| Part ofa series on |
| Artificial intelligence (AI) |
|---|
_artificial_intelligence_icon.png){kind=icon} |
Glossary |
AI-assisted software development is the use ofartificial intelligence agents to augment thesoftware development life cycle. It useslarge language models (LLMs),natural language processing, and other AI technologies to assistsoftware developers in a range of tasks from initialcode generation to subsequentdebugging,testing anddocumentation.[1]
LLMs that have been trained onsource coderepositories are able to generatefunctional code from natural languageprompts. Such models have knowledge ofprogramming syntax, commondesign patterns andbest practices in a variety ofprogramming languages.[2]
AI agents using pre-trained and fine-tuned LLMs can predict and suggestcode completions based on context, going beyond simple keyword matching to infer the developer's intent and picture the broader structure of the developingcodebase. An analysis has shown that such use of LLMs significantly enhances code completion performance across several programming languages and contexts, and the resulting capability of predicting relevant code snippets based on context and partial input boosts developer productivity substantially.[3]
AI is used to automatically generatetest cases, identify potentialbugs, and suggest fixes. LLMs trained on historical bug data can enable prediction of likely failure points in generated code. Similarly, AI agents are used to performstatic code analysis, identifysecurity vulnerabilities, suggest performance improvements and ensure adherence tocoding standards and best practices.[1]
Beyond detection, researchers have explored using LLMs for automated program repair, where models propose candidate patches for buggy code. Off-the-shelf LLMs have been reported to repair some security-relevant defects in a zero-shot setting (i.e., without task-specific fine-tuning), including issues categorized by theCommon Weakness Enumeration (CWE),[4] being comparable to contemporary, non-AI bug fixing tools. These approaches build on LLMs’ code-generation capability and the resulting patches still require validation throughsoftware testing,static program analysis, and humancode review.[4][5]
The incorporation of AI tools has introduced newethical dilemmas andintellectual property challenges. The ownership of AI-generated code is unclear: who is responsible for the generated end-product? Also unclear are the ethical responsibilities of generated code.[6] Changes in the role ofsoftware engineers are inevitable.[7][8]
The outputs from AI-assisted software development require to be validated through a combination of automated testing, static analysis tools and human review, creating agovernance layer that acts as a safeguard ensuring quality and accountability.[9]
Technology sector leaders have highlighted the transformative potential of AI-assisted software development. In an 'Unlocking AI Potential' session of 'Advancing AI 2025' hosted byAMD Developer Central,Andrew Ng andLisa Su emphasized the strategic and operational implications of integrating AI tools into development workflows. Ng noted that AI systems are increasingly capable of "helping programmers focus on higher-level problem solving", while Su framed the shift as "an opportunity to redefine performance and productivity across industries."[10]
| Concepts |
| ||||||
|---|---|---|---|---|---|---|---|
| Applications |
| ||||||
| Implementations |
| ||||||
| People |
| ||||||
| Architectures |
| ||||||
| Political | |||||||
| Social and economic | |||||||
