Artificial intelligence is already changing construction, but one of the most adopted uses of the technology comes from Document Crunch, an Atlanta-area startup now automating one of the most previously time-consuming tasks in the construction process—lawyers and project managers reviewing hundreds of pages of contract documents to find language that boosts risk to a contractor or client. Document Crunch co-founder and CEO Josh Levy did that work as an attorney for contractors JE Dunn and Wood before linking up with tech entrepreneur and CTO Trent Miskelly to apply a large language model to this repetitive task.

“It’s becoming more and more apparent to me that the brand, and the way that you go to market, and the empathy, which is in our DNA for construction, is serving to be a differentiator,” Levy says. “This incredible amount of investment in technology, the core technology being infused with the subject matter, is important.”

De-risking Project Documents

Photo courtesy of Document Crunch

Document Crunch’s machine-learning platform uses construction contract-specific models and generative AI frontier models from OpenAI and Anthropic, as well as a purpose-built retrieval architecture that is designed to deliver answers to complex contractor questions. It also has a chat feature to enable users—often in-house counsels—to ask questions about specific projects. Natural language AIs are becoming increasingly popular to let users essentially talk to the AI. The company’s platform has been adopted by ENR Top 500 contractors realizing that while contracts can’t be standardized, the way contractors analyze them can be.

“We’re seeing things before most others [do] and the crazy thing is, every time that I get pulled into a discussion with an ENR company, I’m sitting in a boardroom with the CIO, the CEO and people who are basically making decisions for the company, and they’re diving deeply into how they are going to change the [firm’s] trajectory, leveraging these new products and new technologies,” Miskelly says.

Applying the knowledge of a database full of construction expertise from Levy and other construction legal experts is not just a timesaver for in-house counsels and other attorneys in assessing contractor risk, it also frees them for more important work.

“This [document review] is a repetitive process, in some respects, in asking yes or no, but there is a little bit of art to it,” says Jeff Brannen, chief legal officer in Texas and Arizona for contractor Balfour Beatty. “To understand and know that and have the vision for it and say that computer software is at a place where it now can do this, can help us.”

Document Crunch raised $21.5 million in a Series B funding round last October led by Titanium Ventures, with participation from Nemetschek AG. Levy said the company plans to use the funding to expand its various document review AI agents into a full platform play that could even go beyond construction documents. The company launched last July its Construction Contract Checklist and Project Playbook—tools that are specifically geared for onsite personnel such as site crew managers, project managers and project engineers.

Yash Patel, general partner at Titanium Ventures who joined the Document Crunch board of directors with the new funding round, said that developing products to help customers deal with risk profile at any stage of a project is a focus for 2025.