{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"START","title":"START: Andrey Gizdov, CEO & Co-Founder, OpenVector: \"Vision Language Action Systems for the Physical World\"","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/78bca0ee\"></iframe>","width":"100%","height":180,"duration":770,"description":"There are over a billion cameras in the world. They can all see. Almost none of them can tell you what they saw.\nAndrey Gizdov has been in computer vision since 2016, when CNNs were all the rage, researching real-time vision models.\nHe met his co-founder Vishal Urlam at a hackathon. His co-founder had deployed cameras and IoT devices across India's power grid to monitor it.\nThen they went to conferences on cameras and intelligence and found the state of affairs grim.\nFrom that point, they knew this was a company that was going to exist.\nOpenVector connects what cameras see to what businesses do.\nConnect an existing camera and describe a workflow in plain English:\nTrack a misplaced item.\nCheck that an SOP was followed.\nDetect an unscanned item.\nTurn an empty shelf into a restocking task.\nWhen something needs attention, OpenVector can take the next step inside the software a business already uses - creating records, sending requests, updating tasks, or notifying someone to act.\nVision → Language → Action.\nDoing that without replacing the existing camera infrastructure is the hard part.\nHistorically, bandwidth and compute pushed vision systems onto on-prem hardware. And ripping out a customer's existing setup doesn't scale.\nAndrey says OpenVector has significantly reduced those requirements with almost no loss in accuracy. Today, the company describes its underlying technology as the world's fastest and lowest-bandwidth VLM engine.\nDuring YC, they sold to major companies, including some of the biggest gas-station operators in the country.\nThe larger bet is that AI is moving out of the chat window and into the physical world.\nOpenVector is building the layer between what a camera sees and what a business does next.\n🎙️Andrey Gizdov, CEO & Co-Founder, OpenVector on Fondo START\n01:39 Harvard and the path into computer vision\n02:42 Vision, language, action systems\n\n03:08 Typed commands into camera workflows\n\n03:17 Warehouse and subway use cases\n\n05:15 Why build it now\n...","thumbnail_url":"https://img.transistorcdn.com/q-E1hh7K6IS4AfZiNy2p4MYVGcUOO8lQP92h8QbOEOA/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS80NzVj/MDEzNjkxNjU1N2Uy/NDFhMDQ3M2ZhNWI3/NWY0MS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}