Automated Document Redaction Service 

Professional services staff across the University spend vast amounts of time and money on manually redacting sensitive information from documents every year – resource that could be better spent on tasks that really require human intervention.

Delivery

Identifying the potential for massive resource savings, we developed a web application that allows users to upload Word, PDF, or Excel files before using a Natural Language Processing tool to automatically redact selected types of Personally Identifiable Information from them.

Outcome

This tool is currently in the final stages of development, prior to entering its pilot phase. Initial conversations suggest huge efficiencies for our professional services staff, and the tool reveals the wider uses of AI, beyond large language models, for meeting University need.