{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/56fef990952b4b4f9daf51baea2a6190\" frameborder=\"0\" width=\"1280\" height=\"960\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":960,"width":1280,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":960,"thumbnail_width":1280,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/56fef990952b4b4f9daf51baea2a6190-5fed4bbf4c65f93d.gif","duration":265.809,"title":"Automating Takeoff Layers with AI Prompts","description":"This Loom demonstrates setting up ZZTakeOff layers using an AI assistant connected through an MCP. The author drags and drops “bid takers” into ZZTakeOff in a dev environment, then prompts it to “build everybody’s layer,” including duplicating the first tab layers so hyperlinks come through. They explain MCP as a way for AI to connect to external tools and note the author has already released “MCP for estimators.” The test produces nine layers and attempts to pull items for “the Tragedy Sculpt” and “carried a data center,” but the automation falls back to manual, slow execution, and the author calls it a disappointment despite being able to create 33 of them."}