Perforce Software this week committed to building an agentic artificial intelligence (AI) framework that will be embedded across its entire portfolio of DevOps tools and platforms.

Company CTO Anjali Arora said Perforce Intelligence will provide access to a set of AI agents that have been trained to automate a range of software engineering tasks that DevOps engineers will be able to orchestrate.

Additionally, Perforce is committing to using the same fabric to integrate its AI agents with other AI agents being developed by, for example, cloud service providers, she added.

Perforce, for example, has already added several AI agents to platforms such as Gliffy, a diagramming platform for Confluence, a Wiki-based collaboration platform for sharing documents provided by Atlassian.

Next month, AI agents will also be added to the Puppet Enterprise Advanced platform to provide access to Puppet Infra Assistant, a natural language chat interface that allows DevOps teams to quickly understand what is happening across the IT environments that have adopted the IT automation that Perforce acquired in 2022.

Via that interface, it becomes possible to know how something is working, what versions of modules or server operating systems are being used and whether something is in or out of compliance without needing to know the Puppet programming language.

Ultimately, the AI agents being developed by Perforce will make it simpler for DevOps teams to create and maintain workflows across a portfolio of DevOps tools and platforms that Perforce has acquired over the past few years, including BlazeMeter, an application testing platform, Delphix, a provider of data masking platform, and, most recently, Snowtrack, a provider of version control software used by application designers.

The overall goal is to eliminate the need for scripts, frameworks, or other legacy approaches to integration in favor of AI agents that share access to an orchestration framework. Those agents will be able to proactively adapt as changes are made across the entire software development lifecycle (SDLC), said Arora.

DevOps teams that have had early access to these AI agents have seen 50% efficiency gains while increasing test coverage by 20%, according to Perforce. In time, it’s apparent DevOps teams will be able to more effectively manage a much broader portfolio of applications, noted Arora. The challenge will be adapting existing DevOps cultures to include AI agents that software engineers are assigning tasks to complete, with the help of other AI agents and policy controls to provide governance functions and validations of output, she added.

It’s not clear to what degree DevOps teams have adopted AI, but research from the Futurum Group finds 41% of respondents expect generative AI tools and platforms will be used to generate, review and test code. A total of 39% also plan to make use of AI models based on machine learning algorithms.

Regardless of what type of AI technologies are adopted, hopefully, DevOps workflows and pipelines will soon be reconstructed in a way that is significantly less fragile as more scripts and connectors are eventually replaced by AI agents.