Action item generation based on multichannel context

A system comprising:

• a processor;
• and
• at least one memory device including instructions that are executable by the processor to cause the processor to:
• detect, at a workplace assistant client application on a client device configured for use with an integrated communication system, electronic content associated with relevant users of the integrated communication system;
• access a plurality of channels communicatively coupled to the workplace assistant client application and metadata describing the relevant users, the metadata configured to describe relationships, group memberships, and previous interactions;
• submit the electronic content, the metadata, and information from the plurality of channels to a predictive model to provide a multichannel context for the electronic content, the multichannel context based on the information, the metadata, collaboration data and past contexts for the relevant users;
• generate, from the relevant users, a who-is-looking list of remote users looking for a user of the client device, wherein the who-is-looking list is sorted by relevance based on the multichannel context provided by the predictive model;
• generate, using output of the predictive model, an action item based at least in part on the electronic content and the multichannel context of the electronic content;
• display the action item and the who-is-looking list using the workplace assistant client application;
• and
• display, responsive to input received from the user, a snippet of messages from at least one of the relevant users in the who-is-looking list as well as the electronic content associated with the snippet.

A non-transitory computer-readable medium comprising code that is executable by a processor for causing the processor to:

• detect, at a workplace assistant client application on a client device configured for use with an integrated communication system, electronic content associated with relevant users of the integrated communication system;
• access a plurality of channels communicatively coupled to the workplace assistant client application and metadata describing the relevant users, the metadata configured to describe relationships, group memberships, and previous interactions;
• submit the electronic content, the metadata, and information from the plurality of channels to a predictive model to provide a multichannel context for the electronic content, the multichannel context based on the information, the metadata, collaboration data and past contexts for the relevant users;
• generate, from the relevant users, a who-is-looking list of remote users looking for a user of the client device, wherein the who-is-looking list is sorted by relevance based on the multichannel context provided by the predictive model;
• generate, using output of the predictive model, an action item based at least in part on the electronic content and the multichannel context of the electronic content;
• display the action item and the who-is-looking list using the workplace assistant client application;
• and
• display, responsive to input received from the user, a snippet of messages from at least one of the relevant users in the who-is-looking list as well as the electronic content associated with the snippet.