Default Scorers

Default scorers measure your AI agent's performance across response accuracy, subagent assertion, and action assertion.

Required Editions

This article applies to:	New Testing Center in Agentforce Studio (Beta)
This article doesn't apply to:	Legacy Agentforce Testing Center in Setup

Available in: Lightning Experience

Available in: Enterprise, Performance, Unlimited, and Developer Editions. Required add-on licenses vary by agent type.

User Permissions Needed
To create tests in the Testing Center:	Manage Agentforce Grids AND Manage Agentforce Testing

User Permissions Needed

To create tests in the Testing Center:

Manage Agentforce Grids

AND

Manage Agentforce Testing

Default scorers always run on every test. The scorers available depend on whether you're running turn-level or conversation-level tests.

Note Subagent and Action scorers are available in both testing types under different names. In turn-level testing they appear as Subagent Assertion and Action Assertion. In conversation-level testing they appear as Subagent Evaluation and Actions Evaluation.

Turn-Level Scorers

Scorer	Definition
Response Evaluation	We send the test utterance to the agent and record the response. An LLM judge determines the expected response, compares it to the agent's response, and assigns a score.
Subagent Assertion	AI-generated test utterances are designed to trigger your agent to select their assigned subagents. This scorer determines if your agent selected the correct subagent based on the utterance.
Action Assertion	AI-generated test utterances are designed to trigger your agent to select specific actions. This scorer checks that the agent selects the right actions based on the utterance.

Note The Expected Response field should reflect the response you expect the agent to give. A common mistake is including instructions about the response like "the agent should mention the order number and be polite." This produces inaccurate scores.

Conversation-Level Scorers

Scorer	Definition
Task Resolution	Returns a pass or fail based on whether the agent resolved the user's issue.
Subagent Evaluation	AI-generated test utterances are designed to trigger your agent to select their assigned subagents. This scorer determines if your agent selected the correct subagent based on the utterance.
Actions Evaluation	AI-generated test utterances are designed to trigger your agent to select specific actions. This scorer checks that the agent selects the right actions based on the utterance.