Smart Paste: Automatically Fixing Copy/Paste for Google Developers

2025-10-04

AI Summary

Developers frequently incur significant overhead manually reformatting, renaming, or translating pasted code across languages, impeding coding efficiency. To address this, we propose and deploy the first enterprise-grade intelligent paste repair system integrated into production IDEs, enabling an end-to-end closed loop: paste → intent prediction → actionable suggestions → real-time application. The system employs a deep learning model trained on large-scale code corpora to infer likely post-paste editing intentions; a lightweight inference module is embedded directly within the IDE plugin to support diverse recommendations—including code formatting, identifier renaming, and cross-language translation—without round-trip latency. Deployed at scale, the system achieves a 45% suggestion adoption rate and contributes over 1% of all newly written code in the organization, demonstrating both the practical efficacy and operational scalability of AI-powered coding assistance in real-world development workflows.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Intelligent Robots: Embodied AI
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Manually editing pasted code is a long-standing developer pain point. In internal software development at Google, we observe that code is pasted 4 times more often than it is manually typed. These paste actions frequently require follow-up edits, ranging from simple reformatting and renaming to more complex style adjustments and cross-language translations. Prior work has shown deep learning can be used to predict these edits. In this work, we show how to iteratively develop and scale Smart Paste, an IDE feature for post-paste edit suggestions, to Google's development environment. This experience can serve as a guide for AI practitioners on a holistic approach to feature development, covering user experience, system integration, and model capabilities. Since deployment, Smart Paste has had overwhelmingly positive feedback with a 45% acceptance rate. At Google's enterprise scale, these accepted suggestions account substantially for over 1% of all code written company-wide.

Problem

• Automating post-paste code edits for developers
• Reducing manual reformatting and style adjustments
• Providing cross-language translation in pasted code

Innovation

• AI-powered IDE feature for post-paste edits
• Deep learning predicts required code modifications
• Integrated system covering UX and model capabilities