Operations | Monitoring | ITSM | DevOps | Cloud

Guardrails for shipping with AI agents, feat. Luca Rossi of Refactoring.fm

Code review has always been a time sink. AI just makes the dysfunction undeniable. Luca Rossi, founder of Refactoring.fm and builder of the open source tool Tolaria, has been running one of engineering's most-read newsletters for five years, with over 170,000 subscribers. He's also been doing what a lot of engineering leaders talk about but rarely do: building a real product with AI agents to pressure-test what's actually possible today.

Catch AI Agent Failures Before They Ship | Harness AI Evals

AI agent quality should not depend on manual checks. But for many teams shipping AI in production, agent failures are silent. The agent doesn't crash - it just gives confidently wrong answers, and your monitoring sees nothing wrong. Without automated guardrails, plausible-sounding wrong responses, hallucinations, and quality regressions reach customers before anyone notices.

Power BI vs. SquaredUp: Which is right for IT teams?

At first glance, Power BI and SquaredUp both look like dashboarding tools. In practice, they solve different problems. SquaredUp serves engineering teams and IT teams, including SREs, DevOps engineers, engineering managers, and technology leaders. It connects to monitoring, cloud, DevOps, and ITSM platforms. This gives teams a real-time insights into service health, performance, and key metrics in one place. Power BI is Microsoft's business intelligence platform, designed for analysts and business teams.

Why workflows, not agents, are the primitive your team is missing - Product Highlights

AI helped your engineers ship more code. It didn't help your team ship more product. So where did the bottleneck actually go? In this Product Highlights conversation, Patrick—a principal engineer at Upsun with twelve years building back-end APIs in Go—breaks down what changed once AI agents entered the workflow. His take: "The code isn't really a problem anymore. We can write that really fast. Everything else is still a bit behind the code." We get into.

Why Model Routing Backfires and How to Build Agents That Don't Burn Your Budget

Model routing promises to cut your AI agent spend by offloading routine tasks to cheaper models like Claude Haiku while reserving frontier models like Claude Sonnet for complex reasoning. In the right configuration, routing strategies can reduce inference costs by 40–85%. But if you implement routing incorrectly in a multi-turn agent, you can end up paying more than if you’d never routed at all. Here’s why and how to fix it.

Send DNS Spy Alerts to Your SIEM: Introducing Webhook Alerts

Enterprise teams can now add a Webhook alert channel that POSTs every DNS Spy alert — DNS record changes, domain outages, security check failures, WHOIS updates, phishing look-alike detections — to any HTTPS endpoint as structured JSON. Requests are optionally HMAC-signed, every delivery is logged and retried, and a Send Test button verifies your integration end to end.

Don't Trust the Diff: Making AI-Generated Code Reviewable And Maintainable

Coding agents changed implementation economics faster than they changed confidence. They let us produce more code, more quickly, but they did not make reviewers any better at understanding system-wide consequences. In our Kubernetes automation stack, that gap became impossible to ignore once AI started generating meaningful amounts of controller code.