Operations | Monitoring | ITSM | DevOps | Cloud

Prompts, skills, and the AGENTS.md nobody wants to write (and how Anthropic writes theirs)

You’ve watched Claude Code compact a conversation. The context bar fills, it pauses, a summary appears, and it carries on like nothing happened. You probably assumed a housekeeping script trimmed the transcript in the background. It didn’t. The model compacted itself. When the window fills, Claude Code sends a long, specific prompt telling the model how to summarize its own conversation. Then it does, same model, same turn. The thing managing your context window is just another instruction.

AI cost calculator: estimate your total spend

An AI cost calculator for the whole wallet adds four lanes: seats and subscriptions, API and token usage, cloud AI services, and GPU infrastructure. Average 2026 totals run $25 per employee per month at light adoption, $100 to $150 at active adoption, and $300 or more at AI-heavy companies. Getting to your number takes four lane subtotals and three corrections.

Agent vs Agentless Monitoring and How to Decide What Goes Where

Why does half the infrastructure end up returning no monitoring data? The standard plan is to install collection software on everything, which moves quickly across servers and stops dead at the first device running closed firmware. Storage arrays, firewalls, and switches will never accept an install, and the rollout stalls there. That plan usually gets set once for the whole environment, with a single collection model applied to hardware it was never suited for.

Microsoft Took 8 Months to Fix This Copilot Vulnerability

Microsoft finally patched a critical Copilot vulnerability nearly eight months after researchers first disclosed it — and the way the attack worked raises some unsettling questions about AI memory. The vulnerability chained together multiple flaws that could allow a malicious prompt hidden inside a webpage to be pulled into Copilot simply by asking it to summarize the page. From there, the attack could potentially access connected data from services like Gmail, Google Drive, and Google Calendar and exfiltrate that information using Copilot’s own capabilities. But the most concerning part may have been persistence.

Build incident response workflows with Datadog Bits Chat

See how Bits Chat turns a natural-language request into an automated incident response workflow. In this demo, Bits Chat builds a workflow that investigates a monitor alert, identifies whether a recent deployment caused the issue, rolls it back when appropriate, and sends a summary to Slack.

Building AI Systems That Survive an Audit: Evidence Trails, Traceability and Compliance by Design

A model returns an answer with a confidence score of 0.94. The team ships it. Six months later someone asks why the system produced that specific answer, and nobody can reconstruct it. For years accuracy was the only number that mattered in machine learning. Get the error rate down, ship the model, move on. In regulated domains that is no longer enough. The harder question is whether you can defend a single decision after it has been made. Most systems were never built to answer that, and by the time someone asks, the information needed is already gone.

Driving Impact and AI Adoption as an FDE

Enterprise AI is only useful when it actually runs in production, inside the tools teams already depend on. Getting there is harder than it sounds. Forward Deployed Engineers at Atlassian work directly inside some of the world's largest organizations, building AI-powered agents, connectors, and workflows on Atlassian's platform. They work alongside customers to understand the real constraints, design solutions that hold up at scale, and see them through to deployment.

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.