Operations | Monitoring | ITSM | DevOps | Cloud

AI can accelerate speed to market, but for IT leaders it also raises a harder question: can you prove how an AI-generated change reached production? Chris Yates (SVP, Managing Director of Data & Architecture, Republic Bank) explains how his team builds a full evidence trail for every change, using version-controlled deployment tooling like Redgate Flyway Enterprise, so governance becomes a guardrail rather than a brake on speed.

The same agent that reads a Kubernetes cluster reads a Windows machine. One MCP server, one config entry, and the questions are the ones you already ask.

You get an answer from the agent and no way to check how it got there. The route it took is recorded, and so is the reason it gave for taking it. AURA emits OpenTelemetry spans, and the Docker quickstart wires them straight into Phoenix. Four services come up together: AURA Web Server as the persistent agent harness, LibreChat as a browser interface for chatting with the agent, Phoenix to receive the spans, and MongoDB to store stateful data for LibreChat. The Compose file arrives pre-configured to point AURA at Phoenix and to enable content recording for the local demo.

End-to-end testing should not slow your delivery pipeline down. But for many teams, Playwright test suites still live in disconnected jobs, produce noisy failures, and make it hard to tell whether a failed test is a real regression, a flaky test, or just another false positive. In this walkthrough, Shibam Dhar, DevRel Engineer at Harness, shows how Harness AI Test Automation helps teams run, analyse, and trigger Playwright tests directly from their software delivery workflows.