Programme Launch Offer: Save 20% - Book Now

Tutorial A

One Agent to Watch Them All: Building an AI Test Monitor

Paula Bassagañas

09:00 - 12:30 CEST, Monday 15th June

Are you tired of keeping one eye on your CI/CD pipelines — checking builds, digging into logs, and chasing down failing commits? Talking to AI about it won’t help much: testers need actions, not just words.

In this hands-on tutorial, you’ll learn how to build your own AI test monitor using Model Context Protocols (MCPs). MCPs act like a modern USB port for AI: they turn your existing APIs into contracts that AI can actually use. With them, you’ll create an agent that:

  • Watches CI/CD executions in real time
  • Reads build outcomes, failing commits, and test metadata
  • Analyses results to surface root causes and impacted areas
  • Sends a structured email or notification with logs and evidence

 

By the end of the session, you’ll have a working MCP-powered agentic AI that doesn’t just chat — it acts. You’ll walk away with a repeatable blueprint to extend this approach to your own pipelines, tools, and reporting needs, turning AI into a teammate in your software delivery process.