GitLab announces new AI-powered features for enhanced DevSecOps efficiency
Tue 21 Nov 2023
GitLab has announced significant updates to GitLab Duo, the company’s suite of AI capabilities. These updates include the beta release of GitLab Duo Chat in GitLab 16.6 this November and general availability of GitLab Duo Code Suggestions in the upcoming GitLab 16.7 release in December.
The new GitLab Duo Chat, a natural-language AI assistant, will provide real-time guidance, insights, and suggestions across a range of development activities. This includes code analysis, security issue resolution, troubleshooting CI/CD pipeline failures, and assisting with merge requests.
GitLab Duo Chat complements Code Suggestions as one of the primary AI-powered interfaces in GitLab’s DevSecOps platform.
David DeSanto, Chief Product Officer at GitLab, explained the strategic vision behind these updates: “The introduction of GitLab Duo Chat furthers our momentum and focus to bring AI beyond just code creation. To realise AI’s full potential, it needs to be embedded across the software development lifecycle, allowing DevSecOps teams to benefit from boosts to security, efficiency, and collaboration.”
GitLab Duo currently has a suite of 14 AI capabilities, ranging from suggested reviewers and code explanation, to planning description generation and value stream forecasting. According to GitLab’s own research, these tools significantly optimise the software development lifecycle. The ‘State of AI in Software Development’ report suggests that developers currently spend only a quarter of their time writing code.
The implementation of GitLab Duo aims to reduce toolchain sprawl and enhance developer productivity, potentially leading to sevenfold faster cycle times and reduced software expenses.
“Organisations have never been more pressed to deliver innovation faster at lower costs while minimising security risk, and we believe GitLab’s AI-powered DevSecOps Platform can help drive that efficiency,” added in DeSanto.
The general availability of Code Suggestions in December is another milestone for GitLab. This feature is designed to aid development, security, and operations teams in creating and updating code more efficiently. This can help teams build more secure software at a faster pace.
Kate Holterhoff, an Industry Analyst at RedMonk, said: “The developers we speak with at RedMonk are keenly interested in the productivity and efficiency gains that code assistants promise. GitLab’s Duo Code Suggestions is a welcome player in this space, expanding the available options for enabling an AI-enhanced software development lifecycle.”
GitLab Duo’s introduction also addresses critical concerns around AI adoption in software development, with a focus on team collaboration, security, and compliance. GitLab’s commitment to privacy and transparency is evident in their approach, aiming to provide customers with the necessary information about AI-assisted features and data protection.
These updates from GitLab signal a step forward in integrating AI across the entire software development lifecycle, promising enhanced efficiency, security, and collaboration for DevSecOps teams.