GitLab this week made generally available a set of generative artificial intelligence (AI) features that DevOps teams can add to the continuous integration/continuous delivery (CI/CD) platform it provides.

The GitLab Duo Enterprise add-on costs $39 per user per month and offers all the AI ​​capabilities of GitLab Duo Pro, plus tools to improve the efficiency of software development workflows, proactively detect and remediate security vulnerabilities, and securely improve team collaboration.

Features available only in GitLab Duo Enterprise include vulnerability explanation and automated remediation, root cause analysis of logs to resolve CI/CD bottlenecks and errors, summary and template tools for discussions, merge requests, and code reviews, and a dashboard for tracking the impact of AI on DevOps workflows.

David DeSanto, chief product officer at GitLab, said the GitLab Duo Enterprise add-on extends the generative AI capabilities provided by GitLab across the entire software development lifecycle (SDLC) and includes additional capabilities to automate DevSecOps workflows later this year.

The overall goal is to reduce the stress and workload that exhausts DevOps teams over time, he added.

It’s not clear to what extent DevOps teams are integrating AI into their DevOps workflows, but a recent GitLab survey found that the top organizational benefits of AI are improved productivity (51%), faster deployments (44%), and increased accuracy and security (40%).
More than three-quarters (78%) of all respondents said they already use artificial intelligence (AI) for software development or plan to do so in the next two years. However, more than half (55%) also admitted that introducing AI into the software development lifecycle is risky, with data privacy and security being the biggest concern.

In general, continued advances in AI should help make DevOps more accessible to a wider range of organizations. For example, many midsize companies have failed to find and retain the software development expertise needed to implement DevOps workflows. AI tools should reduce the skill level required to implement optimal DevOps workflows.

At the same time, companies that have already adopted DevOps workflows should find it easier to manage them at scale as part of a larger transition to platform development that is now taking place, DeSanto noted. Experienced engineers should be able to use AI to automate more workflows without having to manually write additional scripts, for example.

Regardless of the motivation for adopting AI, one thing is certain: the pace at which applications are built and deployed will only accelerate, so many DevOps teams may find themselves rethinking the way they build pipelines using legacy CI/CD platforms that were not built for the AI ​​era.

In the meantime, DevOps teams would be wise to map out the tasks that AI tools should soon be able to automate to identify where human software developers can add the most value now. Ultimately, AI will not replace the need for software developers, but it will undoubtedly transform their role in organizations as more code is generated automatically.