Create an Agent from an Agentforce Service Agent Template
Agentforce Service agents intelligently support your customers by connecting to messaging and other channels and escalating to reps when necessary. Use the default Agentforce Service Agent template to create an agent designed to resolve common support cases and requests. Or select from more specialized templates to fit your use case.
Required Editions
| Available in: Lightning Experience |
| Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type. |
| User Permissions Needed | |
|---|---|
| To build and manage Service Agents: | Manage Agentforce Service Agents AND Manage AI Agents OR Customize Application |
- Best Practices for Agent User Permissions
Many AI agents, such as agents that connect to Messaging channels, operate as Salesforce users in your organization. The permissions that you give to these agent users determine the actions that AI agents can take. - Configure Service Agent Managers
When Service agents are enabled for your Salesforce org, Salesforce admins can create and edit service agents. To define other users as Service agent managers so that they can also create and edit service agents, assign those users the Manage Agentforce Service Agents permission set.
See Also
Create an Agent from a Service Agent Template
Before you begin, set up Einstein Generative AI and enable Agentforce.
-
From the App Launcher, enter
Agent, and then select the Agentforce Studio app. - On the Agents tab, click New Agent.
- Select an Agentforce Service agent template. Under Agent Details, select or create an Agent's User Record for this agent. To securely access data and perform actions, Service agents operate as an agent user, or a Salesforce integration user with all the permissions that the agent needs to do its job. See Best Practices for Agent User Permissions.
- Enter the agent's name and then click Let's Go.
- In the Settings section, define the settings that determine how your agent behaves in conversations, such as system messages and language settings.
- In the Subagents section, manage and customize your agent's subagents and actions.
- In the Data section, select a data library. The Answer Questions with Knowledge action grounds your agent's responses with it. To create or manage data libraries, see Setting Up Data Libraries.
- Click Preview to test out your agent and confirm that it performs as expected and meets your security standards. You can simulate your agent’s behavior with mock data without risking any changes to your actual data or org. Use trace to dig into the steps the agent performed, and ask Agentforce to help you understand your agent’s behavior at any step. See Preview and Test in Agentforce Builder for more details.
- Connect your agent to service channels to transfer agent conversations. See Connect an Agent to Messaging for more information on deploying your agent to a Messaging channel.
- When you’re ready to use your agent outside of the builder, click Commit Version. You must commit an agent version before you can activate it. Committed versions can’t be edited. To continue making changes after committing, create a new version by clicking New Version. See Versioning and Editing Agents for more information.
- When you're ready, activate your agent.
Create an Agent from a Service Agent Template in the Legacy Agentforce Builder
- From Setup, in the Quick Find box, enter Agents, and then select Agentforce Agents.
- Click New Agent.
- Select Create from a Template. Select the template that you want to use to create an agent, and then click Next.
- Review the subagents that come with your template. You can customize these subagents and actions later, but if any of them don’t apply to your use cases, remove them. Then click Next.
-
Give your agent a unique name, API name, description, role, and company.
The description field is used by you and others in your org to identify your agent. The role and company fields are used by your agent to help it understand its responsibilities and the company that it represents.
-
Under Agent User, select New Agent User. Then click
Next.
To securely access data and perform actions, Service agents operate as an agent user—a Salesforce integration user with all the permissions that the agent needs to do its job. Creating a new agent user in the guided setup creates an agent user record with minimal access so that your agent is secure by default. Grant the agent the additional access that it needs. See Best Practices for Agent User Permissions.
- Select Keep a record of conversations with enhanced event logs to review agent behavior. See Enable Enhanced Event Logs.
-
Select a data source to ground your agent responses with the Answer Questions with
Knowledge action. To continue without selecting any data sources, leave this field
blank. You can add and remove data sources later. Then click
Create.
If you don't want to use any of the available data sources, you can create a library to limit Agentforce Service agents to specific articles or uploaded files. See Assign a Data Library to Your Agent.
- From the Settings page, define your agent's settings, such as system messages and language settings. These settings determine how agents behave and present themselves in conversations.
- Back in the builder, configure your agent with subagents, actions, and other agent assets.
-
Test your agent in Agentforce Builder to confirm that your agent performs as expected
and meets your security
standards.
The service agent operates in the same Agent User context here as it does when deployed in messaging channels, so design-time testing reflects how your service agent behaves when deployed.
- Connect your service agent to channels and configure the escalation subagent to transfer agent conversations.
- When you're ready, activate your agent.
Did this article solve your issue?
Let us know so we can improve!
