Detect, Communicate, Resolve: Checkly's Agentic Workflow End-to-End

Coding agents are the fastest-growing audience for the Checkly CLI, and we're doubling down on them. In this session, Stefan hands Claude a real e-commerce app, lets it set up monitoring with `npx checkly init`, generate Playwright tests through MCP, and walk an actual alert end-to-end with Rocky AI in the loop.

Rocky AI docs: https://www.checklyhq.com/docs/ai/rocky-ai/
Checkly Agent docs: https://www.checklyhq.com/docs/ai/overview/

00:00 Session Overview

01:11 Meet the Speaker

02:14 Why Agents Matter

03:54 Monitoring as Code

04:54 CLI Workflow Basics

06:05 Demo Setup Tour

07:37 Init with AI Agent

08:34 Skills and CLI Context

10:20 Claude Scaffolds Checks

14:45 Review Generated Monitors

17:49 Generate Playwright Test

21:51 Simulate Incident Breakage

24:34 Deploy and Await Alerts

25:17 Rocky Root Cause

26:50 Login Check Failure

28:23 CLI Investigation

29:12 Claude Triage

33:13 Incident Safeguards

34:46 Deploy and Recover

38:53 Confirmation Protocol

40:41 Agentic Monitoring Recap

41:56 Agent Navigation Checks

43:53 Wrap Up and Q&A

#checkly