# AutoDev: Automated AI-Driven development

Source: https://arxiv.org/abs/2403.08299
Kiwi News: https://news.kiwistand.com/stories/AutoDev-Automated-AI-Driven-development?index=0x65f83cdb43f79a89c59fdb56cf58ee3e9e125d6bff2bb2f8da89408037cc16324c7bf79b
Submitted by macbudkowski.eth on 2024-03-18 UTC, 1 upvote, 0 comments

## Summary

AutoDev is presented as a fully automated AI-driven software development framework that plans and executes complex software engineering tasks autonomously. Its AI agents can edit and retrieve files, run builds, execute code, run tests, and perform git operations, using compiler output, logs, and static analysis tools. All operations run inside Docker containers, and users can define permitted or restricted commands. On the HumanEval dataset, the authors report Pass@1 scores of 91.5% for code generation and 87.8% for test generation.

## Article

AutoDev: Automated AI-Driven Development

Authors: Michele Tufano, Anisha Agarwal, Jinu Jang, Roshanak Zilouchian Moghaddam, Neel Sundaresan

The landscape of software development has witnessed a paradigm shift with the advent of AI-powered assistants, exemplified by GitHub Copilot. However, existing solutions are not leveraging all the potential capabilities available in an IDE such as building, testing, executing code, git operations, etc. Therefore, they are constrained by their limited capabilities, primarily focusing on suggesting code snippets and file manipulation within a chat-based interface. To fill this gap, we present AutoDev, a fully automated AI-driven software development framework, designed for autonomous planning and execution of intricate software engineering tasks. AutoDev enables users to define complex software engineering objectives, which are assigned to AutoDev's autonomous AI Agents to achieve. These AI agents can perform diverse operations on a codebase, including file editing, retrieval, build processes, execution, testing, and git operations. They also have access to files, compiler output, build and testing logs, static analysis tools, and more. This enables the AI Agents to execute tasks in a fully automated manner with a comprehensive understanding of the contextual information required. Furthermore, AutoDev establishes a secure development environment by confining all operations within Docker containers. This framework incorporates guardrails to ensure user privacy and file security, allowing users to define specific permitted or restricted commands and operations within AutoDev. In our evaluation, we tested AutoDev on the HumanEval dataset, obtaining promising results with 91.5% and 87.8% of Pass@1 for code generation and test generation respectively, demonstrating its effectiveness in automating software engineering tasks while maintaining a secure and user-controlled development environment.