# Gemini in Android Studio: The ICanHazStream Quest > Master AI-driven Android development with Gemini in Android Studio. Explore in-editor refactoring, Agent Mode, GitHub MCP, Studio Journeys, and the Android CLI. - **Author**: Kartik Arora - **Live Presentation**: https://presentations.kartikarora.me/gemini-in-android-studio/ - **Topics**: AI, Android, Development, Gemini --- ## Slide 1: Gemini in Android Studio The ICanHazStream Quest ### Gemini in Android StudioThe ICanHazStream Quest Kartik Arora Lead Engineer @ GDE Android kartikarora.me --- ## Slide 2: Follow Along ### Follow Along Presentation presentations.kartikarora.me/gemini-in-android-studio Codelab Guide codelabs.kartikarora.me/gemini-in-android-studio --- ## Slide 3: Workshop Overview: 3 Acts ### Workshop Overview: 3 Acts AI tooling in Android Studio has evolved from simple autocompletion into an interactive co-developer across the entire engineering lifecycle. - Act 1: Daily In-Editor AI & Guardrails — AGENTS.md, .aiexclude, in-editor diffs via context menu, Java-to-Kotlin math transforms, and XML-to-Compose. - Act 2: Design to Code & Agent Mode — Wireframe multimodal generation, Transform UI in Previews, GitHub MCP Server, and multi-module self-healing Gradle builds. - Act 3: Quality, Verification & CLI — In-memory test fakes with Turbine, Logcat crash diagnostics, Studio Journeys E2E tests, and the headless Android CLI. --- ## Slide 4: Modern Android Challenges ### Modern Android Challenges Today's Android codebases demand rigorous architectural patterns and rapid modernisation: - Multi-Module Overhead: Coordinating changes across :feature, :core:ui, :core:data, and :core:model. - Legacy Debt: Migrating older Java utility classes and XML layouts to Jetpack Compose Material 3. - Reactive State: Moving from legacy LiveData streams to type-safe Kotlin StateFlow. - Deterministic Testing: Verifying asynchronous UI and data streams without fragile mockito overhead. --- ## Slide 5: Introducing ICanHazStream ### Introducing ICanHazStream ### me.kartikarora.icanhazstream Our companion application is a multi-module streaming availability finder. The starter app is immediately functional and interactive (Explore screen with trending movies, movie detail Where to Watch navigation, and Watchlist). --- ## Slide 6: Modern Tech Stack & Standards ### Modern Tech Stack & Standards Built on the latest Android & Kotlin toolchain: - Android Studio Rabbit 2 (2026.2.2 Canary 3): Studio Labs, Agent Mode & bundled JDK 25. - Kotlin 2.4.20 & Gradle 9.8.1: Type-safe build-logic convention plugins. - Jetpack Compose BOM 2026.09: Material 3 design system with Albert Sans typography. - JetBrains Ktor Client 3.6.0: Clean HTTP networking with kotlinx.serialization. - Testing with Turbine 1.2.1: Streamlined testing of StateFlow with in-memory test fakes. --- ## Slide 7: Act 1: Daily In-Editor AI & Guardrails ### Act 1: Daily In-Editor AI & Guardrails Establishing clear project rules, inline refactorings, and legacy modernisation. --- ## Slide 8: Guardrails Architecture ### Guardrails Architecture Grounding Gemini with explicit architecture rules while safeguarding secrets: - AGENTS.md: Mandates MVVM, Clean Architecture, and reusing pre-built :core:ui components. - .aiexclude: Completely blocks local.properties, keystores, and API credentials from AI context indexing. --- ## Slide 9: Grounding with Brand Theme Skill ### Grounding with Brand Theme Skill Ground Gemini in our pre-built Compose design system so it produces consistent, branded composables instead of raw unstyled components: ``` # Install the brand AI skill into Android Studio project npx skills install https://distribute.kartikarora.me/ai/kartikarora-compose-theme.skill ``` - Teaches Gemini about MovieCard, ProviderBadge, and RatingChip in :core:ui. - Automatically applies Albert Sans & JetBrains Mono design tokens. --- ## Slide 10: In-Editor Prompts & Live Diffs ### In-Editor Prompts & Live Diffs Refactoring LiveData to StateFlow with Gemini in-editor live diffs: - Highlight legacy MutableLiveData streams in TrendingMoviesViewModel.kt. - Right-click in the editor and choose Gemini > Generate Code with Gemini (or Refactor with Gemini). - Review side-by-side diffs before committing changes into your file. ``` // In-editor prompt result: private val _movies = MutableStateFlow>(emptyList()) val movies: StateFlow> = _movies.asStateFlow() ``` --- ## Slide 11: Modernising Legacy Java & XML ### Modernising Legacy Java & XML Modernising movie cards from initial baseline/XML into full Compose MovieProviderCard with :core:ui design tokens: --- ## Slide 12: Act 2: Design to Code & Agent Workflows ### Act 2: Design to Code & Agent Workflows From visual sketches to multi-module architecture with Agent Mode and MCP. --- ## Slide 13: Refining UI from Wireframe Mockup ### Refining UI from Wireframe Mockup Refining and generating the Where to Watch detail screen from wireframe mockup sketches: --- ## Slide 14: Tweaking UI in Compose Previews ### Tweaking UI in Compose Previews Iterate on user interfaces visually without re-running the application: - Open WhereToWatchScreen.kt with @PreviewLightDark. - Click Transform UI with Gemini in the Compose Preview toolbar. - Prompt: “Add a subtle outline around the 4K Ultra HD badge and increase provider spacing to 12dp.” - Changes reflect live in preview rendering instantly. --- ## Slide 15: Connecting Context via GitHub MCP ### Connecting Context via GitHub MCP Model Context Protocol connects Gemini to upstream GitHub repositories: --- ## Slide 16: Scaffolding Features with Agent Mode ### Scaffolding Features with Agent Mode Scaffolding the Watchlist feature across modules (:feature:watchlist, :core:data, navigation graph) with Agent Mode: --- ## Slide 17: Act 3: Quality, Verification & Headless CLI ### Act 3: Quality, Verification & Headless CLI Unit testing with fakes, natural-language E2E journeys, and terminal automation. --- ## Slide 18: Testing with In-Memory Fakes & Turbine ### Testing with In-Memory Fakes & Turbine Test reactive streams deterministically without complex mock frameworks: ``` @Test fun testChangingRegionUpdatesProviders() = runTest { val fakeRepo = FakeMovieRepository() val viewModel = WhereToWatchViewModel(fakeRepo) viewModel.uiState.test { assertThat(awaitItem()).isInstanceOf(UiState.Loading::class.java) fakeRepo.emitProviders(listOf(StreamingProvider("Netflix", Quality.UHD_4K))) val state = awaitItem() as UiState.Success assertThat(state.providers.first().name).isEqualTo("Netflix") } } ``` --- ## Slide 19: Studio Journeys: Plain-English E2E Tests ### Studio Journeys: Plain-English E2E Tests Studio Journeys E2E test verifying live navigation from Explore → Dune: Part Two → Stream tab → Netflix 4K AU$16.99 → Watch: --- ## Slide 20: Headless Automation: Android CLI ### Headless Automation: Android CLI Execute Android Studio symbol indexing, preview renders, and lint fixes directly in terminal: --- ## Slide 21: App Quality Insights & Gemini ### App Quality Insights & Gemini Correlating production Crashlytics and Google Play Vitals with source lines for instant fixes: --- ## Slide 22: Workflow Summary ### Workflow Summary The modern AI-assisted Android development lifecycle: - Ground with Intent: Use AGENTS.md and theme skills so the model adheres to your architecture. - Accelerate In-Editor: Right-click and choose Gemini from the context menu for instant, reviewable diffs and code transformations. - Scaffold in Agent Mode: Let the agent coordinate multi-module changes and self-heal Gradle builds. - Verify Rigorously: Assert state with Turbine, execute Studio Journeys, and automate with the Android CLI. --- ## Slide 23: On-Device AI Options ### On-Device AI Options Bring inference directly to user devices with zero server latency: - Gemini Nano via AICore: System-managed on-device foundation model on Pixel and supported flagship Android devices. - Google Play services ML Kit GenAI Prompt API: Zero-setup on-device text generation with automated model downloading and fallback. - Offline Availability & Privacy: Process sensitive queries, movie summaries, and recommendation rankings entirely on-device. --- ## Slide 24: Dig Deeper & Resources ### Dig Deeper & Resources Keep exploring with these workshop links and documentation: - Codelab: codelabs.kartikarora.me/gemini-in-android-studio - Starter Repo: github.com/kartikarora/icanhazstream - Gemini in Studio Docs: developer.android.com/studio/gemini/overview Codelab codelabs.kartikarora.me Happy building with Gemini in Android Studio! --- ## Slide 25: FIN. ### FIN. Kartik Arora Lead Engineer @ GDE Android kartikarora.me Questions & Discussion ---