Operations | Monitoring | ITSM | DevOps | Cloud

We Benchmarked AI Models on Git Tasks. Results Surprised Us

Most AI model benchmarks measure general coding ability or reasoning. GitBench, built by GitKraken developer advocate Chris Griffing, measures something narrower and more practical: how well a given AI model handles specific Git tasks, starting with commit squashing, identifying which commits in a messy history should be combined into one clean commit.

AI Spend Is a Capacity Problem, Not a Billing Problem

Every organisation running models in production eventually reaches the same point: the AI portion of the cloud bill grows faster than expected, and the immediate response is to invest in visibility. Calls are tagged, spending is attributed, dashboards are created, and the results are shown to the teams responsible.

Best AI Humanizer Tools for Ops and IT Teams Writing Technical Documentation in 2026

You finish the postmortem at 11pm, push it to the knowledge base, and the next morning it comes back flagged. Not for a factual error - the reviewer's note says it reads like AI. So now you're rewriting a document that was already correct. Most ops teams have hit some version of this. DevOps engineers, SREs, and IT ops managers draft runbooks, release notes, API documentation, and incident comms with Copilot, ChatGPT, or Gemini in the loop, because the alternative is writing them from scratch at 2am. The drafting problem is solved. The publishing problem isn't.

MCP Servers 1.1.0 Add Flexible HTTP Routing and CLI Connection Management

We are pleased to announce the release of MCP Servers 1.1.0, bringing new configuration options for HTTP-based deployments and expanded command-line capabilities for managing database connections. The new version makes it easier to control how MCP Servers are exposed over HTTP, host multiple MCP Servers under a single hostname, and configure connections directly from the command line.

Can You Prove Your AI Agents Are Paying Off? Most Developers Can't

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.

The Evolution of JFrog AI Catalog: Your AI Control Plane for Agentic Development

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.

Our Customer Success AI bill tripled. Here's why we're spending more.

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.

Shipped: Rightsize Kubernetes workloads without leaving your MCP client

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.

LLM token cost: pricing per token explained

LLM token cost is the price a provider charges per token a model reads or writes, quoted in dollars per million tokens. Input and output bill at separate rates, with output priced at roughly 5x input. As of September 2026, published rates range from under $0.10 to more than $180 per million tokens on top-end reasoning tiers. In late 2025, Hardik Sonetta of Thomson Reuters Labs published a warning about the most common prompt caching mistake in production.