How AI and LLMs are changing how code is written and reviewed.
8 articlesAI-assisted development is the practice of using AI tools — code completion, generation, review, and debugging — to augment software engineers throughout the development lifecycle.
AI code generation is the use of large language models to write, complete, or transform source code — accelerating development while introducing new governance and quality challenges.
AI hallucination in code occurs when an AI model generates syntactically plausible but functionally incorrect or nonexistent code — a critical risk for any AI-assisted development workflow.
An agentic workflow is a multi-step automated process where an AI agent plans, executes, and adapts a series of actions toward a goal — using tools and reasoning across multiple steps.
LLM code review uses large language models to analyze pull requests and code changes, generating natural-language feedback on security, quality, and logic issues.
The Model Context Protocol (MCP) is an open standard by Anthropic that allows AI models to connect to external tools, data sources, and services through a standardized interface.
Prompt injection is an attack where malicious instructions embedded in user input override an AI system's intended behavior — a critical security issue for applications built on LLMs.
Vibe coding is a development approach where engineers describe what they want in natural language and let AI generate the implementation — often without reading the resulting code carefully.