12 posts tagged with "AI"

A friend of mine canceled his Visual Studio Enterprise subscription in January. He had been using it for years, built multiple production .NET systems in it, and genuinely valued the tooling. But he had spent the last six months doing almost all of his coding inside VS Code with GitHub Copilot Agent Mode, and he could not justify the renewal.

Three weeks later, a background service in production started leaking memory. He tried everything in his VS Code setup: logging, diagnostic analyzers, heap dumps through the CLI. Nothing gave him a clear picture. He reinstated his Enterprise license, opened the Performance Profiler with .NET Object Allocation Tracking, identified the leak in twenty minutes, and fixed it in ten. Then he went back to VS Code for everything else.

That story is the honest version of the IDE question in 2026. Not whether full IDEs are dead, and not whether they remain the default. The real question is sharper: for which roles, which tasks, and which codebases do they still provide capabilities that AI-powered editors cannot replicate? And when you look at the full picture, including what comes bundled with a Visual Studio subscription beyond the IDE itself, the analysis is more nuanced than either side of the debate usually admits.

Here is a contradiction I keep running into. Every piece of cognitive science research I have read says the same thing: focus on one task at a time. Multitasking is a myth. Your brain cannot do two demanding things simultaneously without paying a steep performance penalty.

And yet, every day I find myself reviewing a pull request that GitHub Copilot cloud agent opened, while a CI/CD pipeline runs on a second branch triggered by AI-generated code. More parallel workstreams than I ever managed before AI entered my workflow and somehow it feels less chaotic than before.

Something does not add up. Either the science is wrong, or what I am doing is not actually multitasking. I think it is the latter, and the distinction matters for every engineer adapting to agentic workflows.

The Definition Worked. Until a Fourth Participant Showed Up.​

DevOps has always been defined by a simple, powerful equation: People + Process + Tools. That formula captured something essential about how modern software gets built and delivered. It broke down walls between development and operations. It gave organizations a mental model for diagnosing what was wrong when things moved too slowly, failed too often, or created too much friction.

For over a decade, this three-pillar model served the industry well. And it did so because it rested on an assumption that nobody questioned: every participant in the software delivery lifecycle was human.

That assumption no longer holds.

Your Pipeline Was Built for Humans. That's About to Be a Problem.​

Not so long ago, every commit in your repository came from a human. A developer wrote code, pushed a branch, opened a pull request, and a reviewer approved it. Your CI/CD pipeline was designed around that flow: run tests, check lint, scan for vulnerabilities, deploy if green.

That assumption is breaking.

The Journey Most Tutorials Skip​

Most AI tutorials start with "create an Azure resource" and end with "here's your chat completion." They skip the messy middle — the part where a developer goes from "I wonder which model would work for this" to "this is running in production, monitored, secured, and costing what I expected."

That full journey is what this post is about.

The Fragmentation Problem Nobody Talks About​

AI coding agents are no longer experimental. Teams are using GitHub Copilot, Claude Code, Cursor, and other tools to generate code, open pull requests, review changes, and automate multi-step engineering tasks. The results are impressive, but a quieter problem is growing underneath the productivity gains.

Every developer on the team configures their AI agents differently.

When Traditional Metrics Stop Working​

AI-assisted development is no longer an experiment. It is part of everyday engineering work across organizations of all sizes. Tools powered by large language models generate code, propose refactors, write tests, summarize pull requests, and coordinate multi-step engineering tasks.

This creates a fascinating and uncomfortable challenge: productivity is clearly improving, but it is becoming much harder to measure accurately.

How Great Engineers Communicate with AI in the Agentic Era​

AI has changed how we write software. But more importantly, it has changed how we communicate intent.

Early conversations about AI-assisted development focused heavily on prompt engineering. Developers experimented with phrasing tricks, formatting styles, and clever instructions to coax better outputs from language models. Entire communities formed around "the perfect prompt."

That phase was useful, but it was never the destination.

Your Repository Is Now Your Most Important Interface​

The role of the software engineer is evolving rapidly, not because AI can generate code, but because software development itself is becoming a human-agent collaborative system.

In recent years, we moved from AI assisting with snippets, to generating entire functions, to proposing pull requests, and now to agents that navigate repositories, reason about architecture, and execute multi-step development tasks autonomously.

The Collaboration Is Already Happening — The Question Is Whether It's Structured​

If DevOps foundations prepare the system and the evolution of the Software Engineer reframes the role, the next logical question is this:

How do humans and agents actually collaborate in practice?

Not in theory. Not in demos. Not in marketing videos.

But in real repositories, real IDEs, real pull requests, and real production systems.