Systems | Development | Analytics | API | Testing

We’ve been building an AI agent that can take a production bug, find the root cause in captured traffic, write a fix, and validate it before a human reviews it. We call it Agent Factory. Last week we ran it on ourselves, against a real bug in our own production service. The first thing we did was get the workflow wrong.

This is Part 2 of the AI Software Factory series. In Part 1, we established that the Agile methodology is buckling under the weight of “elastic code.” When AI agents can generate functionality in seconds, two-week sprints and manual task management become organizational bottlenecks. We introduced the concept of the AI Software Factory: a shift from managing human tasks to managing business intent through a “Funnel of Increasing Trust.” But a factory requires infrastructure.

CodePush is a great way to ship over-the-air (OTA) updates, avoid app store approval delays, and roll out changes cautiously. Even though App Center has closed down, there are many options available to get started with CodePush. But some of the default settings can create undesirable behaviors, leaving teams wrongly thinking CodePush causes a bad user experience.

There is a specific kind of dread that comes with finding a critical bug in a production React Native app. The fix is usually straightforward: a broken API call, a logic error, a UI state that did not account for an edge case. You can see exactly what went wrong and exactly how to correct it. The code change might take an hour. What takes days is everything that comes after. App Store review. Google Play review. Waiting. Watching your crash reports climb.