AI can generate a lot of code. It cannot run your database responsibly.
That’s the uncomfortable truth in the current wave of vibe-coded products: frontend velocity has exploded, while backend operational maturity often hasn’t.
The result is a familiar pattern:
- product moves fast,
- schema changes pile up,
- query ...
Release automation gets better the moment you stop asking AI to do the fuzzy part first.
Most iOS release work is painfully deterministic. A build either finished processing or it didn’t. Metadata is either in sync or it isn’t. Your TestFlight groups are either configured correctly or they aren’t. Apple already gives us the shape of that workflow ...
You write a prompt, hit enter, and watch the console light up green. Code pours out. It feels like magic. Then you try to maintain the thing a week later, and you realize your shiny new AI agent just built a leaking bucket.
Marc Brooker ...
You write a prompt, hit enter, and watch the console light up green. Code pours out. It feels like magic. Then you try to maintain the thing a week later, and you realize your shiny new AI agent just built a leaking bucket.
Marc Brooker nailed this dynamic on Software ...
If you build iOS apps with AI, you've probably hit a wall the second you leave your text editor. Writing logic is fast. Getting the agent to manage simulators, configure a local database, and push a build to App Store Connect is a nightmare of brittle shell scripts.
Blitz ...
