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 Tuesday, June 30 · 166 sessions
Expo Stage 1 NE
Expo Stage 2 NW
Expo Stage 3 SW
Expo Stage 4 SE
Leadership 1
Leadership 2
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
Every AI company is accidentally building a bank.
Give your coding agents the power of turbogrep!
Your Agent Is Lying to You About Whether It Worked
Every Agent, Everywhere, All at Once
Who Approved That MCP Server? Governing the Tool Layer
Beyond Golden Signals: Monitoring in the Age of GenAI
6 Pillars of an Agentic Harness That Fixes Production Incidents
Can Your Agent Hear You Now?
How We Built the Airbyte Agent MCP Server and CLI
The Enterprise Agentic Gap: When Developer-Level AI Tools Hit Millions of Lines
Actionable Knowledge For Agents With Context Graphs
Agentic vs. Vector Search: An Eval-Driven Approach to Coding Agent Performance
Why building building agent quality platforms is hard.
Voice Agents Are Mostly Invisible. Here's How to See Them.
Build agents fast with GitHub Copilot (from idea to working app)
Video Discovery for Agentic World-Model Training
From Context to Memory: Your Agents Need a Real Memory Layer
From Chatbots to Agents: How Reducto builds for Agent Experience to Enable Real Work
How PayPal Enterprise Payments handles agent-initiated payments across ChatGPT and Google AI Mode
Frontier models for the hard parts, open weights for the rest
Agents Don't Have Coworkers, They Have Hostages
Can LLMs write fast multi-GPU kernels? We built a benchmark to find out.
Designing Evals That Earn User Trust
what we learned by analyzing 1M AI generated PRs
Building agents is trivial now, context is the next frontier
Running a 20T-Token Data Pipeline: Infrastructure Lessons from Production
Towards Reliable Financial Agents: How a 4B Model Outsmarted a 235B Giant
Agentic Search for Coding Agents
Agents, codebases, and teams: what it actually takes to ship together
Would your AI agent get the job? A performance review framework for enterprise agents
Self-Improving Agents That Teach the Company Back
Deploying browser agents at scale
Continuous Engineering: Software Development for the Age of Agents
Self-Driving Production: AI Wrote your Code. AI Should Fix It, Too
From raw documents to AI-ready data
AI Enablement at Automattic: How a Remote Company Builds AI Fluency
Inside the AI economy: What Stripe’s data reveals
Building the engine while flying the plane — launching the Figma MCP server
Agentic SDLC at Uber: Building Blocks for Uber's Software Factory
Scaling Code Quality: Building uReview, Uber’s Multi-Agent Code Review Engine
Spin at the Gate Until Green: The Engineering Primitives Behind Self-Driving Codebases
AI Evals Platform for Cross-Functional Teams at Scale
Productionizing LLM Gateways: Architecture, Tradeoffs, and Hard Lessons from the Trenches
From AI-Assisted to AI-Native: Building a Frontier Development Team
How to Get Your Org to Adopt Coding Agents (Without Shipping Garbage)
Governance Is the Real Bottleneck to AI ROI
Your Agent Evolved. Your Evals Didn't.
The Last Human Code Review: Building Trust in AI-Generated Code
Prototyping as Leadership: How a CTO Ships with AI Agents
Serving 2 Million Models Without Melting: Scaling the Hugging Face Hub
IT Admin for the AI Workforce: Why Your AI Agents Will Need Their Own IT Department
The Era of Compound Engineering
How I automate my own job at Hugging Face using agents
Your Fine-Tuned Model Is Tech Debt: A 50x ROI House of Cards
Unlock Agent Autonomy: The Runtime for AI-Native Systems
The Golden Age of AI Engineering
GLM-5.2: Frontier Intelligence, Open Weights.
Getting the most out of Codex
Rise of the Software Factory
Orchestras, not Factories
What we learned by analyzing 1M AI-generated PRs
Get Out of the Model's Way
Self-Improving software factories: The new open source model"
We're the bottleneck, but we don't have to be
Loop Engineering from first principles
Harness Engineering is not Enough: Why Software Factories Fail
In Code They Act, In Proof We Trust
Recursive Model Improvement
Security Firewall for Agents
Your Agent Didn’t Fail. Your Harness Did.
Everyone Gets A Software Company
Tethered: Our Agents Are Us
Agents' next frontier: agent-to-agent and network effects
Claude for long-horizon tasks
From coding to Knowledge work agents
Your company brain will leak secrets. Here's how we stopped it for big banks and ourselves.
Every Harness Will Become A Claw
Gadgets: Personal app vibe coding that is actually safe
Building the Document Context Layer for AI Agents
Skill issue: stop deploying vision language models, use them with Skills to build e2e vision apps on edge
Modality Misalignment and Originality Attribution in Short-Form Video: A Multi-Agent Approach at Platform Scale
From Ingestion to Agents: How Leading AI Teams Build on Document Intelligence
The Best Models Still Reason Like Toddlers
You’re Not Thinking Big Enough: Rebuilding Food Systems from First Principles with AI Agents
From VLM/VLA's to Embodied Agents
From Scratch to SOTA: Training a 3B State-Space Vision Model for 1.4 Billion People
The unreasonable effectiveness of BM25 for agentic search
The Search Engine for the Agentic Web
Rebuilding the web for agents
If we want them to do Knowledge Work, we need to design Knowledge Agents
Your Agreements Are a Database You Can't Query. We're Fixing That
How to Connect AI to Billions of Legal Documents
Where RL Will Take Search
Stop Chunking Like It's 2022
Claude Managed Agents Workshop (Part 1)
Claude Managed Agents workshop (Part 2)
Claude Managed Agents workshop (Part 3)
Claude Managed Agents workshop (Part 4)
Everybody Gets a Digital Clone! (Part 1 of 3)
Everybody Gets a Digital Clone! (Part 2 of 3)
Everybody Gets a Digital Clone! (Part 3 of 3)
Setting Yourself Up for Success — Part 1
Setting Yourself Up for Success — Part 2
Setting Yourself Up for Success — Part 3
Through the AI Fog: The architectural decision the next 24 months of agentic security depends on.
Your LLM Stack Is a 2008 Database With Better Marketing: Why ML Security Is Dominated by Misconfiguration, Not Missing Features
We Gave an Agent Production Code Access and Then Tried to Sleep at Night
Agentic Development Security
Using LLMs to Secure Source Code
Dual-Surface Architecture: Serving Humans and Agents from the Same Tool Layer
Agentic Security: Permissions, Provenance, and the Agent Supply Chain
It's 10pm. Do You Know Where Your Agents Are?
AI’s Jurassic Park Period
The New Primitives: Building AI-Native Software
Speech-to-Speech Model Research at Google DeepMind
Voice Agents Can Just Do Things
Your Voice Agent is Just a Walkie-Talkie
Tolan: Voice-First AI Companion
5 Voice Agent Failure Modes You'll Hit in Week One
I Monitored Crime Audio. Voice Agents Scare Me More.
Realtime Voice Agents with Frontier Intelligence
"My name is... my name is...": A Linguistic Map for Building and Debugging Voice Agents
Act, Confirm, or Stop? Smarter behavior for AI assistants, wearables & robots
Tokens In, Engagement Out: Training LLM-Recommenders
From approval loops to autonomous agents with Docker pt1
From approval loops to autonomous agents with Docker pt2
From approval loops to autonomous agents with Docker pt3
From approval loops to autonomous agents with Docker pt4
From approval loops to autonomous agents with Docker pt5
How Forward Deployed Engineering is done at Factory
How Forward Deployed Engineering is done at Cursor
AI tools for Forward Deployed Engineering
How Forward Deployed Engineering is done at Cognition
The Dirty Secret of Forward Deployed Engineering
How Forward Deployed Engineering is done at Decagon
How Forward Deployed Engineering is done at Ramp
Forward Deployed Engineering 101
How Forward Deployed Engineering is done at Kepler
Data Quality is the Compute Multiplier
The Messy Reality of Scale: Synthetic Data and Pre-Training at Poolside
Rethinking Environments for Long Horizon Work
Bugcrowd posttraining talk
Scaling to Long-Horizons: Algorithms, Environments, Compute
When Will The Benchmaxxing Plague End?
Building Worlds for Models
Data and Environment Curation for Post-training LLMs
Build agents fast with GitHub Copilot (from idea to working app)
Use Copilot across CLI, dev, and cloud workflows to move faster end-to-end
Modernize CI/CD using agent-assisted workflows that reduce manual debugging
Using AI tools to teach old apps new tricks
Surviving Your Own Velocity: How VS Code Ships Weekly with 40 People