What problem does it solve? Managing Frontline AI agents through a web UI is slow for repetitive tasks like creating flows, editing graph nodes, testing agents, and reviewing conversation transcripts. This Skill lets you perform all of those operations directly from the terminal using the Frontline CLI. ## Core Features & Use Cases - Agent Lifecycle Management: Create, update, deploy, and soft-delete agents, and manage agent settings, themes, channels, variables, and intents with JSON payloads validated by the API. - Flow Graph Editing: Build and inspect flow graphs node by node, with support for node types like START, SAY_AI, RESPONSE_AI, TOOLS_AI, API, and CONDITIONAL_ROUTING, plus edge validation rules. - Testing and Observability: Run an agent end-to-end over the OVERVIEW channel, list and search conversations, read clean or debug transcripts, trace individual messages, and pull analytics by date range. - Use Case: You need to test a new support agent before launch. Create the agent, build a flow with a START and SAY_AI node, run a test conversation with frontline agents run, then review the transcript and trace any unexpected replies. ## Quick Start Ask the AI to list all active Frontline agents as a table and then run a test message against one of them.
