Copilot answers those questions and helps users by citing the code sections it pulls information from, so they can review the actual code themselves.<\/p>\n

\u201cWe\u2019ve always leaned heavily into education and helping users understand the underlying context,\u201d Reynolds said. UpCodes plans to add more explanatory content to Copilot that will help users further understand code, beyond publicly available content.<\/p>\n

Notably, laws hosted by UpCodes have contributed to the top 0.01% of training data for AIs like ChatGPT and Google Bard. Building professionals often turn to those tools to get their questions answered, Reynolds said. They were trained on the C4 dataset from Common Crawl, which pulled directly from UpCodes\u2019 website (basic access to its code database is free).<\/p>\n

\u201cThere\u2019s an increase in focus on data quality for training LLMs,\u201d he explained. \u201cUpCodes has an extensive library of high-quality construction law, which is ideal for an LLM to train on as we\u2019re the only source online for many of these laws. It may have been less of a conscious decision to include building laws and more a result of their algorithm identifying quality data relevant across a broad range of topics, including construction laws.\u201d<\/p>\n

But Reynolds added that the crawl only includes snapshots in time, so their models are likely operating from out-of-date code since regulations are constantly changing.<\/p>\n

This gives Copilot an advantage, since it draws on UpCodes\u2019 constantly updated database. On top of that, codes also vary widely from jurisdiction to jurisdiction. Reynolds said UpCodes spent years building the infrastructure to keep its code database up to date.<\/p>\n

One of the most important challenges facing any AI project is limiting hallucinations. Reynolds said one of the biggest steps UpCodes has taken is \u201cfencing\u201d Copilot into applicable codes for a project. This means it parses over five million code sections, including 160,000 amendments, based on a user\u2019s location and permit year. It also collects additional data like type of building to make sure Copilot only uses relevant codes.<\/p>\n

Copilot has an internal system that fine-tunes responses specific to construction law, and passes each query through multiple layers of analysis to better understand and parse questions. It focuses on jurisdiction-specific codes, to account for variances and because building professionals often have to be familiar with several jurisdictions at once. Once a question is asked, Copilot gives answers with context and direct references so users can see how it arrived at an answer.<\/p>\n

Users who are subscribed to an UpCodes paid plan get to ask Copilot three questions. If they want unlimited access, they can upgrade to UpCodes Professional or add it to their Enterprise plan.<\/p>\n

UpCodes\u2019 Series A will be used to hire for its engineering department, as well as every department that contributes to Copilot. It plans to expand its code library and resources so Copilot can produce more sophisticated answers and add new features, like project management, Reynolds said.<\/p>\n

The startup\u2019s team has known Building Ventures since it was founded. \u201cWe thought they\u2019d be the perfect partner for our Series A,\u201d he added, explaining that the firm is made up of former operators in the construction industry, including former founders. Its portfolio and LP base serve as a valuable resource for guidance when UpCodes needs to validate ideas.<\/p>\n

\u201cThe construction industry can be opaque, a world unto itself, so having investors and partners steeped in it for decades is helpful,\u201d Reynolds said.<\/p>\n

In a statement about Building Ventures\u2019 investment into UpCodes, partner Allen Preger said, \u201cBy unifying and maintaining all building codes in an AI-powered platform, UpCodes is transforming code compliance for the Built Environment. We are thrilled to be leading their Series A investment.\u201d<\/p>\n<\/p><\/div>\n

<\/br><\/br><\/br><\/p>\n