Skip to content

Patent Quality Artificial Intelligence (PQAI)

Open Source AI for Trusted Patent Search

The PQAI initiative is using the power of Open Source to address the problem of patent novelty by creating a transparent, trusted platform to promote high quality innovations.

Creating a commonly recognized, open, and trusted patent search platform will empower all inventors, enable patent attorneys to operate more efficiently, and allow patent offices to adopt the latest technology platforms quickly.

PQAI is an initiative inspired by AT&T to improve patent quality and drive innovation within AT&T, including all inventors like women, minorities, and underrepresented communities.



Make the patent process more transparent for all involved and significantly grow the number of successful inventors – thus accelerating the pace of innovation and simultaneously improving the overall quality of patents. 

Address the fundamental problem that no universal platform is available for the public to easily test and understand the novelty of their inventions (i.e., perform a high-quality prior art search and quickly assess the novelty of their invention).


Create an Open Source patent search engine capable of performing US 102 (obviousness) and 103 (anticipation) novelty searches to better predict the likelihood of obtaining a patent. 

As an Open Source platform, the development community and industry participants will drive the improvements to the platform, which is similar to other Open Source initiatives. 

Additionally, the open nature of the platform will provide transparency and trust among inventors, attorneys, enterprises, and the general public. 

Broad acceptance from the IP community will motivate patent examiners to adopt the use of this platform, hopefully eliminating confusion around patent office examination processes.


This initiative is focused on improving the patent process by enabling better prior art search and analysis. The automating of patent awards or the replacement of any IP expert roles is NOT within the scope of PQAI.

  • Legal Advisory Team to assist in the development of:

    • Benchmarking criteria (i.e., how can we prove to the public, patent attorneys, enterprises, and patent offices that PQAI search results are accurate and high quality)

    • Methodology for identifying 103 prior art  

  • Technical Advisory Team for the Search Engine and Assessor architecture (i.e., ensure the architecture will provide a solid foundation for the Open Source community)  

  • Users to provide feedback on the interface

  • Funding to support the continued development of PQAI

"No universal platform exists for the public to easily test and understand the novelty of their inventions. New tools are needed with broad trust from the IP community."

Sam ZellnerAT&T (Retired), Patent Quality Artificial Intelligence (PQAI) Chair