Operations | Monitoring | ITSM | DevOps | Cloud

Build a multi-agent AI system using CrewAI, Gemini, and CircleCI

Multi-agent AI systems are trending in the software development industry right now. These systems consist of a group of individual agents that collaborate to achieve a desired goal. They mimic real world teams and departments in how they are organized. In multi-agent AI systems, each agent is assigned a task that is required to achieve a final output.

It's Never Different This Time: LLM Reliability Without the Hype with Julien Simon

In this episode, Julien Simon, longtime voice in the open-source ML world, reminds us that even in the era of GenAI, reliability fundamentals haven’t changed. Julien breaks down why calling “the same model” from different providers can produce wildly different results, how deployment choices introduce hidden variability, and why reliability teams need to think of LLM systems as distributed systems.

AI-Suggested Alert Thresholds for Mobile Telemetry

Life is pretty good. I’ve shipped a mobile app and I’m (happily) drowning in telemetry. Battery impact, time in foreground/background per screen, crash rates, slow frames, network retries – the works. The data is brilliant; the challenge is turning signals into reliable alerts that catch real issues which are relevant to my app’s functions. So… what should I actually listen for, and where should I set the thresholds?

AI wrote the code, but can you trust it? #aicoding #integration #cursor #devops #speedscale

Using AI coding tools like Cursor is fast, but it leaves a massive question: Is the new code going to break production? We solve this by combining Cursor with Proxymock! I take a live traffic snapshot of my running app, feed it back to the AI, and instantly run realistic integration tests locally. It's the only way to get true confidence before you push. Watch the full video below!

Technology as a Personal Finance Partner

Technology has evolved into much more than a convenience-it's become a true financial companion. From apps that track spending in real time to platforms that automate savings and investments, digital tools are transforming the way people handle money. For many, these innovations have brought clarity and control to what used to feel like an overwhelming process.

When Bots Grow Brains: RPA and Agentic AI For the Win

For a long time, robotic process automation (RPA) was the fastest way to scale repetitive digital work. Bots copied, clicked, and executed rule-based tasks faster than any human. They reduced error rates and delivered early wins for efficiency. Sounds just fine, right? Prepare for a Matrix moment, because the truth is that IT teams built RPA only for predictability. It could follow instructions, but it couldn’t adapt when something unexpected happened.

Prioritize errors and create tickets using Rollbar's MCP Server

Production errors can feel overwhelming. Your Rollbar dashboard is filling up with alerts, your team is scrambling to understand what needs immediate attention, and critical revenue-impacting issues might be buried among less urgent problems. Sound familiar? In this post, I'll walk you through a workflow that transforms production error chaos into organized, prioritized action items. We'll cover everything from analyzing Rollbar errors to creating properly linked Linear tickets.