Personally, I prefer Apple products to evolve more slowly. The Photos app changes often, and this introduces issues for non–tech-savvy users. AI in every app? Sorry, but UX is already changing daily, and AI tools are evolving just as fast.
I don’t want tools that exist just to push something new. Who would want to spend three months writing a book about AI when, three months later, half the information is outdated?
Rapid development belongs on other platforms. Apple platforms should evolve more slowly, especially during a volatile technological shift like the current AI wave.
Definitely a good point. Things are moving really fast in the AI space right now. It feels like a race to figure out which tools people will actually use day to day (and pay for).
If the Claude app ends up working better as a separate sidekick to Xcode, maybe that’s a win for Apple after all?
In-app chat will probably stay with us and become a UX design pattern. Will it make “Help” in top menus disappear? Or will apps bundle models trained on their own knowledge so they can work offline?
On the other hand: are we going to see a chat in every app, or only in large apps? Will SwiftUI and UIKit eventually give us something like UIChatField / UIChatTextView?
External tools are evolving fast — look at Codex: it started in the terminal and is now a standalone app. We’re in a fast-paced cycle of development.
“If the Claude app ends up working better as a separate sidekick to Xcode, maybe that’s a win for Apple after all?” I like the setup of Codex in the terminal (and now the standalone app) while keeping Xcode for Run, Previews, and Playgrounds. Xcode’s advantage is autocomplete for Apple framework symbols and the Preview system.
If external tools deliver that too, some people may stop using Xcode. So: Codex + Run + Playground + Preview — and we might end up with a new IDE for iOS development. The Navigator tabs (Project, Source Control/Repository, Issues, Build, Tests) already exist in other IDEs and could be built as standalone apps, or integrated into Codex.
About Chat: I already did something similar for one of the projects (in Test mod, of course). Guided Foundation with common commands in app and set instructions to return only valid ones. Maybe Apple will extend MessageKit.
And, yeah, I love the CLI capabilities too. Skills, Agents, usage after all in handy place. While Xcode is for SUI Preview. There is a tools for Preview launch but seems not so convenient. That leaves Xcode as necessary tool for now.
Solid analysis on Xcode's positioning problem. The point about Apple needing to move faster than the yearly WWDC cycle is critical, especially when competetors like Cursor are shipping weekly updates. I've noticed this friction myself when setting up AI tooling for Swift projects. Integration depth matters way more than raw model quality atthis point.
Totally agree. We have tools to choose with setup and integration on different levels. But even Xcode Intelligence tab is not so UX friendly not mention the connectors/skills features.
Personally, I prefer Apple products to evolve more slowly. The Photos app changes often, and this introduces issues for non–tech-savvy users. AI in every app? Sorry, but UX is already changing daily, and AI tools are evolving just as fast.
I don’t want tools that exist just to push something new. Who would want to spend three months writing a book about AI when, three months later, half the information is outdated?
Rapid development belongs on other platforms. Apple platforms should evolve more slowly, especially during a volatile technological shift like the current AI wave.
Definitely a good point. Things are moving really fast in the AI space right now. It feels like a race to figure out which tools people will actually use day to day (and pay for).
If the Claude app ends up working better as a separate sidekick to Xcode, maybe that’s a win for Apple after all?
In-app chat will probably stay with us and become a UX design pattern. Will it make “Help” in top menus disappear? Or will apps bundle models trained on their own knowledge so they can work offline?
On the other hand: are we going to see a chat in every app, or only in large apps? Will SwiftUI and UIKit eventually give us something like UIChatField / UIChatTextView?
External tools are evolving fast — look at Codex: it started in the terminal and is now a standalone app. We’re in a fast-paced cycle of development.
“If the Claude app ends up working better as a separate sidekick to Xcode, maybe that’s a win for Apple after all?” I like the setup of Codex in the terminal (and now the standalone app) while keeping Xcode for Run, Previews, and Playgrounds. Xcode’s advantage is autocomplete for Apple framework symbols and the Preview system.
If external tools deliver that too, some people may stop using Xcode. So: Codex + Run + Playground + Preview — and we might end up with a new IDE for iOS development. The Navigator tabs (Project, Source Control/Repository, Issues, Build, Tests) already exist in other IDEs and could be built as standalone apps, or integrated into Codex.
About Chat: I already did something similar for one of the projects (in Test mod, of course). Guided Foundation with common commands in app and set instructions to return only valid ones. Maybe Apple will extend MessageKit.
And, yeah, I love the CLI capabilities too. Skills, Agents, usage after all in handy place. While Xcode is for SUI Preview. There is a tools for Preview launch but seems not so convenient. That leaves Xcode as necessary tool for now.
Solid analysis on Xcode's positioning problem. The point about Apple needing to move faster than the yearly WWDC cycle is critical, especially when competetors like Cursor are shipping weekly updates. I've noticed this friction myself when setting up AI tooling for Swift projects. Integration depth matters way more than raw model quality atthis point.
Totally agree. We have tools to choose with setup and integration on different levels. But even Xcode Intelligence tab is not so UX friendly not mention the connectors/skills features.