{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/bce95e66815949eaa2106eed7cf8313d\" frameborder=\"0\" width=\"1920\" height=\"1440\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1440,"width":1920,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1440,"thumbnail_width":1920,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/bce95e66815949eaa2106eed7cf8313d-bb4a2db47aa839c0.gif","duration":308.888,"title":"ICP scoring in Clay (deterministic tier)","description":"A walkthrough of an ICP scoring system built in Clay, used to score a list of companies against an ideal customer profile so reps don't waste time on poor-fit accounts. It imports 25 real Y Combinator companies from a CSV, then uses Claygent, Clay's AI research agent, to visit each company's site and pull one sentence on what they actually do. An AI column scores every company from 0 to 100 with a rationale grounded only in that gathered information, and a fixed formula sets the A/B/C tier (80 and up is an A). Sorted by fit, the A-tier accounts form a filtered outbound view, and the score, tier, and rationale write straight into HubSpot as CRM-ready company records."}