Operations | Monitoring | ITSM | DevOps | Cloud

Changing a Kubernetes resource request takes two numbers: what the workload requests, and what it uses. The CloudZero MCP server now returns both, by cluster, namespace, or workload. This gives you a number you can defend. Usage comes back as P95 over the date range you query, 30 days by default. When an engineering lead asks whether a service runs on a smaller request, that is the figure that settles it. Over-provisioning and under-provisioning show up on the same query.

Pop quiz: If you spend $40,000 per month on Anthropic, and you’ve got two customers, what’s your cost per customer? If you bypassed the easy answer of $20,000 and said, “Scott, you old trickster, that’s not enough information to answer that question,” you’ve won today’s prize: a lesson in the perils of average costs. Let’s flesh out the situation: You put an AI feature in your product, a document assistant powered by Claude.

In a single morning, a coding agent can pull an open-source model, connect to an unvetted MCP server, and execute a code-optimizing skill from the web. In the rush toward agentic automation, these AI assets quietly bypass traditional security reviews, creating new attack vectors across the software supply chain. Closing this blind spot has been the driving force behind the JFrog AI Catalog since its launch at swampUP 2025.

It's been one year since we issued an AI mandate inside Honeycomb, and we've been doing a lot of reflecting internally on how far we've come and how far we have yet to go.

We put a blunt question to developers on a recent live webinar: right now, could you actually prove AI agents are paying off for you or your team? Only 24% said yes. The other 76% were guessing, unsure, or already suspicious that agents are costing more than they’re saving. That gap between adoption and proof is the real story in agentic development right now. Teams aren’t behind on running agents. They’re behind on knowing whether it’s working.