Dependencies in the AI era, or: how I stopped worrying and learned to love an empty node_modules

They hired me to add features. The codebase had less than 1% test coverage. Azure was retiring .NET 8, but upgrading seemed too hard, so they'd waited years. The kind of problems you know you should fix but never do.

Four weeks later: 560 commits, 65% test coverage, 13 database improvements, and yes, we shipped features too. Two programmers, four hours a day, one $17/month Claude subscription.

Here's what nobody tells you about AI: Day one, it took us eight hours to fix one nullable reference. Week four, I did fifty in under an hour with five minutes of my time. We didn't get faster because AI got smarter. We got faster because we built the infrastructure—scripts, CLIs, knowledge docs—that let AI scale what we'd already figured out.

This is a field report on what's actually possible when you stop thinking "AI makes me faster" and start thinking "AI lets me solve problems that used to be too expensive to touch."

Come see how we got a codebase under control.

Seven months ago, our engineers said letting an AI approve pull requests was too risky. They were right, so we didn’t start there.

Instead, we built a bot for code reviews and capped it at 200-line PRs, watched every decision, and turned every mistake it made into a rule or a lint check. Then we raised the limit.

This talk covers that loop: small experiments, proof instead of promises, and a system that gets a little better every week.

You’ll leave with a playbook you can start on Monday, whatever tools your company gives you.

Graphs are everywhere: in our interfaces, databases, editors, queries and more. Let's look at a few and see what stories they tell us.