Leaf Automation: Next-Generation AI-Enhanced CAD Plugins

Leaf Automation is a participant in Cohort 3 of Transform, a data science and AI startup accelerator powered by Deep Tech Ventures at the University of Chicago’s Polsky Center for Entrepreneurship and Innovation and Innovation in collaboration with the Data Science Institute.


Leaf Automation develops next-generation AI-enhanced CAD plugins that expedite and optimize the design of commercial electrical and mechanical systems.

“The construction rate of renewable energy infrastructure is being hampered by the tedious CAD drafting that makes up approximately 40% of an engineer’s time,” said Leaf CEO and Cofounder Evan Haug. To enable engineers to focus their time on “more high-impact work,” the startup is embedding AI-automated design generation into CAD platforms.

The Leaf team met during undergrad at Case Western Reserve University (CWRU) in 2020 when the idea was accepted into CWRU’s Great Lakes Energy Institute undergraduate cleantech incubator.

“At Leaf, we’re pioneering the combination of classical AI, reinforcement learning techniques, and rules-based guardrails to generate optimized and code-compliant engineering design schematics in just seconds,” said Haug, who has a background in electrical and solar engineering.

“By using reinforcement learning, we avoid the need to procure the thousands of existing engineering drawings required by the companies in the space that use generative AI,” he explained. This enables Leaf’s models to attain higher degrees of optimization than models trained using human-generated design data.

“Leveraging artificial intelligence in construction engineering accelerates design and implementation, helping overcome the systemic inefficiencies found in current design and development workflows,” added Haug.

The team is confident that its reinforcement learning system is scalable, which will enable them to expand their services across a wide range of engineering disciplines, including plumbing, heating, ventilation, air conditioning (HVAC), structural, and civil engineering, among others. And the feedback from more than 50 potential customers in the construction engineering industry has been positive thus far. “[They are] excited at the idea of leveraging AI from within the CAD platforms they currently use to do their engineering design work,” said Haug.

Additionally, Leaf has partnered with 10 companies to beta test its solar engineering automation tool for AutoCAD, Branch, which is slated for release in May of this year. Haug said the plan is to develop a suite of engineering automation applications across engineering disciplines.

“As the years go by,” he explained, “we hope to spin out a new automation application each year, deploying it at first as a stand-alone CAD plugin offering, but then looking to exit each application to an existing player in that engineering automation space as a licensure or sale of the IP, then using those funds to fuel R&D into future and more ambitious automation applications.”

As part of the Transform accelerator, Haug said they are looking forward to working with the Polsky Center’s resources to iterate Branch, refine their commercialization plan, engage with UChicago AI/ML resources – including faculty and students – and connect with construction engineering leaders to support ongoing work and future products.

// Powered by the Polsky Center’s Deep Tech Ventures, Transform provides full-spectrum support for the startups accepted into the accelerator, including access to business and technical training, industry mentorship, venture capital connections, and funding opportunities.

This site uses cookies and other tracking technologies to assist with navigation and your ability to provide feedback, analyze your use of products and services, assist with our promotional and marketing efforts.

Accept