Mariano, Staff Product Manager at Vercel, explains why serverless architectures are hitting unexpected limits—they’re too fast. The industry has spent millions optimizing serverless for speed, but AI workloads are changing the game. In the AI realm, slower execution often leads to better results. The challenge? Paying for all that idle compute time while waiting for AI responses.

In this episode, we sit down with Adriana Villela, Principal DevRel at Dynatrace and OpenTelemetry contributor to break down how observability impacts reliability. We dive into what contributes to SRE burnout and how managers can create psychologically safer spaces for responders. Adriana also shares her perspective on AI as an observability-buddy to navigate incidents.

In this episode, we sit down with Sean Goedecke, Staff Software Engineer at GitHub, to discuss where LLMs fit into real-world development. Sean shares how he’s using LLMs how he’s drawing the line for AI-assistance in the codebases he manages—though, as he says, this might all change by next summer. Sean also weighs in on how LLMs could assist SREs during outages—especially when you’re only half-awake at 3 a.m. after a rather inconvinient page.

Humans of Reliability: Keeping systems up and the lights on isn’t just about technology—it’s about the people behind it. In this episode, we’re thrilled to chat with Nuno Tomas, founder of Isdown.app, a vendor outage monitoring tool transforming how teams handle third-party incidents. Nuno shares his journey from software engineer to entrepreneur, the pivotal 4 a.m. moment that inspired Isdown, and the challenges of balancing startup life with family. We dive into the complexities of incident communication, how to tackle alert fatigue, and why transparency is key to building trust in SaaS.

Ashley walks you through how to create a schedule and escalation policy using Rootly On-Call, a modern on-call and incident management solution. rootly.com/on-call.

Shadowing experienced responders is one of the most effective ways for folks who are new to on-call to gain the confidence and knowledge to handle incidents independently. Traditionally, shadow rotations are cumbersome to set up, involving duplicating and editing an existing schedule. For Rootly On-Call users, setting up shadow rotations couldn’t be easier with our new native Shadowing feature. Here are a few highlights.

Post-incident learning made effortless. Rootly automates the retrospective process with customizable templates based on industry best practices.