harness-engineering
80 talks
Tribal Dungeons of Global Shipping: AI Agents at Global Scale
From AI-Assisted to AI-Native: Building a Frontier Development Team
Einstein Arena: Harnessing Collective Agent Intelligence for Open Science
The Agent Behind the Curtain: Building the Oz Cloud Agent Platform
Agentic SDLC at Uber
The Era of Compound Engineering
Healthcare's Agent Bytecode: X12 as the Harness for AI Agents
Bringing agents onto the World Wide Web
Improving Agents is a Data Mining Problem
Agents, codebases, and teams
The Evolution of Agentic Surfaces
Codex, Behind the Harness
Rethinking Environments for Long-Horizon Work
Fighting Slop with Slop
Learning on the Job: The Future of Post-Training
The Data for Fully Autonomous Software Engineers and Companies
Your Finance Agent's Bottleneck Is You
Morgan Stanley's ALPHALAB: Multi-Agent Research Across Optimization Domains
Skills are New Features: Building a Skill-Centric Harness
Your Agent Didn't Fail. Your Harness Did.
How Forward Deployed Engineering is done at Factory
How Forward Deployed Engineering is done at Ramp
Loop Engineering from First Principles
Everything Is a Rollout
Harness Engineering is Not Enough: Why Software Factories Fail
Claude for Long-Horizon Tasks
Every Harness Will Become A Claw
AI's Jurassic Park Period
Don't Let the LLM Drive
When Agents Meet Physical Data: The Other Physics of Agent Harnesses
Your Voice Agent Doesn't Need a Frontier Model
Your Agents Need a Save Button
The Great Loops Debate
Using LLMs to Secure Source Code
The engineer of the future is the person who is able to choose what is worth doing.
Modern Post-Training: A Deep Dive
Recursive Language Models for Large Codebases
The Golden Age of AI Engineering
Your agent is blindfolded
Your coding agent doesn't always follow your rules
Beyond the Harness: A Journey Towards Adaptive Engineering
Respect The Process
What if the harness mattered more than the model?
Harness Engineering & Startup Battlefield
Autoresearch & Keynotes
Agents Building Agents
Recursive Coding Agents
Evals Are Broken, Use Them Anyway
Dark Factory: OpenClaw Ships Faster Than You Can Read the Diff
How I Deleted 95% of My Agent Skills and Got Better Results
Bounded Autonomy: Between Free Will and Determinism
The Missing Primitive for Agent Swarms
Don't Build Slop (4 Levels of AI Agent Maturity)
Build Agents That Run for Hours
Harnesses in AI: A Deep Dive
AIE Singapore Day 1
Make your own event-sourced agent harness using stream processors
CI/CD Is Dead, Agents Need Continuous Compute and Computers
Build Dumb AI Loops That Ship
Replacing 12K LoC with a 200 LoC Skill
Building your own software factory
Code Mode: Let the Code do the Talking
Harness Engineering: How to Build Software When Humans Steer, Agents Execute
Building pi in a World of Slop
AIE Europe Keynotes & Coding Agents
Automating Large Scale Refactors with Parallel Agents
Claude Agent SDK [Full Workshop]
How Claude Code Works
Amp Code: Next Generation AI Coding
Making Codebases Agent Ready
AI Kernel Generation: What's Working, What's Not, What's Next
Future-Proof Coding Agents
Agents are Robots Too: What Self-Driving Taught Me About Building Agents
AI Leadership
Ship Agents that Ship: A Hands-On Workshop
Stateful environments for vertical agents
Containing Agent Chaos
AI Engineer World's Fair 2025, Day 2 Keynotes & SWE Agents Track
Arrakis: How to Build an AI Sandbox from Scratch
Code Generation and Maintenance at Scale