AI-assisted software development

AI-assisted software development is the use of artificial intelligence agents to augment the software development life cycle. It uses large language models (LLMs), natural language processing, and other AI technologies to assist software developers in a range of tasks from initial code generation to subsequent debugging, testing and documentation.

Technologies

Code generation

LLMs that have been trained on source code repositories are able to generate functional code from natural language prompts. Such models have knowledge of programming syntax, common design patterns and best practices in a variety of programming languages.

Intelligent code completion

AI agents using pre-trained and fine-tuned LLMs can predict and suggest code completions based on context, going beyond simple keyword matching to infer the developer's intent and picture the broader structure of the developing codebase. 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.

Testing, debugging, code review and analysis

AI is used to automatically generate test cases, identify potential bugs, 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 perform static code analysis, identify security vulnerabilities, suggest performance improvements and ensure adherence to coding standards and best practices.

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 the Common Weakness Enumeration (CWE), being comparable to contemporary, non-AI bug fixing tools. These approaches build on LLMs’ code-generation capability and the resulting patches still require validation through software testing, static program analysis, and human code review.

Challenges

The incorporation of AI tools has introduced new ethical dilemmas and intellectual 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. Changes in the role of software engineers are inevitable.

Governance and oversight

The outputs from AI-assisted software development require to be validated through a combination of automated testing, static analysis tools and human review, creating a governance layer that acts as a safeguard ensuring quality and accountability.

Security risks and challenges

AI-assisted software development introduces novel security risks that extend beyond traditional software vulnerabilities.

Increased vulnerability introduction

Research indicates that developers using AI coding assistants frequently encounter security issues in AI-generated code. A 2023 survey by Snyk found that 56.4% of developers reported that AI coding tools sometimes or frequently introduce security vulnerabilities, yet 80% of developers bypass established security policies when using these tools. The vulnerabilities stem partly from AI models being trained on historical code repositories that may contain outdated or insecure patterns, which the models then suggest with high confidence to developers.

Prompt injection attacks

AI coding tools are susceptible to prompt injection attacks, where malicious instructions embedded in external data sources—such as documents, codebases, or web content—can manipulate the AI's behavior in unintended ways. The OWASP Top 10 for Large Language Model Applications, first published in 2023, identifies prompt injection as the highest-priority vulnerability for LLM-based systems. These attacks can be direct, where users craft malicious prompts, or indirect, where malicious content is embedded in external sources that the AI processes.

Agentic AI risks

Modern AI coding tools increasingly operate as autonomous agents with access to file systems, terminals, and network resources. In September 2024, Anthropic reported that a suspected Chinese state-sponsored threat actor manipulated their Claude Code tool to autonomously target approximately 30 global organizations across technology, finance, chemical manufacturing, and government sectors. Anthropic characterized this as "the first documented case of a large-scale cyberattack executed without substantial human intervention," with AI performing 80-90% of the operation independently.

Shadow AI

Organizations face risks from unauthorized use of AI coding tools by employees, sometimes called "shadow AI." Developers may inadvertently expose proprietary code, credentials, or sensitive data to external AI services without organizational oversight, creating compliance and data governance challenges. Snyk's research found that 80% of developers admitted to bypassing security policies when using AI coding tools, and only 10% scan most of the AI-generated code they use.

Mitigation approaches

Security frameworks are emerging to address AI-specific development risks. The OWASP Top 10 for Large Language Model Applications provides guidance on vulnerabilities including prompt injection, insecure output handling, training data poisoning, and excessive agency. Recommended mitigations include enforcing least-privilege access controls, implementing human-in-the-loop approval for sensitive operations, segregating untrusted content from user prompts, and validating AI outputs before execution. Organizations such as MITRE have developed frameworks like ATLAS (Adversarial Threat Landscape for AI Systems) to catalog AI-specific attack techniques and inform defensive strategies.

Industry perspectives

Technology sector leaders have highlighted the transformative potential of AI-assisted software development. In an 'Unlocking AI Potential' session of 'Advancing AI 2025' hosted by AMD Developer Central, Andrew Ng and Lisa 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."

See also

• Integrated development environment
• Vibe coding
• GitHub Copilot
• Google DeepMind AlphaCode
• No-code development platform
• Machine learning