Copilot - Security and Availability
- What's the current status of Procore Copilot?
- How can my company participate in the Open Beta program?
- Which third party generative AI technologies does Procore Copilot utilize?
- Does Microsoft Azure OpenAI use customer data to train their AI models?
- How do other models besides the LLM used by Procore Copilot utilize customer data?
- How does Procore Copilot follow permissions in our Procore instance?
What’s the current status of Procore Copilot?
Procore Copilot is gradually becoming generally available to customers in North America who license the required tool set. These customers will need to enable Copilot, activate it on projects, and assign permissions to users through permissions templates to access the feature. Additional beta features are being made available gradually and can be enabled on an opt-in basis.
For international customers who license the required tool set, two Copilot beta experiences will gradually become available. The core beta experience offers access to Copilot in Procore's Global Search. The second beta offers additional features. You can choose to opt into either or both beta experiences if your company licenses the required tool set. It's important to note that Copilot currently only answers questions in English at this time, and uses United States English construction terminology.
See Enable Copilot to learn more.
How can my company participate in the Open beta program?
To learn if the beta is available to your company, visit your Company Admin tool and look for the option to sign the beta agreement. Then, follow the steps in Enable Copilot to start participating.
Which third party generative AI technologies does Procore Copilot utilize?
Procore Copilot currently utilizes Microsoft’s Azure OpenAI Service. Microsoft Azure OpenAI is a listed Procore subprocessor.
Does Microsoft Azure OpenAI use customer data to train their AI models?
No, customer data is not used to train, retrain, fine-tune, or improve Microsoft Azure OpenAI or any other Microsoft products or services, and is not provided to OpenAI. Additionally, the indexed data sent to the LLM is not persistently stored by Microsoft, only the prompts and responses are stored securely for up to 30 days by Microsoft to detect and mitigate abuse. You can learn more about how Microsoft uses prompts and data by reviewing Microsoft's Data Privacy and Security for Azure OpenAI page.
How do other AI models besides the LLM, used by Procore Copilot utilize customer data?
In addition to Azure OpenAI, Procore Copilot also utilizes internal AI models that help it better understand user inputs and prioritize relevant search results, improving the overall user experience. These internal models may utilize data collected from customer inputs and outputs to help improve Copilot accuracy. Procore never shares or discloses a customer’s data with another customer, and that includes customer prompts to Procore Copilot and Procore Copilot’s responses. Due to the nature of machine learning and the technology powering Procore Copilot, output may not be unique, and Procore Copilot may generate the same or similar output for third parties.
How does Procore Copilot follow permissions in our Procore instance?
We've designed Copilot to strictly adhere to existing data permissions set in Procore. Copilot’s responses (output) are based only on data that the user can access based on these set permissions. As an example, if a user does not have access to the RFIs tool at all (based on the settings in the permissions tool), and they ask a question related to a specific RFI, then they would not get any answer based on RFIs.