{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/75b470f4f60b4110a4131c6261978037\" frameborder=\"0\" width=\"1662\" height=\"1246\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1246,"width":1662,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1246,"thumbnail_width":1662,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/75b470f4f60b4110a4131c6261978037-0b50d6fc81dc8ada.gif","duration":211.797,"title":"Converting Messy RFQs into Structured Supplier Outputs","description":"This Loom explains Track 2 of a workflow that converts messy RFQ supplier inputs into structured outputs for mental materials. It takes unstructured PDFs or spreadsheets, extracts details like quantities and that items are stainless sheets, and standardizes them into the ASTM format used in supplier catalogs. The AI process loads quickly due to caching and typically takes around 21 seconds for new inputs. It also detects prompt injection attempts in a synthetic PDF and asks clarification questions when the buyer’s required standard must be assumed from context. The system then matches against supply catalog data, determines pricing, and sends an email back to the buyer while using knowledge base, agent traces, and guardrails to flag runs."}