Atlassian has added a command line interface (CLI) option to provide application developers with a familiar construct for invoking Rovo Dev, its artificial intelligence (AI) agent for building software

Part of a portfolio of Rovo Software Agents that Atlassian now makes available in beta, Rovo Dev completes and debugs code, creates tests, surfaces insights and explanations of code bases, makes suggestions to improve code and generates documentation. It is also integrated with Jira project management software and Confluence collaboration tools provided by Atlassian.

Using a set of software engineering (SWE) benchmarks maintained by researchers at Princeton and Stanford, Rovo Dev achieved a 41.98% resolve rate across 2,294 tasks.

It can also be integrated via a Model Context Protocol (MCP) Server to access external data sources capable of providing more context that might be needed to complete a specific task.

Shuyin Zhao, vice president of product for Atlassian, said the goal is to provide a single agent capable of performing a wide range of tasks versus requiring developers to create workflows that require them to orchestrate multiple agents to build and deploy software. The more memory that can be allocated to an AI agent the more it is able to preserve context, she added.

Longer term, as the reasoning capabilities provided by large language models (LLMs) continue to expand, the scope of complex tasks that can be assigned to that AI agent will also increase, noted Zhao.

Eventually, many developers will find they will be spending more time reading and evaluating code rather than writing it themselves, she added.

It’s not clear how widely AI tools are being adopted by software developers and engineers, but a Futurum Group survey found 41% of respondents expect generative AI tools and platforms will be used to generate, review and test code. The one thing that is certain is more developers than ever are using these tools to write code, but how much of that code is making it into production environments is unknown. In some instances, an AI tool might enable a developer to write better code than they can on their own. In other instances, it might create vulnerabilities or recommend using software packages that simply don’t exist.

Additionally, even as more code is generated, the existing DevOps pipelines might not be robust enough to deploy software at higher levels of scale than what is already being achieved.

None of that means AI agents won’t be incorporated into DevOps workflows, but it does mean there is still a considerable amount of effort required to re-engineer those processes in a way that is optimized for AI agents rather than human application developers.

In the meantime, however, DevOps teams would be well-advised to start creating a list of tasks they are willing to delegate to AI agents, assuming there is some level of supervision. Otherwise, it’s all but inevitable that AI agents might generate the same issues that human developers create, albeit just at a different level of scale. The issue then becomes making sure the right governance policies are in place to prevent as many of those issues from arising in the first place.