Redesigning how software gets built
FDE Playbook: Build an AI Support Agent and Give It a Voice
AI agents don't read your policy docs. They hit your APIs.
Prompt, Memory, Weights: The Architecture Decisions Most AI Teams Make by Accident
Natively Multimodal from Step Zero
Your Stack Has a Latency Problem You Can’t See
Continuous Offensive Security the only approach in an agent-first world
Vibe Code Safely: Introducing Gadgets
Ray Actors, Vision Tokens, and the GIL: Engineering an SFT Data Pipeline That Keeps GPUs Busy
How do you diffuse AI into the real world?
How to avoid disaster when vibe-coding a billing engine
Your Code Has Bugs. Lean4 Has Proofs. A Practical Guide to Formal Verification for Engineers
AI-Native Organisations runs on Skills: How to Extract, Structure, evaluate and Scale Them
The Half Life of Agent Infrastructure
Guardians of the State: How We Built an Air-Gapped AI Fortress for Consumer Data
From Tokenmaxxing to Trusted Throughput
Agents Are Where Microservices Were in 2015. We're Making All the Same Mistakes.
Agentic Sites: Building Hyper Personalized Websites
The Chief AI Officer: A framework for the emerging Swiss Army Knife of roles
The Z/L Continuum: Should AI Engineers Still Read Code?
Is Orchestration the Future?
How to Kill the Code Review
The Death of the Code Review
Tokenmaxxing is the New "Lines of Code"
Engineering Agency out of the Happy Path
I Let Agents Refactor My Codebase for 3 Weeks. Then I Read the Code.
Intelligent Model Routing: Frontier Performance Without Frontier Bills
Inference is the New Training Loop: Architecting High-Reliability Agents and Continuous AI Systems
The state of AI in software development: Insights across 400+ organizations
11:00 AM – 12:00 PM
Tokenomics: From AI Spend to AI Value
Martin Harrysson, Matt Linderman, Prakhar Dixit
In the Land of AI Agents, the Verifiers Are King
Research to Reality with Google DeepMind
First Steps Toward Automated AI Research
Autoresearch for Dense Retrieval: Test-Time Compute with Frozen Embedding Models
Memory Harnesses for Long-Running Research Agents
« the era of (auto) research »
Closing the Loop: An Autonomous AI Research Agent
An AI Agent Became the #1 Contributor in OpenAI's Hiring Challenge
Self-Improvement of Context, Harness, and Model Weights through Reflective Optimization
Autoresearch in a Multi-Agent AI Village
Don’t build agents, build environments
Letting the Interns Loose — How We Accelerated AI Adoption.
Kubernetes Is Not Your Sandbox
Your agent needs a sandbox, not a desert
From fork() to Fleet: Designing an Agent Sandbox Cloud Pt 1
From fork() to Fleet: Designing an Agent Sandbox Cloud Pt2
1,000 Agent Tasks in a Sandbox: What Breaks When LLMs Write and Run Code
The Next Trillion Users of the Internet Still Don't Have an Identity
Sandboxes Aren't Optional: Runtime Isolation Patterns for Coding Agents at Scale
Building ambitious software
Building the simulation infrastructure for practical world model use
Building the simulation infrastructure for practical world model use (Part 2)
Commercial Grade-Robots for Real World Usage
Unitree: Building Mass Produced Humanoids
Frontier Robotics Research
From Manual Drones to Autonomous Multi-Agent Missions
Why Large? Tiny LMs & Agents on Edge/Robotics
From Self-Driving Monorepo to Self-Driving Cars
Beyond Static Intelligence: Evaluating Continual Learning
Scaling up Continual Learning
Scaling Compute on Context
Intelligence + Continual Learning = Expertise
Adaption Labs — Gradient-Free Continual Learning
Improving Agents is a Data Mining Problem
Bringing Continual Learning into Enterprises
Designing Agents (The Floor Is the Frontier)
Lessons from Studying Every Memory System
LLM Knowledge Bases: a practical guide
Build realtime multimodal agents with Gemini Live
Build realtime multimodal agents with Gemini Live (continued 2)
Build realtime multimodal agents with Gemini Live (continued 3)
Build realtime multimodal agents with Gemini Live (continued 4)
The Agentic Power User's Playbook: Tips and Tricks for Swarm-Style Agentic Development
The Agentic Power User's Playbook: Tips and Tricks for Swarm-Style Agentic Development (continued 2)
The Agentic Power User's Playbook: Tips and Tricks for Swarm-Style Agentic Development (continued 3)
Don't Write Skills, Train Models
Don't Write Skills, Train Models (cont. 2/3)
Don't Write Skills, Train Models (cont. 3/3)
Vending-Bench: Long-Horizon Agent Evals for a Simulated Vending Business
From Signal to PR: Anatomy of a Self-Improving Agent
Building Closed-Loop Evals for a Multimodal Agent at Uber Scale
From Agent Traces to Agent Simulations: The next era of agent evaluation
Model Whisperers: How Evals and Prompts Shape Agent Behavior
Evals Driven-Development: Engineering a Mental Health AI Coach Ethically & Safely
Don't Ship Skills Without Evals
Understanding is the new bottleneck
The Spatial Harness: Bringing Agents to the Canvas
The Design-Code Roundtrip That Isn't
Mousepower: agents that can’t be measured, can’t be managed.
Design at the Speed of Adjectives
The Missing Layer: Design Taste in AI Agents // Stop Letting Your Agents Ship Ugly UIs
Generative UI... in Python?
One Designer + Al. Hundreds of Deliverables.
Computer-use models will agentify the web, not APIs
Computer Use at the Edge of the Statistical Precipice
Bringing agents onto the world wide web
The Dark Arts of Web Automation: Teaching Agents to Use Websites Like Humans
The Rise of CaaS: Context-as-a-Service for Agentic AI
Computer-Use 2.0: Agents Just Got Multi-Cursor
Will AI predict people like we predict the weather? (alternate title “A field guide to synthetic personas for market research”)
How Web Data Infrastructure Powers the Next Generation of AI
Build-Time vs. Run-Time: Why Your Dev Tools Will Fail in Production
It’s Tokens All The Way Down: How RLMs are Different
500 Skills, Zero Fine-Tuning: LinkedIn's Playbook for AI Agents That Actually Know Your Codebase
Your agents lack context: Here's how to fix "You're absolutely right!"
How long can your skills be before your agent forgets what you told it?
WTF Is the Context Layer? The Missing Infrastructure for Production Agents
MCP Apps - Extending the frontier
MCP Apps: Give the Model Data, Give the User a UI
MCP Tasks (async)/ Why the heck aren't any agents supporting MCP tasks/async?
The Universal Remote Control for AI
Training Frontier Models to Out-Think Hackers
Learning on the job: the future of post-training
Reinforcement Learning without Verifiable Rewards
Emulated: The data for fully autonomous software engineers and companies
Agents at Scale: Inside MiniMax's Model and the Infrastructure Behind It
Benchmarks: The Good, the Bad, and the Ugly
From framework to runtime: running agents with Foundry Agent Service
OpenAI, Anthropic, or agent frameworks: choose the right AI stack
Power agents with Microsoft IQ
Deploy agents to users in M365, Teams, and apps