Microsoft Technology Licensing, LLC

Susan Marie Grimshaw

Poonam Ganesh Hattangady

Michael Ivan Borysenko

Caleb Whitmore

Ashok Kuppusamy

Amund Kronen Johansen

Dag Steinnes Eidesen

Scott M Stiles

Michael Francis Palermiti, Ii

Krister Mikalsen

Amy Harilal Rambhia

Tashfeen Ahmed

Ravi Teja Koganti

Systems and methods for using a generative artificial intelligence (AI) model to generate a suggested draft reply to a selected message. A message generation system and method are described that use inferred context to improve the suggested draft reply message for the user. Various message data and additional context are obtained and included in a prompt provided to the AI model to improve suggested content. In some examples, the message data and additional context include a message thread history and previously sent messages, profile information of the sender and recipient(s) of the selected message, known relationship information between the sender and the user, etc. For instance, the user's preferred communication style and talking points can be inferred based on the profile data, relationship data, and the user's past communications with similar participants and used to tailor the suggested draft reply to the user.

Leveraging inferred context to improve suggested messages

Systems and methods for using a generative artificial intelligence (AI) model to generate a suggested draft reply to a selected message. A message generation system and method are described that use guardrails that prevent unnecessary AI model processing and accidental sending of an AI model-generated draft. In some examples, draft reply-generation is limited to a subset of messages (e.g., focused, non-confidential) and triggering of the draft reply generation is performed only after user interaction criteria are satisfied. In some examples, a confirmation message is presented when the draft reply is attempted to be sent with no changes or quickly after the draft is generated. For instance, the guardrails limit the number of times the AI model is invoked to generate suggested replies and further prevents users from accidentally sending drafts generated from the AI model.

Guardrails for efficient processing and error prevention in generating suggested messages

Systems and methods for using a generative artificial intelligence (AI) model using a multi-turn process to generate a suggested draft reply to a selected message. A first turn of the multi-turn process uses a shorter prompt including at least a portion of the body of the selected message and that requests multiple draft replies from the AI model. The resulting AI-generated draft replies are shortened, summarized, and/or otherwise converted into a plurality of shortened summaries that are presented as reply options to a user. Upon selecting a shortened summary, a more robust prompt is generated in a second turn with the AI model with the selected reply option to generate a more complex suggested draft reply to the selected message. Additionally, various customization options are provided, which when selected, reframe a query presented to the AI model to generate a more relevant and personalized response.

Efficient multi-turn generative AI model suggested message generation

A system and method for surfacing content relevant is described. The system computes a rank score for each item of a plurality of items that are accessible from a user of an enterprise application. The system identifies a set of relevant items from the plurality of items based on the rank score for each item of the plurality of items. The system surfaces the set of relevant items within a context of a communication application of the user without receiving, from the user, a query for any of the items in the set of relevant items.

Preemptively surfacing relevant content within email

Growing community of inventors

Kirkland, WA, United States of America

Susan Marie Grimshaw