In-call experience enhancement for assistant systems

One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

• establish a video call between a plurality of client systems, wherein access to an assistant system is persistently maintained during the video call;
• receive, from a first client system of the plurality of client systems, a request by a first user to be performed by the assistant system during the video call, wherein the request references one or more second users associated with the plurality of client systems;
• determine an intent of the request;
• analyze, by a context engine of the assistant system, images of a scene of the video call to identify the one or more second users within the scene;
• determine respective user identifiers of the one or more second users identified within the scene;
• instruct the assistant system to execute the request based on the determined intent and user identifiers;
• and
• send, to one more of the plurality of client systems, a response to the request while maintaining the video call between the plurality of client systems.

A system comprising one or more processors and one or more computer-readable non-transitory storage media coupled to one or more of the processors and comprising instructions operable, when executed by one or more of the processors, to cause the system to:

• establish a video call between a plurality of client systems, wherein access to an assistant system is persistently maintained during the video call;
• receive, from a first client system of the plurality of client systems, a request by a first user to be performed by the assistant system during the video call, wherein the request references one or more second users associated with the plurality of client systems;
• determine an intent of the request;
• analyze, by a context engine of the assistant system, images of a scene of the video call to identify the one or more second users within the scene;
• determine respective user identifiers of the one or more second users identified within the scene;
• instruct the assistant system to execute the request based on the determined intent and user identifiers;
• and
• send, to one more of the plurality of client systems, a response to the request while maintaining the video call between the plurality of client systems.