Operations | Monitoring | ITSM | DevOps | Cloud

AI agents are undoubtedly exciting. What company would turn down the opportunity to use an intelligent bot that can make decisions, perform complex tasks, and take on the tedious work employees would normally have to deal with? On paper, AI agents sound like tremendous time and money-savers. The reality, however, is a bit different from the fantasy.

We are in mid-2025, and teams across industries are rolling out large language models, or LLMs, to power everything from conversational agents to document understanding. However, getting them to run smoothly in production… That’s still a challenge. A working model isn’t just about putting it in a container and tossing it into a Kubernetes cluster.

If writing SQL code is part of your daily work, you won’t be surprised by things like context-aware code completion, as-you-type syntax validation, and debugging. All of them are designed to enhance and speed up your SQL coding. But what if we said that you could completely reshape your experience with an AI-powered assistant? What if you could have your error-free queries generated, analyzed, and optimized in just a couple of moments?

Twelve months ago, we shipped Edwin AI with a specific hypothesis that AI agents could handle the operational drudgery slowing down ITOps teams. It was a deliberate bet against the cautious consensus that AI should act only as a copilot, limited to offering suggestions. Most AIOps tools still follow that script. They’re stuck surfacing insights and stop short of action. Edwin was built differently. It was designed to make decisions, correlate events, and execute fixes.

When it comes to incident management, the ability to quickly access and act on operational data can mean the difference between brand loyalty and costly downtime. PagerDuty’s integration with the Amazon Q Business index addresses this challenge head-on by providing a seamless, more secure, and faster way to search and access enterprise knowledge across the IT ecosystem.

Imagine incidents resolved through insights, not manual investigations. ‍ Picture an incident management future where you're never alone during critical alerts. Imagine your best engineer always available, tirelessly investigating issues, analyzing logs, correlating metrics, checking recent code changes, and delivering actionable insights, instantly. Today, ilert is stepping boldly into this future with our first intelligent agent: ilert Responder.