Define the Technical Requirements
When planning an AI agent, gather technical requirements that will help you build the right solution. Key factors to explore include: data, channels, routing and escalation, and security controls.
Required Editions
| Available in: Lightning Experience |
| Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type. |
Data
Your organization needs to be data-ready to start an AI project, which means the data for the project is accurate, complete, available, accessible, and securely governed. When defining the data requirements for your Agentforce use case, be sure to assess the data quality, migrate and integrate data, establish data governance, and create a plan for data analytics. To learn more about data requirements, see AI + Data: Project Planning.
Channels
Consider the channels where the AI agent will operate. How will the agent engage with internal or external users? How will the agent be presented to users? See Deploy Your Agent to Channels to learn more about the different options for deploying agents to channels, such as Slack, email, and messaging platforms.
Routing and Escalation
AI agents sometimes need to escalate conversations to a live representative. Some reasons for escalating to a rep can include company policy, brand requirements, security measures, risk management, or regulatory compliance.
During the planning process, define all the ways in which human decision-making and oversight will occur during the course of the AI agent’s work. Clear guidelines about when and how reps should step in will make it easier for your organization to configure the right guardrails as you start prototyping your agent.
Security Controls
When you start planning your AI agent, consider permissions and access for admins, employees, customers, and the AI agent itself.
- Admin Access: To create and manage AI agents in Salesforce, you need the Manage AI Agents user permission and the required permissions for your agent type, or the Customize Application user permission.
- Employee Access: If your employees interact with the AI agent in Salesforce, the agent runs in the context of the currently logged-in Salesforce user. See Trust and Agents.
- Customer Access: If your agent is deployed to external channels, such as your website, there are probably certain actions you don’t want an AI agent to perform on behalf of customers unless they’re verified. The way you design your authentication solution for Agentforce depends on the security and identification requirements for your particular use case. See Maintain Trust with Agentforce Actions.
- Agent Access: Some AI agents, such as service agents, operate as an agent user, and the agent user has a dedicated user profile and role in Salesforce. The actions the AI agent can take depend on the permissions it’s assigned. See Best Practices for Agent User Permissions to find out how to control what data your AI agent can access.
