Android × AI
Android AI
We track 39 Android AI case studies from 22 engineering teams. Google, Meta and Callstack write about it most. Many posts also cover Testing and Android Studio. The posts run from 2017 to 2026. The newest is from September 2026.
Android AI articles 1–30 of 39
Why Expo is a great fit for new and existing React Native apps
Keith Kurak from Expo makes a bold claim: AI coding agents don't eliminate the need for cross-platform frameworks. They actually make the case stronger.
How AI Learned to Investigate Mobile Build Failures Like an Experienced Support Engineer
Archana Indran's team at Salesforce turned years of mobile debugging expertise into AI that investigates build failures like a senior engineer. Eight people now support 60+ repositories with less firefighting.
How Dart and Flutter are thinking about AI in 2026
Mariam Hasnany from Google's Flutter team just dropped their AI strategy, and the numbers reveal a massive shift: 79% of Flutter developers already use AI assistants. But there's a trust problem.
Making AI Write Android Code Our Way: A Practical Guide to Agent Skills
Pierrick CAEN from Medium's Android team reveals how they turned AI coding assistants from generic code generators into team-specific experts. The secret? Teaching the AI their exact conventions through structu...
Enabling R8 optimization at scale with AI-assisted debugging
Grab's Android team cracked a 6-year problem that stumped multiple attempts: enabling R8 optimization across 9 million lines of code. One engineer led the charge, and AI was the secret weapon.
Patch Me If You Can: AI Codemods for Secure-by-Default Android Apps
Pascal Hartig explores how Meta's Product Security team uses AI to automatically patch security vulnerabilities across millions of lines of Android code. The challenge? Doing this at scale without disrupting th...
Elevating AI-assisted Android development and improving LLMs with Android Bench
Matthew McCullough from Android just dropped something the AI coding world needed: a public leaderboard showing which LLMs actually understand Android development. No more guessing which AI assistant knows Jetp...
Supercharge your Android development with 6 expert tips for Gemini in Android Studio
Trevor Johns from Google just dropped 6 expert tips for using Gemini AI in Android Studio, and they're a game-changer for how we build apps. These aren't basic prompting tricks—this is how Google engineers and ...
Vision-Based Mobile App Testing CLI for Claude Code
Revyl introduces a CLI tool that gives Claude Code vision-based mobile app testing capabilities. The tool interacts with apps like a human — no scripts, selectors, or element IDs needed — enabling a full write-...
The Intelligent OS: Making AI agents more helpful for Android apps
Matthew McCullough from Android reveals how Google is fundamentally changing app interaction: users won't open apps anymore, they'll just ask AI to handle tasks for them.
Agent Device: AI-Native Mobile Automation for iOS and Android
Callstack just released a CLI tool that finally lets AI agents actually test mobile apps. No more agents that can write code but can't click a button.
Automating Memory Leak Detection with AI
Ricardo Marin from Grindr turned memory leak debugging from a 2-4 hour manual slog into a minutes-long automated process. The secret? Recognizing that memory leaks are pattern-matching problems, not creative on...
Migrating to Jetpack Compose: How AI Accelerated Our Journey at Caper
Instacart's Caper team turned a multi-quarter Fragment-to-Compose migration into a dramatically faster effort using AI coding assistants.
How Automated Prompt Optimization Unlocks Quality Gains for ML Kit's GenAI Prompt API
Google just solved one of mobile AI's biggest challenges: how do you customize foundation models for your app without breaking device constraints? Their answer might surprise you—it's not fine-tuning.
Supercharging Mobile Development with Permanent Work Trees and Claude
Umair Ali from ZAR Engineering turned weeks of mobile development work into single days by eliminating a hidden productivity killer. The secret? Rethinking how Git worktrees interact with AI coding assistants.
LLM Flexibility and Agent Mode Improvements
Sandhya Mohan and Trevor Johns from Google just dropped a game-changer: Android Studio now lets you use ANY LLM—OpenAI, Claude, or even local models—to power your AI coding assistant.
Profiling MLC-LLM's OpenCL Backend on Android: Performance Insights
Running LLMs on Android devices just got a serious performance deep-dive. Callstack profiled MLC-LLM's OpenCL backend to uncover what actually happens when you run local AI on mobile hardware.
How AI Is Transforming the Adoption of Secure-by-Default Mobile Frameworks
Meta just shared how they're using AI to automatically fix security vulnerabilities across billions of lines of code. The twist? The AI doesn't need to be perfect to be incredibly useful.
Building for Android XR: AI Glasses Development
Matthew McCullough from Google just dropped the toolkit that could make AI glasses actually useful. Developer Preview 3 brings purpose-built libraries for augmented experiences that keep users present in the re...
Android Studio Otter 2 Feature Drop
Sandhya Mohan and Trevor Johns from Google just dropped Android Studio Otter 2, and it's packing Gemini 3 Pro with a 1 million token context window. Your AI coding assistant just got a serious upgrade.
Building AI Agents In Kotlin Part 3: Under Observation
Denis Domanskii from JetBrains tackles a problem every AI agent developer faces: your agent works, but you can't see what it's doing. When debugging takes hours and costs are invisible, you're flying blind.
Scaling Mobile UI Testing with AI
Trendyol scaled from 4,869 to 10,400 UI tests in under a year — while keeping execution under one hour. Here's how AI became their test generation engine.
Gemini Nano with On-Device ML Kit and GenAI APIs
Caren Chang, Joanna Huang, and Chengji Yan from Google reveal how they're making Gemini Nano v3 940 tokens/second fast while keeping quality consistent across devices. The secret? LoRA adapters and rigorous eva...
Accelerating on-device ML on Meta’s apps with ExecuTorch
Meta just shared how they moved billions of daily users to their new on-device ML framework. The performance gains are substantial.
Agentic AI Integration in Android Studio with Gemini
Sandhya Mohan and Jose Alcérreca from Google just dropped Agent Mode for Gemini in Android Studio. This isn't another code completion tool—it's an AI that creates execution plans, makes multi-file changes, and ...
On-Device Generative AI APIs: ML Kit and Gemini Nano
Caren Chang, Chengji Yan, and Taj Darra from Google just made on-device AI dramatically easier for Android developers. Four new ML Kit APIs let you integrate Gemini Nano without any prompt engineering or fine-t...
How we reduced manual regression tests by 70% using AI tools
Duolingo's QA team cut manual regression testing by 70% using AI. Here's how they made it work at scale.
What's New in Gemini in Android
Sandhya Mohan from Google just dropped the biggest Gemini in Android Studio update since launch. If you're still manually writing commit messages and test scenarios, this changes everything.
Gemini Nano Experimental Access Available on Android
Taj Darra just announced that Google is opening Gemini Nano to all Android developers. On-device AI just became accessible for production-ready mobile apps.
Precision in Motion: Deep Learning for Smarter ETA Predictions
DoorDash handles 2 billion orders annually, and every ETA prediction matters. Their old tree-based models couldn't keep up with the complexity.