Microsoft patents AI filter that blocks medical queries against clinical guidelines
Microsoft describes a system that sits between a user and a generative AI to monitor conversations. It checks if user inputs follow clinical practice guidelines before allowing the AI to process them, replacing non-compliant questions with safer alternatives.
In the filing’s own words
A computer-implemented method, computer program product and computing system for: enabling a generative AI system to effectuate an analysis protocol; enabling a user to utilize the generative AI system during an interactive session concerning the analysis protocol; receiving content during the interactive session, thus defining received content; and determining whether the received content is relevant with respect to the analysis protocol.
What exactly they claim (claim 1)
1. A method comprising: monitoring, by a model safeguarding processor, an interactive session between a user and a generative Artificial Intelligence (AI) system to ensure that content exchanged between the user and the generative AI system complies with guidelines for clinical practice, the model safeguarding processor being independent from the generative AI system, wherein monitoring the interactive session includes: receiving, by the model safeguarding processor, an initial inquiry from the user that includes user-generated content for processing by the generative AI system during the interactive session; processing, by the model safeguarding processor, the user-generated content based on the guidelines for clinical practice to determine whether to transmit the initial inquiry to the generative AI system; sending, by the model safeguarding processor, a request to the user upon determining not to transmit the initial inquiry to the generative AI system; receiving a replacement inquiry in response to the request; and transmitting, by the model safeguarding processor, the replacement inquiry to the generative AI system in lieu of the initial inquiry.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- SYSTEM AND METHOD FOR SAFEGUARDING MODELS
- Publication number
- US20260300484A1
- Application number
- 19700171
- Filed
- Jun 5, 2026
- Published
- Oct 1, 2026
- Inventors
- 5
- Claims
- 20
Classified under
G06F 21/554 Physics & computingG06N 3/0475 Physics & computingG06F 2221/034 Physics & computingMore from Microsoft in AI & software
- Microsoft patents method to check AI answers against verified facts Oct 20, 2026
- Microsoft patents AI that presents PowerPoint slides for you Sep 3, 2026
- Microsoft patents method to check if LLM answers are based on real data Sep 10, 2026
- Microsoft patents system to blend multiple AI agents into one chat Oct 1, 2026
- Microsoft patents system that answers questions using your screen history Oct 15, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.