A specialist argues that any agent type can be deployed to any channel, so channel alone should never be used to decide between Employee, Service, and Sales agent. What is the better basis for that decision?
Select an answer to reveal the explanation.
Short Explanation
Channel is just the doorway; audience and job are what actually decide who should be standing behind the counter. A Sales agent parked on Slack is still a Sales agent, just wearing a Slack badge.
Full Explanation
Agent type selection is driven by who the agent serves and what kind of work it is meant to do, because those two things determine which standard topics and actions come available by default and which security posture, such as external customer-facing versus internal staff-facing, is appropriate. Channel is a deployment detail layered on top: the same Service agent could reasonably be reached through a website, the mobile app, or email, and none of that changes what makes it a Service agent. Picking a type based on configuration order is arbitrary and has no bearing on fit; consistency for its own sake is not a design principle the exam tests. Topic count is also irrelevant to type selection; an Employee agent can have many topics and a Sales agent can have few, since topic count reflects scope of configuration, not agent category. There is no notion of agent type being selected by data volume or throughput; nothing in Agentforce ties type selection to processing capacity, and inventing such a rule is the kind of unsupported feature claim the exam explicitly penalises. The correct mental model is audience-and-purpose first, channel and configuration details second.