AI can automate much of today’s mundane software development tasks. It can also help software engineers produce code more quickly.
AI-augmented software engineering tools help developers write more and better code, because emerging AI tools can recommend the best code fragments to meet functional and operational requirements. Software engineers who use these tools are more productive, happier and tend to stay longer in their jobs than those who do not.
Here are five ways that forward-thinking software engineers can immediately start to leverage AI for critical activities along the software-development life cycle.
Use generative AI to write and understand software code.
- Generative AI code generation tools like GitHub Copilot, Amazon Code Whisperer and Google Codey are good choices for almost any enterprise seeking AI-enabled code generation tools.
- The use of non-enterprise large language model (LLM) offerings, such as public versions of ChatGPT and Google Bard, by contrast, requires several trade-offs that many enterprises will find unacceptable. For example, your prompts and code may be included in future updates to the vendor products, which could put you in breach of data privacy regulations and leak critical intellectual property.
- Tap plug-in coding assistants powered by machine learning to offer predictions of what single or multiline code fragments might come next, speeding the build.
- Interact with code assistants in an exploratory, conversational manner to help turn a vague idea into a program.
Deploy generative AI as an app modernization tool
- Gartner predicts that by 2027, 70% of professional developers will use AI-powered coding tools, up from less than 10% today. Here’s how generative AI can help with app modernization:
- OpenAI’s ChatGPT chatbot can already translate software code from one language to another, providing a quick and easy automated way to transform and modernize software code.
- GenAI tools can support developers’ app modernization efforts, but we recommend limiting their use.
- There are significant risks if code is not translated exactly, which can happen because of generative AI solutions injecting hallucinations (such as made-up methods, APIs (Application Programming Interface) (Application Programming Interface) (Application Programming Interface)) and other factual errors into code.
Use generative AI to explain, detect and measure technical debt and its impact
- Technology debt is the amount of money that an organization must spend to meet its digital technology cost obligations and continue doing business. Technical debt is the segment that originates from software application architecture, design, and development. Generative AI can help manage this burden.
- To effectively prioritize the debt risk and remediation cost with business partners, use generative AI to detect and measure sources of technical debt and simply demonstrate the implications, risks and level of effort required for remediation.
- For now, do not use generative AI products to remediate or track technical debt. Doing so is expensive and can produce inaccurate results.
Meet user expectations for AI-powered products and services
- Generative AI is forcing user experience (UX) designers to deliver against users’ increasing expectations of AI-driven products and services.
- As conversational prompt-based interfaces proliferate, users expect to see this feature in software products. Failing to provide it will lead to unhappy users. Top of Form
- Yet, pushing such features when the user-base does not want it, will backfire. Therefore, user research is essential.
Leverage AI across the software testing life cycle
- AI is transforming software testing by enabling improved test efficacy, resilience, and faster delivery cycle times.
- AI augmentation can provide benefits across five areas of software testing:
-
-
- Test planning and prioritization
- Test creation and maintenance
- Test data generation
- Visual testing
- Test and defect analysis
-
(This article is authored by Arun Batchu, VP Analyst at Gartner)