Work with Center Agent
Put your organization’s Agent to work with clear goals, context, and responsibilities.
Center Agent is your organization’s AI agent. It helps coordinate people, agents, and work across Spaces and connected channels, using the goals and responsibilities your organization gives it. See the Center Agent overview for its role and scope.
For each request, it uses the context, tools, and permissions available to the person asking.
Start a conversation
- Open Center Agent from the bottom toolbar.
- Open the full chat if you need its history, files, or other views.
- Write the result you want. Add the information needed to produce it.
- Read the reply, check the result, and continue in the same conversation.
Start a new conversation for unrelated work. Switching conversations changes the discussion context; it does not create another Center Agent.
Write a useful request
Include the source, output, and limits. For example:
Use the notes below to draft a customer update. Keep it under 150 words. Separate shipped changes from planned work. Save the draft here; do not email it.
For work in another app, name the account or repository and what the Agent may change. If a required connection is missing, connect the Plugin before expecting that action to work.
Follow work and respond
Read progress and any request for information or approval. A question from the Agent may be the next required step.
Use the conversation's available stop control when you want work to stop. Check the resulting state. A click alone does not prove an external operation was canceled.
Review the outcome
Check that a claimed file exists, a draft contains the right facts, or a change appears at its stated destination. Ask for the source when a factual claim matters.
Use Tasks to track deliverables in this conversation and Files for attached artifacts. Graph offers a visual view of the conversation's work. Neither replaces the actual result.
Suggestions and memory
Center Agent may suggest an improvement during a conversation. You can accept, defer, or dismiss it. Accepting a suggestion does not, by itself, authorize every action needed to implement it.
Memory, Skills, and shared knowledge supply different kinds of reusable context.
If an owner or admin pauses Center Agent, work may be unavailable until it is resumed in Center Agent settings.
Configure the workspace’s Agent
Open Settings → Center Agent for model and reasoning choices, identity, Team Brief, memory, Channels, Audit Log, and pause or resume. Changes can affect the whole workspace. See Configure Center Agent for the steps and scope.

