Abstract: 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.

Abstract: An electronic message computing system tracks new activity items that reflect activities that have not yet been seen by the user. A. generative artificial intelligence (AI) model generates a digest summary that is provided to the user the next time the user accesses the electronic message system. The digest summary summarizes new activity. The generative AI model also generates importance summaries that summarize the importance of a particular activity to the user, and content summaries that summarize the content of an activity item (such as an electronic mail message). The electronic messaging system also assigns a priority to each new activity item and provides the summaries, along with a priority, to a client computing system. The client computing system conducts a user experience, navigating the user through the new activity items, based upon the priority assigned by the electronic message computing system.

Abstract: 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.

Abstract: 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.

Abstract: 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 optimize input that is provided to the AI model so that it provides the most relevant information. In some examples, input prompts to the AI model are limited in size and latency can be impacted based on the size of the input provided to the AI model. Thus, the method and system identify, include, and format relevant information in an input prompt. The prompt reduces latency by the generative AI model in processing the prompt and may also lead to more relevant results produced by the generative AI model.

Abstract: 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.

Abstract: A method for improving visibility of contents displayed on a GUI by providing a dark viewing mode that preserves user-generated formatting and/or style contained in the contents is disclosed. The method includes receiving content for displaying on the display, parsing the received content into one or more objects, based on at least a formatting characteristic of the objects, and comparing for each object a first color characteristic of the object with a second color characteristic to determine if a contrast between the first color characteristic and the second color characteristic satisfies a threshold requirement. Upon determining that the threshold requirement is not satisfied, the method includes adjusting the first characteristic, and displaying the objects with the adjusted first characteristic.

Abstract: A method for improving visibility of contents displayed on a GUI by providing a dark viewing mode that preserves user-generated formatting and/or style contained in the contents is disclosed. The method includes receiving content for displaying on the display, parsing the received content into one or more objects, based on at least a formatting characteristic of the objects, and comparing for each object a first color characteristic of the object with a second color characteristic to determine if a contrast between the first color characteristic and the second color characteristic satisfies a threshold requirement. Upon determining that the threshold requirement is not satisfied, the method includes adjusting the first characteristic, and displaying the objects with the adjusted first characteristic.