Operations | Monitoring | ITSM | DevOps | Cloud

On 28 September, Anthropic published a playbook for designing evals and hillclimbing against them, and shipped two commands that put it to work. In Claude Code, /claude-api build-eval interviews you and builds an eval inside your codebase. /claude-api hillclimb then improves your app against it, one change per round, with a held-out split to catch overfitting. It is a good piece of work, and the results are concrete.

Monitoring used to mean checking that your dashboards looked fine and starting to troubleshoot when something broke. That approach is outdated. Today, the health of your applications directly affects your business. A slow checkout page, a lagging database, or an unresponsive server costs you customers, revenue, and trust. A problem that once took hours to identify and fix is no longer acceptable. This is where AIOps comes in.

Learn how to secure AI agents across development, testing, deployment, and runtime using the OWASP Top 10 for Agentic Applications. A single poisoned web page can be enough to hijack an AI agent. As organizations move from AI assistants that generate responses to autonomous agents that take action, the security risks are changing. An agent can access sensitive data, execute code, modify configurations, and interact with external systems.

AI coding agents lose context once a PR enters the pipeline. See how code context and delivery context work.

Every enterprise board now expects an agentic AI plan. Far fewer operating leaders can say which workflow should carry it first, and why. That debate ran through the closed-door roundtable jointly hosted by iOPEX and Soroco in London, with senior operations and transformation leaders from telecom, banking, retail, financial data, and life sciences.

Table of Contents In Part 1: Agentic AI at Scale – Building the Kubex Agentic AI Platform of this series, we laid the foundation for scaling agentic AI across cloud infrastructure. We examined why traditional ops workflows get stuck in reactive loops of dashboard watching, why static context limits intelligence, and how the Kubex platform uses context engineering and a distributed nervous system to bridge the gap between telemetry and deterministic actions.

Improving an AI agent often involves changing its prompts, models, retrieval methods, or tools. But determining whether those changes actually improve performance can be difficult. A revised prompt might produce better answers for a handful of test cases but perform poorly on unexpected user requests. A cheaper model might reduce token costs while introducing tool-calling errors or longer execution times.

I used to joke that I got my best parenting ideas from management books, and my best management ideas from parenting books. Now, I'm extending it to agents. Hear me out. When you're teaching a teen how to drive, you don't hand them the car keys on day one. You start in an empty parking lot. You ride along and ask them to talk through what they're doing.