Code Semantic Zooming
For developers using LLMs for code generation, CodeZoom provides a high-level abstraction to enhance control and comprehension, addressing the limited control of natural language prompts.
CodeZoom introduces a pseudocode-based abstraction layer for LLM-assisted code generation, enabling developers to iteratively refine code across semantic levels. In a user study (n=26), it matched Claude Code on usability while significantly improving code comprehension, with over 90% of participants feeling more in control of design decisions.
Recent advances in Large Language Models (LLMs) have introduced a new paradigm for software development, where source code is generated from natural language prompts. While this paradigm significantly boosts development productivity, building complex, real-world software systems remains challenging because natural language offers limited control over the code generation process. Inspired by the historical evolution of programming languages toward higher levels of abstraction, we advocate for a high-level abstraction language that gives developers greater control over LLM-assisted code writing. To this end, we propose Code Semantic Zooming (CodeZoom), a novel approach based on pseudocode that allows developers to iteratively explore, understand, and refine code across multiple layers of semantic abstraction. In a within-subjects user study (n=26), our method matches a state-of-the-art coding agent, Claude Code, on usability while producing a large effect on code comprehension: over 90% of participants reported feeling more in control of design decisions when using CodeZoom compared to using Claude Code.