{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/3c633a40ea84442e9853f7c232277dca\" 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/3c633a40ea84442e9853f7c232277dca-c2bc38a8495e5d20.gif","duration":325.141,"title":"Dynamic ICP Scoring using Codex + Clay ","description":"This Loom explains a three-layer dynamic ICP scoring workflow in Clay for an AI connectivity platform. The first layer creates a seed list from Cortex using a deterministic ICP definition to generate 50 structurally fitting companies in batches, avoiding expensive top-50 filtering from larger TAM sourcing lists. The second layer uses Clare to score technographic readiness based on cloud, engineering, and legacy IT signals using a mix of LLM-based scraping, enrichment, synthesis, and composite scoring, with optional pain point detection. The third layer detects active buying and building signals; all three layers are combined with formulaic logic into a composite score out of 100 for downstream ABM rubric assignment."}