Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kumar, Anand, Khare, Vishal, Sharma, Deepak, Kumar, Satyam, Saini, Vijay, Yadav, Anshul, Jain, Sachendra, Rana, Ankit, Verma, Pratham, Meena, Vaibhav, Edubilli, Avinash
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.19708
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912602405208064
author Kumar, Anand
Khare, Vishal
Sharma, Deepak
Kumar, Satyam
Saini, Vijay
Yadav, Anshul
Jain, Sachendra
Rana, Ankit
Verma, Pratham
Meena, Vaibhav
Edubilli, Avinash
author_facet Kumar, Anand
Khare, Vishal
Sharma, Deepak
Kumar, Satyam
Saini, Vijay
Yadav, Anshul
Jain, Sachendra
Rana, Ankit
Verma, Pratham
Meena, Vaibhav
Edubilli, Avinash
contents We present a comprehensive real-world evaluation of AI-assisted software development tools deployed at enterprise scale. Over one year, 300 engineers across multiple teams integrated an in-house AI platform (DeputyDev) that combines code generation and automated review capabilities into their daily workflows. Through rigorous cohort analysis, our study demonstrates statistically significant productivity improvements, including an overall 31.8% reduction in PR review cycle time. Developer adoption was strong, with 85% satisfaction for code review features and 93% expressing a desire to continue using the platform. Adoption patterns showed systematic scaling from 4% engagement in month 1 to 83% peak usage by month 6, stabilizing at 60% active engagement. Top adopters achieved a 61% increase in code volume pushed to production, contributing to approximately 30 to 40% of code shipped to production through this tool, accounting for an overall 28% increase in code shipment volume. Unlike controlled benchmark evaluations, our longitudinal analysis provides empirical evidence from production environments, revealing both the transformative potential and practical deployment challenges of integrating AI into enterprise software development workflows.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19708
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Intuition to Evidence: Measuring AI's True Impact on Developer Productivity
Kumar, Anand
Khare, Vishal
Sharma, Deepak
Kumar, Satyam
Saini, Vijay
Yadav, Anshul
Jain, Sachendra
Rana, Ankit
Verma, Pratham
Meena, Vaibhav
Edubilli, Avinash
Software Engineering
Artificial Intelligence
Machine Learning
We present a comprehensive real-world evaluation of AI-assisted software development tools deployed at enterprise scale. Over one year, 300 engineers across multiple teams integrated an in-house AI platform (DeputyDev) that combines code generation and automated review capabilities into their daily workflows. Through rigorous cohort analysis, our study demonstrates statistically significant productivity improvements, including an overall 31.8% reduction in PR review cycle time. Developer adoption was strong, with 85% satisfaction for code review features and 93% expressing a desire to continue using the platform. Adoption patterns showed systematic scaling from 4% engagement in month 1 to 83% peak usage by month 6, stabilizing at 60% active engagement. Top adopters achieved a 61% increase in code volume pushed to production, contributing to approximately 30 to 40% of code shipped to production through this tool, accounting for an overall 28% increase in code shipment volume. Unlike controlled benchmark evaluations, our longitudinal analysis provides empirical evidence from production environments, revealing both the transformative potential and practical deployment challenges of integrating AI into enterprise software development workflows.
title Intuition to Evidence: Measuring AI's True Impact on Developer Productivity
topic Software Engineering
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2509.19708