{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/abdc7793d91243618d9bf5117a799bc6\" frameborder=\"0\" width=\"1728\" height=\"1296\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1296,"width":1728,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1296,"thumbnail_width":1728,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/abdc7793d91243618d9bf5117a799bc6-f61fa7b6f4705514.gif","duration":633.979,"title":"AI Support Decisioning System: LangGraph + Human-in-the-Loop Workflow","description":"Walkthrough of an AI Support Decisioning System for customer support operations.\n\nThe demo shows how the workflow uses LLM-assisted understanding, backend reward signals, deterministic risk and decision rules, LangGraph orchestration, human-in-the-loop review, fallback behavior, observability, and Playwright-based validation.\n\nThe key idea: use AI for language understanding and response drafting, but keep business decisions controlled by evidence and policy."}