Operations | Monitoring | ITSM | DevOps | Cloud

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.

— 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.

In the past, success was measured in impressions, clicks, and conversions. And in many boardrooms, it still is, because it's easier to justify ad spend with vanity metrics than to explain what real customer trust looks like. Today, it’s an intimacy economy, and customer loyalty is earned over time and not captured in a moment. Brands are no longer competing for attention but are competing for emotional relevance, consistency, and trust.

Node.js is popular for building scalable applications because its non-blocking architecture can handle many requests at once. But when your app depends on a database, performance hinges on how efficiently queries run behind the scenes. Even a single slow database query can block the Node.js event loop, causing delayed responses, frustrated users, and cascading performance issues. Too often, teams only notice these problems after customers experience lag or timeouts.

HAProxy is the workhorse in front of countless APIs and apps because it’s fast, lean, and flexible. Because it sits on the traffic hot path, it’s also your earliest warning system when something slows down or breaks entirely. This means that monitoring it isn’t optional. You need to see connection queues and retries, per-stage timings, health-check failures, and spikes in error statuses to catch incidents before users do.

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.

Security and compliance teams face a critical challenge: by the time they discover suspicious activity in their development pipeline, it’s often too late to prevent damage. Manual audit log requests create bottlenecks that delay incident response, and gaps in visibility leave organizations vulnerable to insider threats and compliance violations. If your team struggles with any of these issues, you need a systematic approach to real-time audit monitoring.

In complex data pipelines with dozens of jobs and intermediary datasets, it can be difficult to effectively monitor how data travels and changes through various steps. When tracking issues in these pipelines, you need visibility into upstream components where the root cause may originate from, as well as downstream datasets and consumers of data that may be experiencing further impacts.

In cybersecurity, prevention often gets most of the attention. But no matter how strong your defenses are, incidents will happen. And how you respond in that moment of truth defines resilience. That’s why I really connected with a framework Chris Johnson shared with me on the MSSP 1337 podcast, the 3 P’s – plan, practice, prevail.

Modern security operations are drowning in data but starving for intelligence. Organizations process terabytes of raw telemetry daily from a wide variety of sources, including firewalls, endpoints, and cloud services, yet 80-90% lacks the contextual intelligence needed for effective threat detection and response. This torrent of data creates a major challenge for Security Operations Centers (SOCs).