Niantic Spatial's Inhi Cho Suh and Eugene Chong on building the layer between the physical world and AI
In this episode
Despite the wealth of information LLMs draw on, they are not reliably grounded in the physical world. Spatial knowledge is rarely written into agentic development and remains invisible to LLMs. This episode’s guests, Niantic Spatial’s CEO Inhi Cho Suh and Director of Product Management Eugene Chong, are building a grounding layer to fill that gap. Inhi and Eugene join 1Password CTO Nancy Wang and Google Gemini’s Dev Tagare to discuss why spatial understanding is a prerequisite for AI systems operating in the physical world and the grounding layer for world models to make spatial data precise and useful to AI.
Why AI needs to be grounded in the real world
Without an accurate grounding layer, world models are guessing at a world they don’t actually know
Spatial data prevents AI hallucinations by providing “ground truth” instead of predictions of what comes next
Precision enables AI behaviors that weren’t previously possible, like choosing safe delivery drop-off locations
Flipping the sim-to-real process leads to faster and more precise deployment at scale
Also available in audio format on the following platforms: Apple Podcasts, Spotify
Inhi Cho Suh
Inhi Cho Suh is CEO of Niantic Spatial, a San Francisco-based physical AI company spun out of Niantic, Inc. that is building real-world models for machines and people. She brings decades of experience scaling enterprise software and AI businesses. Previously, she was President of DocuSign, where she led product, engineering and other core functions as the company grew from $2 billion to $3 billion in revenue and achieved its first full year of profitability. She also served four years on DocuSign’s board. Before DocuSign, Inhi spent 20 years at IBM, leading its $10 billion-plus Global Strategic Partnerships business and serving as General Manager of Watson Customer Engagement and Big Data. She serves on the boards of Otter.ai and AnitaB.org and has delivered a TED Talk on data and healthcare. She holds a law degree from North Carolina Central University School of Law and a degree in Biology and History from Duke University. Outside work, her adventures include trekking to Everest Base Camp and climbing Yosemite’s Half Dome.
Eugene Chong
Eugene Chong is Director of Product Management at Niantic Spatial, where he leads product strategy and the robotics and defense verticals. His current focus is on real-to-sim for embodied AI: reconstructing a robot’s deployment sites as simulation environments accurate enough for policy training and evaluation. He joined Niantic in 2024 to work on its Visual Positioning System product. Before that, he was a Principal Product Manager at SafeGraph, developing location data products for customers in ad-tech, local search, and commercial insurance. He holds a master’s degree in city planning from the University of Pennsylvania and attended the University of Chicago for his undergraduate degree. In his free time, he plays lots of ultimate frisbee.
Get the episode transcript
More episodes
OpenAI Agent Security Lead Fotis Chantzis discusses one of the biggest unsolved problems in AI
Vercel Chief Product Officer Tom Occhino reflects on React and how AI transforms software creation
Cursor Head of Security Travis McPeak considers how to secure agents without slowing work
Braintrust founder and CEO Ankur Goyal examines why AI learning happens after launch
Mercor co-founder and co-CEO Adarsh Hiremath addresses the AI onboarding problem
Temporal co-founder and CTO Maxim Fateev uncovers the distributed systems hiding behind AI agents
Cognition President of New Enterprise Jeff Wang envisions a future where AI agents prove their own work
OpenAI Codex product leader Rohan Varma is redefining what it means to be a developer
