In this third episode of our four-part series, we build the first of two AI Agents, one that uses cloud resource tags to automatically populate CMDB attributes at scale. Building on the framework established in Episode 2, this episode focuses on two new tools: a custom Now Assist Skill that identifies the most relevant tags for a given CMDB attribute, and a subflow that finds matching CIs and copies the tag value directly to the target attribute. Together with the common tools built in Episode 2, these components are wired into a complete AI Agent that guides the user through the entire enrichment process conversationally. In this episode we cover: - A review of the use case and solution architecture - Building a custom Now Assist Skill to find relevant tags for a selected CMDB attribute - Building a subflow to find CIs with a matching tag and update the specified attribute - Building the AI Agent that orchestrates the process end to end - A live demo of the tag-based enrichment agent in action 0:00 - Introduction 1:00 - Review 4:58 - Tools 7:07 - AI Agent 8:04 - Demo creation of custom Now Assist skill for finding relevant tags 14:30 - Demo creation of subflow for finding tagged CIs and updating an attribute 23:23 - Demo creation of an AI Agent 29:00 - Recap and Preview Supporting blog post with code snippets and additional resources: https://www.servicenow.com/community/cmdb-blog/closing-the-cmdb-data-gap-with-purpose-built-ai-agents/ba-p/3450078