Developers find themselves in a world where old maps no longer apply. The rules of software development have fundamentally shifted, and continue shifting at unprecedented speeds.

Drawing from a year of exploration, this talk reveals where AI truly shines - from rapid prototyping to uncovering what we didn't know we didn't know - and hidden dangers that can erode the very trust our software depends on.

Come discover the patterns emerging from this new reality: when to explore freely, when to be careful, and what opens up when the old constraints disappear.

A walkthrough of a real session where two developers and their AI agent teams collaborated on a complex architectural change — going
from a rough spec to 8 PRs, 4,500 lines of code, and a clean task board in a single day.

The talk covers how we used git worktrees as a shared context surface between two developers' Claude Code agents, spawned specialist
subagents (including a Redis expert that caught two critical production bugs during design review), ran parallel implementation
across multiple branches, and coordinated via a dedicated agent that polled for commits and monitored Slack and CI.

The focus is on the collaboration model — not the technical feature itself — and what the human's role becomes when AI agents can
read, write, test, and coordinate autonomously.

AI coding agents feel like magic... right up until they collide with production code.

For teams maintaining legacy systems, these agents often hallucinate APIs, run off on tangents, and shatter trust faster than an unreviewed hotfix at 5pm. Ignoring the past won't save us, because new code becomes old!

We can do better, and we will. In this session we'll go over emerging strategies for improving the accuracy of coding agents on real codebases, benchmarks such as SWE-bench that evaluate our progress, and their limitations. Expect to walk away with actionable techniques and a renewed respect for code that came before us and the challenges ahead.

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.