Operations | Monitoring | ITSM | DevOps | Cloud

AI finds vulnerabilities faster than you can fix them

If an AI model can find a vulnerability for an attacker, the same model should help a defender fix it. In practice, the math doesn't favor the defender. This quick video digs into the real asymmetry AI-powered vulnerability discovery creates: The goal is models acting as tools for defenders, not weapons for attackers. Getting there means rethinking how much ground your team can realistically cover on its own.

MCP Won't Replace Your Monitoring Tool

MCP is generating a lot of hype nowadays (but then again, almost anything that emerges in AI seems to attract hype). The anticipation around it is similar to the level of excitement that would break out if Apple were to finally introduce USB-C to iPhones. To be fair, though, some of that hype is warranted, considering the fact that MCP provides a standardized approach to connecting agents with third-party tools, which significantly simplifies this type of integration (hence the USB-C analogy).

How task containers give AI agents real infrastructure without idle cost

Infrastructure for AI agents usually forces a choice between two bad options. A sandbox is safe but blind, cut off from the data and services that would make the agent's output useful. Full access means paying to keep a container idle between runs, waiting on a prompt that might not arrive for hours. Task containers, which Upsun released on August 12, 2026, are built to avoid that choice. A task container is a single-purpose container defined in a project's.upsun/config.yaml file.

Why AURA Scratchpad Is Rad: Bound the AI SRE Agent Context Window

A big tool result does not have to be a big context cost. AURA moves it to disk and hands the model a pointer plus the tools to navigate what is there. A large MCP tool result can consume or overflow an agent's context window, and on a third-party server you do not control how much comes back. Scratchpad breaks the link between how big a tool result is and how much context it costs: the full output goes to disk, and only the slice the model asks for ever enters the window. Errors always pass through inline, so the model can react to them.

Building AI SRE Agents, Part 2: Leave the Laptop, Earn Trust

Moving the agent off your machine and pointing it at real clusters — read-only, in shadow mode — then climbing a trust ladder toward carefully scoped action. This is the second article in a three-part series on taking an AI SRE agent from a weekend experiment to enterprise production. Part 1 built a local agent on a throwaway cluster: read-only, propose-only, refined against a small eval set, with portable skills and no production write access.

AI Norms & Values, Part 1 of 3: How We Do Business at Honeycomb

It's been almost exactly one year since we issued our AI mandate here at Honeycomb, and we've been doing some reflection. When we issued our mandate, it's not like we hadn't been using AI. We were the first in the industry to bake a feature powered by AI into our product, way back in May of 2024. Many of us had been experimenting and using these tools in our spare time. But we believe that software is the killer app for AI.

MCP vs API: How they work together and when to use each

Summary: An API defines how software interacts with a service. MCP defines a standard way for AI applications to discover and invoke tools exposed by a service. They usually work together: an MCP server can sit in front of APIs you already run, turning low-level operations into capabilities an agent can find and use at runtime. Your API may already expose everything an AI agent needs. The harder problem is helping the agent figure out which operations matter for the task it has been given.

Don't Break the Agent: Lessons in Token Optimization

This one is for the curious souls who wonder how somebody actually builds a harness optimizer — and, more to the point, how they know it works. When we launched JFrog Boost into public preview, we told the story of the bill that broke us and the 100 billion tokens we clawed back across JFrog R&D. What that post didn’t cover is the question that consumed most of our engineering time: how do you measure any of this?

You Aren't As Behind As You Think

If you look at the people posting to social media the most about AI, you’ll probably feel left behind. They’re running dozens or hundreds of agents and probably shipping more than you. But, they are not representative of the rest of the dev world. They are the 1% of the 1%. The thing that might be missed is that you reading their posts is probably separating you from a much larger cohort of devs that are still trying to figure out how to use AI effectively in their day to day work.

Reliability Engineering in the AI Era

Engineering leaders have been claiming to “shift quality left” for years but production remains stubbornly stuck out of reach of software engineers. The realm of production remains mysterious with tools no one has access to and UIs that wouldn’t make sense to engineers anyway. I’ve noticed a small but growing trend of large enterprises hiring Reliability Engineers instead of Site Reliability Engineers. Dropping one word looks cosmetic but I think it points to a much bigger change.