Real-time feedback for message composition in a communication platform

1. A method comprising:

receiving, by one or more servers of a group-based communication platform and from a first client of a user of a plurality of users associated with the group-based communication platform, a first request to generate a new message internal to the group-based communication platform;

determining, by the one or more servers of the group-based communication platform, an intended recipient of the new message;

obtaining, by the one or more servers of the group-based communication platform, a corpus of historical messages exchanged via the group-based communication platform associated with one or more users of the plurality of users, wherein a historical message of the corpus of historical messages is associated with a recipient, a channel with which the recipient is associated, and an organization with which the recipient is associated;

training, by the one or more servers of the group-based communication platform and based at least in part on the corpus of historical messages, a model to output recommendations for new messages;

based at least in part on output of the model and the intended recipient, generating, by the one or more servers of the group-based communication platform, a recommendation associated with an aspect of the new message to optimize the new message for the intended recipient;

causing, by the one or more servers of the group-based communication platform, a user interface element associated with the recommendation to be presented via a group-based communication user interface of the group-based communication platform in association with the new message;

receiving, by the one or more servers of the group-based communication platform, a selection of the user interface element to update the new message to an updated new message in accordance with the recommendation;

receiving, by the one or more servers of the group-based communication platform and from the first client of the user via the group-based communication user interface, a second request to send the updated new message to the intended recipient; and

sending, by the one or more servers of the group-based communication platform and to a second client associated with the intended recipient, the updated new message.

2. The method of claim 1 , wherein the corpus of historical messages comprises one or more prior messages exchanged between the user and another user on the group-based communication platform.

3. The method of claim 1 , wherein the recommendation is generated further based at least in part on a characteristic of the intended recipient.

4. The method of claim 1 , further comprising:

identifying, by the one or more servers of the group-based communication platform and in association with the new message, a reference to an object or a topic, wherein generating the recommendation is further based at least in part on determining whether at least one of the object or the topic has been referenced or is being referenced by at least one other user of the group-based communication platform.

5. The method of claim 1 , wherein the new message is associated with a virtual space, and wherein the recommendation is generated further based at least in part on data associated with the virtual space.

6. The method of claim 1 , wherein the new message is associated with a type, and wherein the recommendation is generated further based at least in part on the type.

7. A system comprising:

one or more processors; and

one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the system to perform operations comprising:

receiving, by one or more servers of a group-based communication platform and from a first client of a user of a plurality of users associated with a group-based communication platform, a request to generate a new message internal to the group-based communication platform;

determining, by the one or more servers of the group-based communication platform, an intended recipient of the new message;

obtaining, by the one or more servers of the group-based communication platform, a corpus of historical messages exchanged via the group-based communication platform associated with one or more users of the plurality of users, wherein a historical message of the corpus of historical messages is associated with a recipient, a channel with which the recipient is associated, and an organization with which the recipient is associated;

training, by the one or more servers of the group-based communication platform and based at least in part on the corpus of historical messages, a model to output recommendations for new messages;

based at least in part on output of the model and the intended recipient, generating, by the one or more servers of the group-based communication platform, a recommendation associated with an aspect of the new message to optimize the new message for the intended recipient;

causing, by the one or more servers of the group-based communication platform, a user interface element associated with the recommendation to be presented via a group-based communication user interface of the group-based communication platform in association with the new message;

receiving, by the one or more servers of the group-based communication platform, a selection of the user interface element to update the new message to an updated new message in accordance with the recommendation;

receiving, by the one or more servers of the group-based communication platform and from the first client of the user via the group-based communication user interface, a second request to send the updated new message to the intended recipient; and

sending, by the one or more servers of the group-based communication platform and to a second client associated with the intended recipient, the updated new message.

8. The system of claim 7 , wherein the corpus of historical messages comprises one or more prior messages exchanged between the user and another user on the group-based communication platform.

9. The system of claim 7 , wherein the recommendation is generated further based at least in part on a characteristic of the intended recipient.

10. The system of claim 7 , wherein the new message is associated with a virtual space, and wherein the recommendation is generated further based at least in part on data associated with the virtual space.

11. The system of claim 7 , wherein the new message is associated with a type, and wherein the recommendation is generated further based at least in part on the type.

12. The system of claim 7 , the operations further comprising:

identifying, by the one or more servers of the group-based communication platform and in association with the new message, a reference to an object, wherein generating the recommendation is further based at least in part on determining whether the object has been referenced or is being referenced by at least one other user of the group-based communication platform.

13. The system of claim 7 , the operations further comprising:

identifying, by the one or more servers of the group-based communication platform and in association with the new message, a reference to a topic, wherein generating the recommendation is further based at least in part on determining whether the topic has been referenced or is being referenced by at least one other user of the group-based communication platform.

14. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

receiving, by one or more servers of a group-based communication platform and from a first client of a user of a plurality of users associated with a group-based communication platform, a first request to generate a new message internal to the group-based communication platform;

determining, by the one or more servers of the group-based communication platform, an intended recipient of the new message;

obtaining, by the one or more servers of the group-based communication platform, a corpus of historical messages exchanged via the group-based communication platform associated with one or more users of the plurality of users, wherein a historical message of the corpus of historical messages is associated with a recipient, a channel with which the recipient is associated, and an organization with which the recipient is associated;

training, by the one or more servers of the group-based communication platform and based at least in part on the corpus of historical messages, a model to output recommendations for new messages;

based at least in part on output of the model and the intended recipient, generating, by the one or more servers of the group-based communication platform, a recommendation associated with an aspect of the new message to optimize the new message for the intended recipient;

causing, by the one or more servers of the group-based communication platform, a user interface element associated with the recommendation to be presented via a group-based communication user interface of the group-based communication platform in association with the new message;

receiving, by the one or more servers of the group-based communication platform, a selection of the user interface element to update the new message to an updated new message in accordance with the recommendation;

receiving, by the one or more servers of the group-based communication platform and from the first client of the user via the group-based communication user interface, a second request to send the updated new message to the intended recipient; and

sending, by the one or more servers of the group-based communication platform and to a second client associated with the intended recipient, the updated new message.

15. The one or more non-transitory computer-readable media of claim 14 , wherein the corpus of historical messages comprises one or more prior messages exchanged between the user and another user on the group-based communication platform.

16. The one or more non-transitory computer-readable media of claim 14 , wherein the recommendation is generated further based at least in part on a characteristic of the intended recipient.

17. The one or more non-transitory computer-readable media of claim 14 , wherein the new message is associated with a virtual space, and wherein the recommendation is generated further based at least in part on data associated with the virtual space.

18. The one or more non-transitory computer-readable media of claim 14 , wherein the new message is associated with a type, and wherein the recommendation is generated further based at least in part on the type.

19. The one or more non-transitory computer-readable media of claim 14 , the operations further comprising:

identifying, by the one or more servers of the group-based communication platform and in association with the new message, a reference to an object or a topic, wherein generating the recommendation is further based at least in part on determining whether at least one of the object or the topic has been referenced or is being referenced by at least one other user of the group-based communication platform.