Building code compliance is one of the most critical and time-consuming aspects of architectural practice. With the International Building Code alone exceeding 700 pages and projects subject to multiple overlapping codes, zoning ordinances, and accessibility standards, the potential for errors and omissions has never been greater. This comprehensive course introduces architects to the transformative world of artificial intelligence and machine learning as applied to code compliance review. Whether you are a principal architect, project manager, code consultant, or design professional, this course will equip you with the foundational knowledge needed to understand, evaluate, and implement AI-driven compliance solutions in your practice. By completing this course, you will gain practical insights into how AI technologies can accelerate code research, automate routine compliance checks, and provide early design feedback when changes are least costly. Studies of AI compliance tools have demonstrated reductions of 30 to 50 percent in time spent on code review tasks, while also improving the consistency and accuracy of compliance analysis. Pilot programs in cities including San Jose and Las Vegas have shown that AI can identify 60 to 80 percent of code issues that would otherwise be caught during building department plan review. This course bridges the gap between cutting-edge technology and practical application, preparing you to leverage AI tools while maintaining the professional judgment that remains essential for complex code interpretations.

Learning Objectives:

• Describe the traditional code compliance review process and identify its limitations, including time requirements, inconsistency in review, and knowledge management challenges.
• Define artificial intelligence, natural language processing, large language models, and computer vision, and explain how these technologies apply to code compliance applications.
• Identify the major building codes and regulatory frameworks, including the IBC, IFC, accessibility standards, and energy codes, and explain the challenges they present for automated interpretation.
• Explain how natural language processing enables semantic search, question answering, requirement extraction, and chain-of-thought reasoning for code interpretation.
• Describe how computer vision technologies extract information from architectural drawings, including element recognition, dimension extraction, and spatial analysis.
• Distinguish between rule-based systems, knowledge graphs, and machine learning approaches for compliance checking, and identify the advantages of hybrid approaches.
• Explain the capabilities and limitations of automated plan review systems, including workflow integration, coverage, accuracy rates, and building department adoption.
• Describe BIM-based compliance checking approaches, including model data access, rule checking platforms, and model quality requirements.
• Evaluate commercial AI compliance platforms and software options, and understand integration requirements with design workflows and quality control processes.
• Identify professional responsibility and ethical considerations for AI deployment, including professional liability, accuracy limitations, data privacy, and transparency requirements.