Operations | Monitoring | ITSM | DevOps | Cloud

Monitoring equipment isn’t enough for today’s smart buildings; true value comes from being able to predict issues, optimize performance, and take action automatically. Traditional building management systems often fall short, limited to dashboards and alarms that only notify you of an issue after the fact. With the rise of open source hardware, modern databases, and AI-driven diagnostics, facilities can now move from reactive to proactive management.

— Jensen Huang, NVIDIA GTC 2025 Enterprise AI strategies have rapidly evolved, with substantial investments in Generative AI technologies delivering significant but limited business value. While Generative AI excels at content creation and information synthesis, its fundamentally reactive nature constrains its ability to drive autonomous business outcomes.

Today, we announced that PagerDuty is now officially part of the Glean MCP Directory! This partnership brings together two leaders in AI-powered productivity and operations, making it easier than ever for organizations to connect PagerDuty’s incident data directly to any AI tool or agent in their stack through the standardized Model Context Protocol (MCP). PagerDuty is the first (and currently only) incident management partner that is available via Glean’s AI ecosystem.

As a developer, you often face the challenge of retrieving information from multiple sources with different structures. What if you could create a single interface that automatically routes queries to the right data source? Imagine your application needing to answer both “What’s the population of California?” and “What are popular attractions in Hawaii?”.

The race on AI is heating up; the next generation of vibe coders and prompt engineers are entering the job market as we speak, and AI is the hottest line item on most IT budgets this year. Building the next great home automation software or adaptive learning platform with cutting-edge machine learning is great and all, but like all great software, it needs to start with the plumbing.

A few days ago I hosted a live conversation with Pranav, co-founder of Chatwoot, about issues his team was running into with LLM observability. The short version: building, debugging, and improving AI agents in production gets messy fast. There's multiple competing standards for default libraries for LLM observability. And many such libraries like OpenInference which claim to be based on OpenTelemetry don't strictly adhere to it's conventions.