GitLab unveils AI-powered Duo Chat and Code Suggestions to boost DevSecOps

GitLab, the AI-powered DevSecOps platform, has announced updates to GitLab Duo, its suite of AI capabilities. These updates include the beta launch of GitLab Duo Chat and the general availability of GitLab Duo Code Suggestions.

GitLab Duo Chat, a natural-language AI assistant, offers real-time support. This assistant provides users with guidance, insights, and suggestions to help in tasks including analysing code, planning, addressing security issues, troubleshooting Continuous Integration/ Continuous Deployment (CI/CD) pipeline failures, and assisting with merge requests.

Duo Chat, currently in beta, will join Code Suggestions as one of the two main interfaces into GitLab's AI-assisted suite within its DevSecOps platform.

GitLab's suite Duo includes 14 AI capabilities such as Suggested Reviewers, Code Suggestions, Chat, Vulnerability Summary, Code Explanation, Planning Discussions Summary, Merge Request Summary, Merge Request Template Population, Code Review Summary, Test Generation, Git Suggestions, Root Cause Analysis, Planning Description Generation, and Value Stream Forecasting.

According to GitLab's State of AI in Software Development report, developers spend only a quarter of their time writing code. GitLab Duo aspires to optimise the complete software development lifecycle and reduce toolchain sprawl, aiming to lead to much faster cycle times and improving both developer productivity and reducing software spend.

In addition to introducing GitLab Duo Chat now in beta, GitLab will also make Code Suggestions generally available in their 16.7 December product release. Code Suggestions helps development, security, and operations teams to create new code and update existing code. The aim is to lighten cognitive load on developers, increase efficiency, and enable them to quickly build more secure software.

According to GitLab's report, 83% of DevSecOps professionals claim that implementing AI in their software development processes is essential to maintain their competitive edge. A robust 95% stated that they prioritise privacy and the protection of intellectual property when selecting an AI tool.

GitLab Duo aims to minimise the security and compliance risks associated with AI adoption by bringing the entire software development lifecycle into a single privacy-first AI-powered application. This approach is designed to give customers essential information about GitLab Duo's AI-assisted features and how data is securely used and protected.

Kate Holterhoff, an industry analyst at RedMonk, commented on the productivity and efficiency gains that code assistants can offer. She 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."

Speaking on GitLab's latest updates, David DeSanto, chief product officer of GitLab, said, "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 security, efficiency, and collaboration improvements. 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."