This paper explores the application of large language models (LLMs) in design and manufacturing workflows. The research investigates the capabilities of LLMs in various tasks such as converting text prompts into designs, generating design spaces and variations, transforming designs into manufacturing instructions, evaluating design performance, and searching for designs based on performance metrics. The study identifies the current strengths and limitations of LLMs, suggesting areas for potential enhancements. It also examines the ethical implications and proposes strategies to mitigate risks associated with employing generative AI in design and manufacturing. The paper outlines the standard CAx workflow and identifies opportunities for automation or acceleration through generative AI methods. It dissects the workflow into five distinct phases, assessing the potential for efficiency and quality enhancements in each phase by integrating generative AI tools. The components under review include generating a design, constructing a design space and design variations, preparing and documenting designs for manufacturing, evaluating a design’s performance, and discovering high-performing designs within a given performance metric and design space. The study evaluates the ability of LLMs to create designs from natural language instructions, spanning various design contexts such as individual parts, hierarchical assemblies, and hybrid designs that integrate existing components. The LLM demonstrates proficiency in generating designs from high-level textual input, effectively handling a diverse range of representations and problem domains. For instance, the LLM successfully generates coherent and well-structured code in OpenJSCAD, complete with semantically meaningful variables and comments. It also shows skill in interpreting and completing underspecified prompts by inferring and supplying plausible values for missing parameters. The paper also explores the LLM's capacity to infer a parametric design space from a specific preexisting design provided by the user. The input designs for the LLM are provided in a text-based DSL such as OpenJSCAD, with varying degrees of semantic annotations and explanatory comments. Enriching LLM inputs with more semantic information noticeably enhances the quality of the resulting design space. For instance, including the name of the object being modeled in the design proves beneficial for generating a parametric design. The study further examines the LLM's ability to generate design for manufacturing (DfM), offering potential enhancements in the design and production of parts and assemblies. It serves as a repository of manufacturing expertise, leveraging its pattern recognition and language interpretation capabilities during the design and manufacturing phases. Additionally, LLMs' programming skills and text pattern analysis enable them to generate and modify design and manufacturing files. The paper also discusses the LLM's ability to evaluate a design's performance, considering aspects like mechanical performance, dynamic functionality, and geometric compliance. The evaluation can focus on a single criterion or multiple criteria to determine if the design meets specific requirements. Results of this assessment can range from a single number to a spectrum of outcomes. More complex evaluations involve comparing different designs for optimization or final production decisions. The study also explores the LLM's ability to perform inverse design, aiming to create designs that are as close to optimalThis paper explores the application of large language models (LLMs) in design and manufacturing workflows. The research investigates the capabilities of LLMs in various tasks such as converting text prompts into designs, generating design spaces and variations, transforming designs into manufacturing instructions, evaluating design performance, and searching for designs based on performance metrics. The study identifies the current strengths and limitations of LLMs, suggesting areas for potential enhancements. It also examines the ethical implications and proposes strategies to mitigate risks associated with employing generative AI in design and manufacturing. The paper outlines the standard CAx workflow and identifies opportunities for automation or acceleration through generative AI methods. It dissects the workflow into five distinct phases, assessing the potential for efficiency and quality enhancements in each phase by integrating generative AI tools. The components under review include generating a design, constructing a design space and design variations, preparing and documenting designs for manufacturing, evaluating a design’s performance, and discovering high-performing designs within a given performance metric and design space. The study evaluates the ability of LLMs to create designs from natural language instructions, spanning various design contexts such as individual parts, hierarchical assemblies, and hybrid designs that integrate existing components. The LLM demonstrates proficiency in generating designs from high-level textual input, effectively handling a diverse range of representations and problem domains. For instance, the LLM successfully generates coherent and well-structured code in OpenJSCAD, complete with semantically meaningful variables and comments. It also shows skill in interpreting and completing underspecified prompts by inferring and supplying plausible values for missing parameters. The paper also explores the LLM's capacity to infer a parametric design space from a specific preexisting design provided by the user. The input designs for the LLM are provided in a text-based DSL such as OpenJSCAD, with varying degrees of semantic annotations and explanatory comments. Enriching LLM inputs with more semantic information noticeably enhances the quality of the resulting design space. For instance, including the name of the object being modeled in the design proves beneficial for generating a parametric design. The study further examines the LLM's ability to generate design for manufacturing (DfM), offering potential enhancements in the design and production of parts and assemblies. It serves as a repository of manufacturing expertise, leveraging its pattern recognition and language interpretation capabilities during the design and manufacturing phases. Additionally, LLMs' programming skills and text pattern analysis enable them to generate and modify design and manufacturing files. The paper also discusses the LLM's ability to evaluate a design's performance, considering aspects like mechanical performance, dynamic functionality, and geometric compliance. The evaluation can focus on a single criterion or multiple criteria to determine if the design meets specific requirements. Results of this assessment can range from a single number to a spectrum of outcomes. More complex evaluations involve comparing different designs for optimization or final production decisions. The study also explores the LLM's ability to perform inverse design, aiming to create designs that are as close to optimal