CIAO - Code In Architecture Out - Automated Software Architecture Documentation with Large Language Models

2026-04-09

AI Summary

This work addresses the limitation of existing large language model (LLM) approaches, which are often confined to local code snippets and struggle to produce system-level architectural documentation. The authors propose the CIAO pipeline, which uniquely integrates standardized architecture frameworks—including ISO/IEC/IEEE 42010, SEI Views & Beyond, and the C4 model—with LLMs through structured prompt engineering and automated parsing of GitHub repositories to enable end-to-end, low-cost generation of system architecture documentation. In evaluations involving 22 developers, the generated documents were consistently rated as valuable, comprehensible, and largely accurate, with the entire process taking only minutes. Although improvements are still needed in diagram quality and deployment views, the approach effectively bridges the gap between source code and holistic architectural understanding.

Abstract

Software architecture documentation is essential for system comprehension, yet it is often unavailable or incomplete. While recent LLM-based techniques can generate documentation from code, they typically address local artifacts rather than producing coherent, system-level architectural descriptions. This paper presents a structured process for automatically generating system-level architectural documentation directly from GitHub repositories using Large Language Models. The process, called CIAO (Code In Architecture Out), defines an LLM-based workflow that takes a repository as input and produces system-level architectural documentation following a template derived from ISO/IEC/IEEE 42010, SEI Views \& Beyond, and the C4 model. The resulting documentation can be directly added to the target repository. We evaluated the process through a study with 22 developers, each reviewing the documentation generated for a repository they had contributed to. The evaluation shows that developers generally perceive the produced documentation as valuable, comprehensible, and broadly accurate with respect to the source code, while also highlighting limitations in diagram quality, high-level context modeling, and deployment views. We also assessed the operational cost of the process, finding that generating a complete architectural document requires only a few minutes and is inexpensive to run. Overall, the results indicate that a structured, standards-oriented approach can effectively guide LLMs in producing system-level architectural documentation that is both usable and cost-effective.

Problem

• software architecture documentation
• system-level description
• large language models
• automated documentation
• GitHub repositories

Innovation

• Large Language Models
• Software Architecture Documentation
• System-level Architecture
• Automated Documentation
• CIAO