Plan Your AI Agent
Planning an AI agent is crucial for several reasons. It ensures that your AI project aligns with your company's overall AI strategy and business goals. It also helps you define the agent's work and assess its potential impact on the organization.
Required Editions
| Available in: Lightning Experience |
| Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type. |
Addressing concerns and risks upfront by integrating risk management into the planning stage can accelerate projects and ensure they meet ethical, legal, regulatory, and security requirements. Without proper planning, an agentic AI project might fail to deploy or be scrapped entirely.
Although careful planning is important, try to strike a balance between experimentation and planning. When you’re getting started with Agentforce, hands-on learning and prototyping are essential for understanding AI agents and testing out ideas.
- What is an Agentforce Use Case?
An Agentforce use case is an application of AI technology where an AI agent takes an action or series of actions that accomplish a goal or job-to-be-done on behalf of your employees, customers, or organization. - Define an Agentforce Use Case
After identifying your use case ideas for Agentforce, flesh out each of the use cases so your organization can assess and prioritize them. Remember, this stage of the planning process is about the project goals, not the technical solution. - 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. - Salesforce Considerations for Agentforce Projects
Your AI agent must coexist with your current Salesforce configuration and architecture. Consider Salesforce-specific factors that can influence your Agentforce implementation. - Identify Risks and Guardrails for an Agentforce Project
Autonomous AI agents come with risks, such as security threats, data breaches, reputational harm, financial loss, bias, hallucinations, and issues with transparency and accountability. When planning an AI agent, identify risks for your Agentforce use case and plan risk mitigation strategies. - Map Business Processes for an Agentforce Project
When planning an AI agent, it’s important to define the work the agent will do. One way to define the work is to map the business processes related to your Agentforce use case. - Identify the Subagents and Actions
After determining your agent’s use case and the work the agent will do, you can identify the right subagents and actions for the agent. Agents are made up of subagents, which define the different jobs an agent can do. Subagents also contain a set of actions, which are the tools the agent can use to do its job. - Design the Subagents and Actions
After identifying the right subagents and actions for your AI agent, start planning how to build them. Following best practices when designing the subagents and actions can help your agent perform reliably and effectively.
