Improving NetApp engineering with GenAI

As software development grows in complexity, developers are turning to AI to help streamline their workflows and improve engineering productivity. AI has become an invaluable tool in the coding process, helping with everything from code optimization to debugging and testing. At NetApp, we’re exploring how we can use generative AI (GenAI) to accelerate our product innovation and ensure that proper safeguards are in place.

However, it’s important to note that AI is not a replacement for developers but rather a powerful tool to augment their capabilities. Developers must still provide direction, context, and oversight so that AI-generated content follows best practices.

Thomas Edison once stated, “Good fortune is what happens when opportunity meets with planning.” That is precisely what we’re doing at NetApp with GenAI: defining our expected outcomes, planning our objectives and priorities, establishing our ground rules, anticipating potential challenges, and equipping our team with the confidence to navigate the path forward.

To ensure that the technology operates ethically, safely, and reliably, guardrails must be established for using AI. Transparency, accountability, and privacy are principles that must be included in these policies. Transparency requires creating explicit guidelines for approved use cases and restrictions with GenAI. Accountability means that employees use GenAI applications responsibly, and privacy protects data from unauthorized access and misuse.

We’re introducing the following safeguards as we adopt GenAI at NetApp:

• Confidential information and intellectual property are used in approved systems only.
• Heightened precautions must be followed for GenAI output in products, services, or any automated decision-making.
• NetApp’s data governance policy, information classification policy, and record retention schedule need to be followed.
• Federal data, as defined in the federal data reference guide, may not be used with GenAI.
• Any use of GenAI must comply with NetApp’s Global Security and IT policies.

To enhance developer productivity, we’re exploring several GenAI use cases:

• Knowledge search
• Unit testing and test automation
• Log and failure analysis
• Bug identification
• Code translation
• Code assist
• Creation of internal source-code documentation

Just as the iPhone revolutionized communication, information access, and daily tasks by consolidating multiple functions into one user-friendly device, AI is transforming industries by simplifying and streamlining complex user tasks. Initially, companies took a cautious approach to smartphones, allowing personal devices in the workplace only after setting business guidelines and allowing security measures to mature.

Similarly, NetApp aims to harness the benefits of AI while integrating policies and guidelines to ensure safe usage. Safeguards need to be flexible rather than static, adjusting as processes and technologies mature. This approach allows us to safely explore the unprecedented benefits of GenAI and its impact on our business.

Developers often find debugging and testing time-consuming and tedious, but GenAI can help streamline these processes.

AI algorithms can identify potential bugs by analyzing code for common error patterns, suggesting fixes, and automatically refactoring problematic code sections.

In addition to identifying and fixing bugs, GenAI enhances the testing phase by automatically creating unit tests, covering a wide range of scenarios that developers might miss. One of the most significant advantages of GenAI is its ability to identify edge cases—those often-overlooked conditions that can cause unexpected behavior in software. This speeds up the debugging process and enhances code reliability and quality.

Using AI as a tool for internal corporate knowledge can revolutionize how developers access and use information. An AI-powered chatbot can act as an intuitive and efficient interface for querying vast amounts of internal data, ranging from questions about departmental engineering tools to explanations of specific code. By leveraging information from internal data repositories, the chatbot can respond to developer queries in real time, providing accurate and contextually relevant domain knowledge. Instead of spending hours searching through internal wiki pages, NetApp developers can simply ask the chatbot—increasing productivity, reducing time spent searching for information, and ensuring easy access to up-to-date, well-referenced resources.

Using AI to help with code translation, such as converting Perl to Python, can significantly streamline software development. By assisting in the translation process, developers can save substantial time and effort typically spent manually rewriting and debugging code. The AI assistant can suggest adapting language-specific idioms, which can optimize performance and ensure compatibility with Python’s libraries and frameworks. Furthermore, the AI tool can learn from various coding examples, improving its accuracy and efficiency in translating complex codebases.

This use of AI enhances productivity and reduces the likelihood of human error, allowing developers to be more productive and focus on higher-level design and innovation tasks.

As AI technology evolves, its potential to enhance organizational efficiency will only increase. By taking advantage of AI, NetApp developers can concentrate on creative problem-solving, strategic planning, and innovation, thereby improving the overall efficiency and quality of our software development process. Striking the right balance between AI and human expertise allows NetApp developers to accelerate product enhancements, enabling customers to advance their AI initiatives.

To explore further, visit our NetApp^® AI solutions page.

Read more about NetApp AI thought leadership perspectives.

If you missed out on our webinar where we talked through the survey results of IDC’s AI maturity model white paper, you can watch it on demand.