Posted by Sandhya Mohan – Product Supervisor, Android Studio and Sarmad Hashmi – Software program Engineer, Labs
The Android workforce believes AI has the potential to revolutionize coding, drive unprecedented innovation and productiveness in software program growth, and supercharge your growth productiveness. AI code completion is a key a part of this effort inside Gemini in Android Studio.
Since launching in Might 2024, we have been arduous at work enhancing this function to supply the very best expertise for all Android builders. On this publish, we wish to take you “beneath the hood” on how we achieved a 40% relative enhance in acceptance price since launch, and share a few of our pleasure for the way we now have seen Android builders use this function. We hope you may give it a try to tell us what you suppose.
An AI coding companion for each developer
Our imaginative and prescient for Gemini in Android Studio is to empower builders to construct top quality Android apps — making it simple for builders to shortly write right code aligned with Android’s finest practices. Launched final 12 months, the primary model of Studio Bot offered a chat expertise the place builders may entry Android-specific steerage, powered by Google’s newest AI fashions. Builders are in a position to ask Gemini in Android Studio to supply developer steerage, summarize technical documentation, and critique their Android code. However in all these circumstances the suggestions is reactive, responding to a consumer’s query.
AI code completion takes these capabilities a step additional by offering real-time suggestions as you’re employed as a developer, considering forward and suggesting the subsequent few strains of code that you’re more likely to kind primarily based on the context from the encircling file and what was simply typed. You’ll be able to consider AI Code Completion as a accomplice in your work — a coding companion ready to supply steerage whenever you want it.
This function is especially properly fitted to duties like defining enterprise logic, creating database schemas, making community requests, and even writing checks — duties which are usually time-consuming and distract from constructing the core expertise on your app. Many builders have advised us how a lot they benefit from the velocity AI completions brings to their app growth workflow.
.gif)
Bringing extra clever code completion to Android growth
Whereas we’re excited to see how AI Code Completions have improved builders’ workflows, we all know there’s nonetheless extra we will do to enhance developer productiveness. Improvement of Gemini in Android Studio is an ongoing, large-scale collaborative effort by many groups throughout Google. Earlier this 12 months, we switched to Gemini 1.5 fashions and noticed a big enchancment within the high quality of code completions, leading to a 2x enhance in our developer productiveness metrics, together with general acceptance price for ideas.
As soon as we began doing A/B check experiments to enhance AI code completion we discovered a number of enhancements round mannequin high quality, context, and heuristics. This general effort led to a 40% relative enhance in acceptance price — how usually customers settle for the AI’s proposed code ideas — since we launched. Since then, we have been exploring a number of enhancements like:
- Retrieval augmentation: Along with your opt-in consent, we use the recordsdata and dependencies most related to your present coding context to reinforce the accuracy of ideas. That is simply step one and we’re persevering with to experiment with including much more context from the IDE as a part of every request.
- Filtering out low-confidence completions: Prioritize exhibiting top quality ideas the place they’re most related, and due to this fact most certainly to be accepted. We do that by utilizing a mix of the possibilities returned by the mannequin and utilizing a classifier skilled to establish high-quality completions primarily based on developer suggestions.
- Smarter post-processing: The LLM’s output for AI Code Completion is essentially completely different from the output customers anticipate in a chat session. Responses have to be tightly scoped so as to shortly output helpful code, with out surrounding expository textual content. We apply extra heuristics on the mannequin output to make sure responses are concise and correct, in addition to ensuring that the generated code is legitimate inside the context of the consumer’s codebase.
- Improved fashions: We use opt-in suggestions from Android Studio customers, akin to noting when a code suggestion is accepted or rejected, to adapt the code completion mannequin to their coding model and preferences over time. We frequently ship new fashions with larger high quality information primarily based in your suggestions.
We’re additionally exploring metrics past acceptance price to raised measure AI affect on developer velocity, akin to the share of complete code written by AI.
Attempt it out!
We’re rolling out these profitable experiments and others as shortly as doable.
If you have not tried AI code completions but, you’ll be able to allow this function by clicking on the 
Gemini button in your editor window and signing in to your Google account.
After doing so, navigate to Settings > Instruments > Gemini and choose “Allow AI-based inline code completions”.
As all the time, Google is dedicated to the accountable use of AI. Android Studio will not ship any of your supply code to servers with out your consent — which suggests you may must opt-in to allow Gemini’s developer help options in Android Studio. You’ll be able to learn extra on Gemini in Android Studio’s dedication to privateness.
Attempt enabling AI Code Completions in your challenge and inform us what you suppose on social media with #AndroidGeminiEra. We’re excited to see how these enhancements assist you construct superb apps!
This weblog publish is a part of our collection: AI on Android Highlight Week, the place we offer assets — weblog posts, movies, pattern code, and extra — all designed to to discover the most recent in AI and its potential for Android app growth.
