Will artificial intelligence (AI) help move DevOps efforts from fragile to agile? There is speculation in the industry that AI can significantly speed up not only code generation for software, but all the details that come with it, including specifications, documentation, testing, implementation, etc.
AI has been used for several years in its operational and predictive form, working behind the scenes to automate work processes and planning. Now, IT managers and professionals are harnessing the potential of generative artificial intelligence.
Also: Agile development can unlock the power of generative artificial intelligence – here’s how
Over the next three years, the number of platform engineering teams using AI to enhance the software development lifecycle is likely to increase by 5% to 40%, according to an analysis published by a team of Gartner analysts led by Manjunath Bhat.
Across the IT industry, there is notable optimism about the potential that AI brings to DevOps and related Agile practices. “The combination of DevOps and AI can complement each other by improving all phases of the software development lifecycle and enabling faster, more reliable and more efficient time-to-market,” Billy Dickerson, chief software officer at SAS, told ZDNET.
Also: 3 ways to accelerate generative AI implementation and optimization
There is a lot of activity happening around generative artificial intelligence and the DevOps process. Nearly all (97%) of the 408 technology leaders surveyed in a survey released by automation specialist Stonebranch indicated they were “interested in integrating generative artificial intelligence into their automation programs.” These professionals “see genAI as an essential tool for connecting a more diverse set of tools and empowering a wider range of users,” the authors of the survey point out.
AI is driving DevOps, but DevOps is also driving AI application development, as Stonebranch’s research shows. At least 72% of respondents have adopted machine learning pipelines to power their generative AI initiatives.
Although the use of generative artificial intelligence to create or modify software code has received much attention, it is only a fraction of the development process. It’s time to look at how AI can help IT professionals and managers in other ways.
“On average, developers spend between 10% and 25% of their time writing code,” wrote Gartner’s Bhat and his co-authors. “The rest of the time is spent reading specs, writing documentation, reviewing code, attending meetings, helping colleagues, debugging existing code, collaborating with other teams, securing environments, troubleshooting production issues, and learning technical and business concepts. to name a few. »
Integrating AI into “all phases of the DevOps feedback loop—planning, code review and development, building, testing, deploying, monitoring, measuring—increases collaboration within teams and positively improves results,” emphasized SAS’s Dickerson. In addition to planning, “AI can make the project management process more efficient by automatically generating requirements from user requests, detecting mismatched deadlines, and even identifying incomplete requirements.”
Dickerson said AI can also handle heavy code review and development processes: “Not only can AI offer developers suggestions for automatically generating boilerplate code, but it can also contribute to the code review process. This approach enhances collaboration between teams and can lead to more innovation, faster time-to-market and better alignment with business goals. »
Still, tech leaders and experts should be careful before going too far with AI-powered DevOps and other Agile practices. “Overreliance is a risk,” Ian Ferguson, senior director of SiFive and former vice president of marketing at Lynx Software Technologies, told ZDNET.
Also: Generative AI is the technology that IT feels the most pressure to take advantage of
“If we don’t understand how the autonomous AI platform came to a decision, we lose accountability,” Ferguson said. “Without transparency in AI thinking, we risk blindly accepting the results without being able to question or confirm them. We face a future where a very limited number of companies can create complicated systems, or we see a decline in system quality. ”
Ferguson called for fostering “human-AI collaborative dynamics in DevOps.” AI can handle rote coding, while humans have to define the complete set of system requirements and behaviors themselves,” he explained.
Dickerson also advised caution when adopting AI-driven DevOps: “Since AI can automate many tasks in the DevOps feedback loop, ideally there should be human oversight to ensure that AI is making the right automated decisions. approval of every major business decision.
In their report to Gartner, Bhat and his co-authors said that applying artificial intelligence to part of the software development life cycle “can result in move rather than economy effort, creating a false impression of saving time. For example, time saved during coding can be offset by increased time spent on code review and debugging. »
Also read: AI sector is booming: ChatGPT Enterprise now has over 600,000 users.
However, there are reasons to be excited about AI’s impact on DevOps. The data suggests that AI can be applied to assist or accelerate the later stages of the DevOps process. When it comes to the build and test phase of software, for example, “AI can evaluate the inputs and outputs of the build process and look for failure patterns to optimize recovery time,” Dickerson said.
In addition, “with its ability to analyze large amounts of data and make predictions, AI can also help analyze test results. This can help identify the most influential and unreliable test patterns to optimize the testing process.”
In the implementation phase, “AI can automate the provisioning, configuration and management of shared infrastructure resources. In turn, this can trigger deployments using these automatically generated artifacts, which can then allow engineers to spend more time on complex deployments,” said Dickerson. .
As for monitoring and measurement, “because enterprise deployments can produce a large amount of data, DevOps teams can have trouble digesting the information needed to solve problems as they arise,” Dickerson said. “To aid this effort, artificial intelligence can analyze metrics and logs in real-time to detect problems much earlier and enable faster resolution. By continuously analyzing data and patterns, AI can predict potential bottlenecks, identify areas for improvement and help with optimization. all stages of the DevOps life cycle.
Ferguson said that with human oversight, “AI can augment approaches like DevOps and Agile.” He said that effectively combining AI and humans throughout the software lifecycle can increase productivity and innovation: “However, we need to shape this future proactively, through transparency, building from trust, to workflow reengineering and skills training.