Deploying the agent
When you decide that an agent is ready for use by your team, you need to deploy it to move it from draft to live.
An agent in draft is in the process of development and is not available for use in channels like chat. Deploying the agent to live makes it available with the current copy of the functions that are used to ground the agent.
After deployment, you can use the agent in the channels set up during its development. For more information, see Connecting to channels.
Before you begin
Create the agent with the minimum required details such as name and description before you deploy it.
Deploying the agent
In the agent details page, click Deploy. It makes the agent work with a current copy of the functions that you use to ground the agent such as instructions, knowledge, tools, collaborator agents, and channels.
The functions that you use to ground the agent is not updated until you redeployed this agent.
Updating a deployed agent
Over time, you might need to update your agent to add new features, improve performance, or adapt to changing user needs.
In the agent details page, click Deploy. Redeploying the agent updates it with the latest updates in its functions.
If a collaborator agent is updated and deployed separately, the updates to the collaborator agent are not reflected until you redeploy the agent.
Reverting a deployment of an agent
Eventually, you might decide to retire the agent when it's no longer needed. Click the overflow menu 
> Undeploy to revert a deployment.
What to do next
After you deploy the agent, use the agent on any of the configured channels. For more information on using agents in watsonx Orchestrate chat, see Using agents in the watsonx Orchestrate chat.