Microsoft patents system that auto-sends follow-ups to get tasks done
Microsoft describes a system that helps people manage work by automatically sending follow-up messages to employees or contractors. It uses machine learning to craft these messages and learns from whether the task gets completed to improve future requests.
In the filing’s own words
Aspects of the present disclosure relate to assisting a requestor to manage activities a cross a plurality of diverse actors. In examples, a system is provided that includes at least one processor, and memory storing instructions that, when executed by the at least one processor, causes the system to perform a set of operations. The set of operations include receiving a request for a task to be completed, from the requestor, receiving actor context data, recording an assignment of the task to an actor, based on the actor context data, generating a communication to request that the actor complete the assigned task, and sending the communication to the actor.
What exactly they claim (claim 1)
1. A method for assisting a requestor to manage activities across a plurality of actors, the method comprising: receiving an indication of a pending task that is assigned to an actor; determining that a follow-up communication, from a requestor, is appropriate; generating, using a machine learning model, message content for the task to follow-up with the actor, wherein the machine learning model has previously been trained to generate communication based on a training message content and a training task acceptance and completion; sending, to a computing device of the actor, the follow-up communication comprising the generated message content; receiving, from the computing device of the actor, a feedback indication corresponding to the follow-up communication; updating, based on modified message content of the generated message content according to the feedback indication, the machine learning model as reinforcement learning, thereby increasing a probability that future message content generated for the actor to follow-up regarding a given task by the machine learning model trained based on the modified message content results in completion, by the actor, of the given task; determining whether the feedback indicates that the actor will complete the assigned task; and in response to determining the feedback indication indicates that the actor will not complete the assigned task, recording a re-assignment of the task.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- AUTO-MANAGING REQUESTOR COMMUNICATIONS TO ACCOMMODATE PENDING ACTIVITIES OF DIVERSE ACTORS
- Publication number
- US20260289445A1
- Application number
- 19685582
- Filed
- May 22, 2026
- Published
- Sep 24, 2026
- Inventors
- 1
- Claims
- 20
Classified under
G06Q 10/063114 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.