AI Coworkers are AI-powered systems that can do various tasks for you.
You'll provide your AI Coworker with responsibilities it should perform based on things you'd like it to monitor, such as your email, GitHub, or meetings you're attending or invited to.
AI Coworkers belong to the Organization they're created in.
Each AI Coworker has individual permissions that control who in your Organization can interact with them.
Each AI Coworker may be set to be available to specific users or anyone in the organization.
To change the AI Coworker's visibility, add, or remove specific users, click on "Share" in the header while viewing the AI Coworker.
Keep in mind that anyone with permission to view the AI Coworker can see, add, and remove any of the Responsibilities and Monitors that have been created for it, as well as interact with the AI Coworker via chat.
Connections are the systems that your AI Coworker can access to perform work. You grant the AI Coworker access to a Connection, just like you may grant a human employee access to software they need to do their job.
Monitors are the systems that your AI Coworker can monitor for changes. You grant the AI Coworker access to a Monitor, and as data changes in that external system, the AI Coworker will be able to see those changes and act on them through recurring Responsibilities.
After you create a new AI Coworker, you will be added to a new chat room with the AI Coworker. You may ask the AI Coworker what work they can perform, and they will answer based on the Connections they have access to and the Responsibilities they have been given.
The Room will only be you and the AI Coworker to start, but you can add anyone else in your Organization by clicking "Share" in the Room.
Responsibilities define work that an AI Coworker should do.
They are made up of a trigger, which is the event that causes the work to happen, and a set of instructions that the AI Coworker should follow.
Explain when work should happen.
For example:
Explain what work should happen.
This is a free-form text field, so you can just write instructions without knowing anything about how they will be implemented. However, the more structure and opinion you give the better the AI Coworker will perform.
You'll be able to iterate on this later after you see how your AI Coworker performs.
For example:
Add any important details or contextual information here. This could include details about the trigger, the tasks, how this fits into the overall work you and your team is doing, and even encouragement for your AI Coworker.
The more the AI Coworker knows, the better it can perform. This is also a great way for you to capture the why behind what you're asking them to do.
AI Coworkers is a recently launched feature, and for now you can create unlimited coworkers. This may change in the future.