Operations | Monitoring | ITSM | DevOps | Cloud

AI agents are part of the modern development workflow. They write code, review pull requests, generate tests, call tools, interact with MCP servers, and help developers move faster. But behind every useful agent, there is something just as important as the model itself: the context that tells the agent how to behave. That context can include skills, prompts, instructions, hooks, commands, scripts, references, and MCP server definitions. In a small project, managing these primitives is pretty simple.

AI cost observability is the practice of measuring, attributing, and analyzing AI workload costs at the request, model, and workflow level in real time. It connects cloud infrastructure spend, inference and token costs, and business attribution (cost per feature, team, customer, or product) so engineering, finance, and product teams can see where AI spend goes and whether it creates value. On July 14, IBM had its worst trading day since 1987.

Two-dimensional group-by improvements in Explorer.

AI cost observability is the practice of measuring, attributing, and analyzing AI workload costs at the request, model, and workflow level in real time. It connects cloud infrastructure spend, inference and token costs, and business attribution (cost per feature, team, customer, or product) so engineering, finance, and product teams can see where AI spend goes and whether it creates value.

This is the third post in our DRIVE Deep Dive series. We've covered Delivery and Reliability so far; this post takes on Initiatives. For the complete model, download the full DRIVE framework.

As Staff Engineers and Principal Architects, most of us have spent years thinking about long-term system health. We are considerate of the company’s business objectives and strategy, accumulation of technical debt, and operational risk. For us it is not about whether code works today, but whether the engineer who inherits it in three years will be able to understand what it was trying to do and why. That's what makes a codebase maintainable rather than just functional.

Cloud resilience often feels like an uphill battle. When you’re overseeing hundreds of applications across different providers, identifying potential failure points manually is nearly impossible. You’re left trying to find the needle in a haystack—a needle that could take down your entire application at any moment. To truly protect your uptime, you have to break the cycle of reactive troubleshooting.