--- title: Android Studio Panda: planning mode, next edit... description: Android Studio Panda (stable as Panda 4) introduces several AI-powered features: Planning Mode lets you review and refine an agent's step-by-step plan before... canonical: https://daily.dev/posts/android-studio-panda-planning-mode-next-edit-prediction-and-other-ai-features-8j9lfjwl3 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Android Studio Panda: planning mode, next edit prediction, and other AI features | daily.dev og:description: Android Studio Panda (stable as Panda 4) introduces several AI-powered features: Planning Mode lets you review and refine an agent's step-by-step plan before... og:url: https://daily.dev/posts/android-studio-panda-planning-mode-next-edit-prediction-and-other-ai-features-8j9lfjwl3 og:image: https://api.daily.dev/og/posts/8J9lfJwl3.png og:image:alt: Android Studio Panda: planning mode, next edit prediction, and other AI features og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Android Studio Panda: planning mode, next edit prediction, and other AI features **[Collections](https://daily.dev/sources/collections)** · 3 min read · 3 upvotes · 1 comments ## Summary Android Studio Panda (stable as Panda 4) introduces several AI-powered features: Planning Mode lets you review and refine an agent's step-by-step plan before execution; Next Edit Prediction anticipates where the next logical code change should happen across a file; a new AI project flow generates working Kotlin/Compose prototypes from a single prompt; a Gemini API Starter Template handles Firebase wiring and API key management; the Version Upgrade Assistant automates dependency bumping and error fixing; the Gemini agent gains real-time web search for up-to-date library docs; Custom Skills encode project-specific workflows; and Granular Permissions control what actions the agent can take. ## Content Android Studio Panda (now stable as Panda 4) ships a batch of AI-powered features aimed at reducing the manual overhead of Android development. Here's what's new. ## Planning mode Before the agent writes a single line of code, Planning Mode lets you see and comment on what it intends to do. The agent produces a step-by-step implementation plan, you can push back or refine it, and only then does it start executing. Progress is tracked in a task list artifact, and when it finishes, a walkthrough artifact summarizes every change made. This is useful for complex tasks where you'd otherwise discover halfway through that the agent went in the wrong direction. ## Next Edit Prediction Next Edit Prediction (NEP) goes beyond cursor-position autocomplete. It watches your recent edits and anticipates where the *next* logical change needs to happen — even if that location is somewhere else in the file. Update a constructor, and it might suggest the corresponding change in your preview code without you having to navigate there. In practice this means less context-switching when a single conceptual change touches multiple spots. ## Project Assistant and new project flow A new AI-powered project flow lets you describe an app in a single prompt and get back a working prototype built with Kotlin, Compose, and standard best-practice libraries. It's not a blank template — it generates actual structure you can build on. ## Gemini API Starter Template For apps that need generative AI, there's a new Gemini API Starter Template that wires up Firebase, handles API key management, and sets up the backend scaffolding automatically. Less boilerplate to write before you get to the interesting parts. ## Version Upgrade Assistant Dependency upgrades are tedious. The Version Upgrade Assistant automates the process by iteratively bumping versions, building, and fixing the errors that result — repeating until things compile cleanly. ## Agent Web Search The built-in Gemini agent can now query Google in real time. This matters most for third-party libraries whose documentation postdates the model's training data — the agent can look up current APIs rather than hallucinating outdated ones. ## Custom Skills and Granular Permissions Teams can encode project-specific workflows as Custom Skills — reusable agent instructions that capture how *your* codebase does things. Alongside that, Granular Agent Permissions let you control exactly what actions the agent is allowed to take, so you're not handing over a blank check. ## New templates Two new templates reduce setup friction: one for the Car App Library (previously a lot of boilerplate to get started) and the Gemini API integration template mentioned above. --- The through-line across all of these is reducing the gap between "I know what I want to build" and "I have working code" — whether that's through better autocomplete, automated dependency management, or an agent that explains its plan before acting on it. ## Community discussion Top comments from developers on daily.dev. **@allinonetools** · 3 upvotes > Planning mode looks especially useful—catching wrong assumptions before touching code can save a lot of rework. Also like next edit prediction, small feature but huge time saver during refactors. --- Tags: [#android](https://daily.dev/tags/android), [#kotlin](https://daily.dev/tags/kotlin), [#google-gemini](https://daily.dev/tags/google-gemini), [#android-studio](https://daily.dev/tags/android-studio), [#ai-assisted-development](https://daily.dev/tags/ai-assisted-development) [View this post on daily.dev](https://daily.dev/posts/android-studio-panda-planning-mode-next-edit-prediction-and-other-ai-features-8j9lfjwl3) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Android Studio Panda: planning mode, next edit prediction, and other AI features","url":"https://daily.dev/posts/android-studio-panda-planning-mode-next-edit-prediction-and-other-ai-features-8j9lfjwl3","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/android-studio-panda-planning-mode-next-edit-prediction-and-other-ai-features-8j9lfjwl3"},"datePublished":"2026-04-23T17:15:59.292Z","dateModified":"2026-04-24T16:50:25.471Z","description":"Android Studio Panda (stable as Panda 4) introduces several AI-powered features: Planning Mode lets you review and refine an agent's step-by-step plan before...","image":"https://i.ytimg.com/vi/LvqggFvnX_E/sddefault.jpg","thumbnailUrl":"https://i.ytimg.com/vi/LvqggFvnX_E/sddefault.jpg","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":1,"discussionUrl":"https://daily.dev/posts/android-studio-panda-planning-mode-next-edit-prediction-and-other-ai-features-8j9lfjwl3","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":1}],"keywords":"android,kotlin,google-gemini,android-studio,ai-assisted-development","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"Android Studio Panda: planning mode, next edit prediction, and other AI features"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/android-studio-panda-planning-mode-next-edit-prediction-and-other-ai-features-8j9lfjwl3","comment":[{"@type":"Comment","text":"Planning mode looks especially useful—catching wrong assumptions before touching code can save a lot of rework. Also like next edit prediction, small feature but huge time saver during refactors.","datePublished":"2026-04-24T03:34:04.421Z","url":"https://daily.dev/posts/8J9lfJwl3#c-wKyvnALIn","author":{"@type":"Person","name":"AllInOneTools","url":"https://daily.dev/allinonetools","image":"https://media.daily.dev/image/upload/s--4ZT8QlF0--/f_auto/v1769790028/avatars/avatar_igzBsWloJeaegzm9bQltZ?_a=BAMAMiiu0"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":3}}]} ```