Skip to main content
  1. Home
  2. Computing
  3. Features

Claude redefined my bond with Macs. I am building my own apps and it’s a bliss.

I talk to Claude. It builds me apps. It's as simple as that!

Add as a preferred source on Google
iOptimize with Nadeem Sarwar Claude AI on Mac.
Nadeem Sarwar / Digital Trends
Electronics, Phone, Mobile Phone
This story is part of iOptimize, a recurring Digital Trends series
Updated less than 2 hours ago

A few days ago, one of my colleagues asked me a favor. They wanted a few iOS and macOS screenshots turned into a mockup image where the UI is rendered on an iPhone and a MacBook. The problem? It was 3 am PST, which meant asking one of my design team colleagues was out of the question. 

Now, there are plenty of online tools that will do it, but you either have to pay for a subscription (as in Canva), or sign up to buy usage credits after a few free trials. Moreover, these editors limit you to a handful of design presets. I turned to Anthropic’s Claude, and within half an hour, I had a screenshot-to-mockup editor built for the entire team to use. Take a look:

I named it Framely, of course. It runs in a browser tab and doesn’t need an internet connection. Nothing is ever uploaded to a cloud server, so I don’t have to worry about privacy, either. Framely generates unique backgrounds and works like a charm. All I need to do is drag a screenshot, pick the device, and export it as a JPEG. 

Recommended Videos

I never saw the code, and the whole editing software comes in at just 8MB in size. Even when it came to fixing bugs or iterations, I merely narrated the changes and Claude did it all in the background. I even had the whole editing tool feel native to macOS by using Apple’s Liquid Glass design language, complete with a dark/light mode toggle to go with it. 

Building is addictive

This won’t be the first web tool or app that I’ve created using Claude. So far, I’ve made Chrome extensions, a Mac app that replaced Grammarly for me, an AirPods motion-sensing utility to monitor my posture, and more. I have a few more ideas that are currently in the build phase, and I can’t wait to share them.

Now, I won’t call myself a builder. I don’t know how to code, nor do I know the nitty-gritty of UI design. All I know is what I want to build, and using nothing but voice commands, I have Claude build these tools and utilities for me. 

This is a transformational phase for how we interact with computers.

I am talking more, and typing less. And there are multiple arguments that I can make to convince you to get into this new mode of using computers and building your own software. First, when you build an app for personal use, you have full control over the features you want, and most importantly, skip the jargon you want to avoid. No redundant features. You have full control over the UX design, too.

I’ll give you another example. I recently built a fully offline Grammarly editor and designed it as a menu bar utility. The idea is a mix of Antinote, one of my favorite apps, and Grammarly. I simply gave the design guidelines to Claude, while it suggested using the Harper engine for grammar and spell checks. In doing so, I not only avoided paying for yet another app, but also won full control over my writing and data. 

When I build an app for myself, I have full control over the privacy aspect. There are no data harvesting worries I have to live with. I no longer have to think about hidden trackers or activity loggers. It’s no secret that in the modern age, free software almost always comes with a privacy compromise. Or, as the tech adage goes, if it’s free, you’re probably the product.

Another massive perk is that you don’t have to wait for updates to fix bugs or add new features. It’s a cakewalk, actually, if you’re using a tool like Claude. The code lives on your device. All it takes is a voice command (or text instruction in natural language) for Claude to jump into action, make the necessary changes (read: upgrades), while showing you the changes in real-time. 

So many reasons to build for oneself

Earlier today, in merely two hours, I built myself a minimalist word processor with all the core features I need for my newsroom duties, while skipping all the useless tools I never bother to click. The original idea was an utterly minimalist UI, and the whole prototype ran in a browser tab with less than 200MB memory intake on a machine with an ageing Intel Core i3 processor. The file size of the package came in at less than 20MB, which is ridiculous. 

After a bit of dogfooding, I asked Claude to jazz up the UI and make it feel native to macOS 27 Golden Gate’s Liquid Glass look, complete with a dark and light mode toggle. The final result had a lovely gradient look, featuring Apple’s signature rounded UI elements. It was as if the word processor was the brainchild of Apple’s in-house designers. 

I did it all without ever seeing a line of code, or writing it. I simply told Claude what I wanted and saw the visual editor reflect the changes in real-time. And I didn’t even use the all-too-mighty Claude Fable 5. Anthropic’s less-power Claude Opus model handled the chore just fine. Imagine building a word processor with all the core features and modern looks, compress to less than 20MB file size? Yeah, that’s what you can do with AI tools such as Claude.

The convenience is so addictive that each night, before I go to sleep, I discuss a product idea with Claude, brainstorm the feasibility, and have it chalk out the detailed plans for building it. All this happens on my phone. The next morning, I open the Claude desktop app on my Mac, simply type “build” in the chat, and the AI delivers a fully functioning app or utility within an hour. 

The time that I would spend in mindless doomscrolling is now spent brainstorming and building. How cool is that, right? I am hooked on this phase, and I am not stopping anytime. What’s next? 

Well, I just turned my iPad into a diary that works just like the one owned by Tom Riddle in the Harry Potter universe. I scribble a question, it vanishes a second later, and then I get my answer appear on the screen, one word at a time, as if the digital diary is talking to me. 

Fun times! 

Nadeem Sarwar
Nadeem is the Managing Editor at Digital Trends.
ASUS Zenbook Duo UX8407AA review: Two screens finally earned their place in my bag
Two machines are definitely better than one, but on the same laptop? Asus nailed it, but you must be willing to pay for the convenience.
ASUS Zenbook Duo has two displays

See at Amazon

Two displays on a laptop once sounded like an elaborate solution waiting for the right problem. ASUS has spent the past few generations steadily proving otherwise. After using the latest Zenbook Duo (2026) UX8407AA for over two weeks, I started arranging my daily routine around that second display. 

Read more
How Claude helped my 65-year-old dad finally ditch his handwritten ledgers
AI has a lot to answer for, but this one small win is hard to argue with, at least for me.
Claude app on iPhone

My dad has owned a small business for as long as I can remember, and for just as long, he's kept his books the old-fashioned way. Every sale gets written down by hand so he can file his taxes later. The problem is that his accountant needs this data in Excel, and my dad, who didn’t grow up around computers, has never learned how to use it.

For years, his workaround was paying someone to manually type his handwritten entries into a spreadsheet. It worked, but it was adding additional cost to his business, which he wanted to avoid, but couldn't.

Read more
AI’s energy tax was already concerning. Research says AI agents are over hundred times worse
AI agents could consume 136 times more energy than today's AI, study finds
AI agents

The AI industry's soaring electricity demand has already become a growing concern for governments, utilities, and technology companies. But a new study suggests the next generation of artificial intelligence could make that problem significantly worse.

Researchers from the Korea Advanced Institute of Science and Technology (KAIST) have published what they describe as the first comprehensive analysis of the energy cost of AI agents - AI systems capable of reasoning, planning, and completing tasks autonomously. Their findings show that these systems can consume up to 136.5 times as much energy per query as conventional generative AI models, raising fresh questions about whether the infrastructure supporting tomorrow's AI is ready for what's coming.

Read more