Reliable Computer Use Agents require coding
Even the world's best computer-use agents cannot repeat their successes at the moment. Agents that write code — emitting structured selector-based actions instead of clicking pixels — break through that ceiling. We'll share two years of experience from Simular's production agent platform, the architectural decisions that mattered (refs over pixels, code as substrate, Simulang DSL), and a live demo: a 30-step unattended Windows workflow, side-by-side with a vision-only baseline. If you're shipping agents to real users, this is the playbook.
About the Workshops Day 1 Track
Workshops Day 1 sessions at AI Engineer World's Fair 2026 in San Francisco.
When
Monday, June 29, 2026
4:30 PM - 5:30 PM·1h
Where
Track 1 · Room 2010
Capacity: 250 attendees
Sign in to add this talk to your schedule.
Speaker
Ang Li
CEO and Co-Founder
Simular
@angli_ai
Ang Li is the CEO and co-founder of Simular, a research-driven AI company building autonomous computer agents with human-level capabilities. Formerly an AI researcher at Google DeepMind, Ang co-founded Simular to bridge the gap between frontier research and production-ready agentic systems. Under his leadership, Simular won the Best Paper award at the ICLR 2025 Agentic AI Workshop and has raised $27 million from investors including NVentures (NVIDIA) and Felicis. Ang is a graduate of the Google for Startups Cloud AI Accelerator and StartX. He speaks regularly on the future of human-computer interaction at industry events including Google Cloud Next, AI2, GenAI Summit, and Morgan Stanley Tech Week.