SShortSingh.
Back to feed

Building an AI Keyboard for iOS: What They Don't Tell You About Keyboard Extensions

0
·3 views

Building an AI Keyboard for iOS: What They Don't Tell You About Keyboard Extensions TL;DR: I built SmartReply — an iOS system keyboard that reads messages (from clipboard or screenshot OCR), sends them to an AI backend (DeepSeek), and drops 5 reply candidates right into your chat app. The hardest parts aren't the AI calls. They're the iOS sandbox, the process isolation, and StoreKit 2 inside an extension. Here's what I learned. AI keyboards aren't new.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingDEV Community ·

What Open Source Has Taught Me So Far

What Open Source Has Taught Me So Far I started contributing to open source because I wanted to learn how real projects are built outside of tutorials. Over time, I got comfortable working with technologies like React, Node.js, TypeScript, MongoDB, Next.js, and REST APIs. But the biggest learning didn't come from the technologies themselves. It came from reading someone else's code, understanding an existing codebase, opening issues, reviewing pull requests, fixing bugs, and learning how to communicate with other developers. Being involved in open source has also taught me that you don't need

0
ProgrammingDEV Community ·

Core Web Vitals: What Cloudflare's BEACON Data Says to Fix First

I have a bad habit with performance work. I open Lighthouse, see a red number, and start fixing whatever the report lists first. Usually that's an image that's 40KB too big. It feels productive, and it moves the score, and half the time it has nothing to do with what my client's users actually wait for. So when Cloudflare released a dataset of real-user measurements from about 10,000 of the biggest sites on its network, I read the BEACON announcement with a specific question: if I had one afternoon to improve Core Web Vitals on a normal client site, where should it go?

0
ProgrammingDEV Community ·

Keeping large chart previews and CSV exports consistent

A user loads a year of minute candles, zooms out to see the whole period, then downloads a CSV. The file should retain the selected resolution even if the chart has to combine candles to draw that view. That requirement connects several parts of a browser export tool: the dataset, viewport, pagination loop, Cancel button and file writer. Each can make a different decision about how much data it needs. Those decisions should remain visible to the user.