You could write a full, shippable app every evening with Xcode's agentic coding features. Two apps a day, even.
ā¦you just know App Review isn't ready for *any of this*. Maybe that's why we've been seeing multi-day waits lately
@stroughtonsmith as someone else in your mentions said, it works reasonably well if you create a plan first of what you want to build, and when you would consider it finished (persisted to a Markdown file or whatever), and go back and forth with the agent, ask it for proposals, challenge its proposals.
then whenever you want to work on this project, you start with "let's work on item X from PLAN.md", and the LLM doesn't have to start from scratch again, and you've given it a more focused chunk of work to do.
you can also add pre-loaded files like AGENTS.md, and CLAUDE.md (to help you do boring admin stuff by just typing "commit and push" (and have it format, lint, cleanup, create commit messages, whatever, and give it some basic knowledge of the project and its architecture up front).
but for quick prototypes, asking for an app certainly is valid :) when you want to turn it into something real though, and want a lower slop ratio, and something roughly approximating how you would do it yourself, a plan helps.
@stroughtonsmith Out of curiosity, how did you ālet it internalize your development styleā? Did you point it at your existing projects and generate an AGENTS.md? Or did you have to manually write some kind of style guide?
Also in the past (lol like three months ago) LLMs seemed to have a lot more trouble with Swift; did you have to handhold it a lot, or does Codex feel like it understands Swift better now? Also, any idea if itās any good at SwiftUI?

Attached: 1 image 2025 was, indeed, the dawn of dropshipping apps, as the prophecy foretold.
@stroughtonsmith once agents remove writing code as a bottleneck, the next bottleneck is PR review/knowledge sharing
We donāt review code syntax, we review the associated spec, the correspond tests (ie āwhat is this supposed to do and how is it proving it is actually done today and tomorrowā) and the overall pattern/shape of the code for consistency with the rest of the app (ie ācan I still find my way around that code?ā)
Because we are still the ones on-call to be woken up at 2am if something is acting wonky and āI dunno, Claude generated thisā is not an acceptable answer
@stroughtonsmith from an Software Engineer point-of-view, this is as if our team just got bigger with way more code outputed faster. However this is basically the same job weāve been already doing, minus the code writing part. Since there is typically more than one engineer per team, this is just a scaling issue.
But for Product Management, especially Product Owner/Business Analyst, where there is usually just one or two per team, this is a scaling they are not prepared to cope with. They become the main bottleneck.