Explanation:

Option C (Correct):

The Agentforce Testing Center provides automated regression testing with metrics like Subagent Pass % and Action Pass %. By re-running the stored test suite, the Specialist can quickly identify regressions introduced by the Billing subagent changes, confirm the scope of misrouting, and extend the suite to cover the new refund escalation path. This ensures systematic diagnosis and compliance with best practices.

Option A:

Utterance Analysis is useful for reviewing logs, but it is reactive and manual. It does not provide regression metrics or systematic coverage. It is better suited for fine-tuning after regressions are already identified, not for confirming the full extent of impact.

Option B:

Manually replicating scenarios in Conversation Preview is time-consuming and error-prone. It cannot scale to cover all possible utterances or provide quantitative regression metrics.

Reference:

Salesforce documentation on Agentforce Testing Center highlights its role in regression testing, automated validation, and ensuring subagent routing accuracy after configuration changes.

Explanation:

Relying purely on natural language system instructions (probabilistic control) to enforce strict business rules or security compliance often leads to hallucinations. When a rule is absolute—such as a security or financial restriction—you must use deterministic guardrails.

Why C is correct:

Agentforce allows administrators to set Action Conditions (or Action Visibility filters) on individual actions. These function exactly like conditional visibility rules elsewhere in Salesforce. By setting a condition where Account Tier EQUALS Platinum, the Agentforce runtime evaluates the current record context or session data before presenting the action to the LLM.

If the customer is a "Standard" tier, the action is hidden from the agent's available toolset entirely. Because the agent does not even know the action exists for that customer, it is physically impossible for it to invoke it, completely preventing backend errors.

Why A is incorrect:

This is what Universal Containers is currently doing. System instructions are probabilistic; while they reduce unwanted behavior, they can still be bypassed or hallucinated under certain conversational contexts.

Why B is incorrect:

Text filtering or blocking keywords like "refund" is brittle, negatively impacts user experience, and does not gracefully handle natural variations in human speech (e.g., a customer saying "I want my money back").

Reference:

Salesforce Agentforce Documentation: Manage Agent Actions. Action conditions let you control when an action is available to an agent based on user permissions, record data, or session variables. This ensures compliance and prevents the agent from executing unauthorized tasks.

Explanation:

Option A (Correct):

Agent Inspection provides full visibility into the entire agent interaction lifecycle — from the initial user request through to resolution. It allows specialists to review transcripts, actions taken, and outcomes, making it the right tool for analyzing agent behavior and response quality.

Option B:

Agent Insights focuses on aggregated performance metrics and trends (e.g., deflection rates, escalation volumes). It does not provide detailed inspection of individual interactions.

Option C:

Agent Optimization is about improving agent performance through tuning and configuration changes. It is not designed for analyzing complete interaction histories.

Reference:

Salesforce documentation on Agentforce Observability highlights that Agent Inspection is the feature used to review full agent sessions for compliance, quality assurance, and behavioral analysis.

Explanation:

This question tests your understanding of Agent Script's hybrid reasoning model, which combines:

• Declarative instructions for AI-driven, flexible reasoning.
• Procedural instructions for deterministic, rule-based execution.

Because the loan origination workflow includes regulatory compliance (identity verification followed by a credit check in a mandatory sequence), the agent must use procedural instructions for those critical steps.

Why B is correct

Agent Script supports two complementary instruction patterns:

Declarative instructions

• Written in natural language.
• Interpreted by the LLM.
• Allow conversational flexibility and adaptive reasoning.
• Suitable for tasks where the agent can decide how best to respond.

Procedural instructions

• Use the -> syntax.
• Support constructs such as run, if, and transitions.
• Execute in a deterministic, predefined order.
• Ideal for workflows where compliance or business rules require specific sequencing.

For regulated processes like:

• Verify identity
• Perform credit check
• Continue only if verification succeeds

procedural instructions ensure the sequence cannot be skipped or reordered.

Why the other options are incorrect

A. Declarative instructions require Flow execution...

This is incorrect because:

• Declarative instructions are interpreted directly by the LLM.
• They do not require Salesforce Flow to implement business logic.
• Procedural instructions are not limited in the way described and can invoke actions that access external systems and APIs.

❌ Misrepresents both instruction types.

C. Declarative instructions only work in Canvas View...

This is incorrect because:

• Declarative and procedural instructions are language constructs, not features restricted to a particular editor.
• They are not differentiated by Canvas View versus Script View.

❌ Confuses editing interfaces with execution semantics.

Salesforce References

This topic is covered in Salesforce resources related to Agentforce and Agent Script, including:

• Agentforce Developer Guide – Agent Script syntax and hybrid reasoning.
• Trailhead: Build AI Agents with Agentforce – Declarative versus procedural instruction patterns.
• Salesforce documentation on deterministic execution in Agent Script.

Explanation:

To ensure the verification email is automatically triggered immediately after the account creation action (without requiring additional user interaction or relying on the reasoning engine to decide the next step), the specialist should add the send verification logic inside the procedural instructions of the relevant topic/action.

In Agent Script:

Procedural instructions (often marked with ->) run deterministically every time the topic/action executes.
This is the best way to enforce strict sequencing in multi-step workflows (e.g., account creation → immediate verification email → profile setup).

You can chain actions directly using statements like run @actions.send_verification_email within these instructions.

This guarantees execution right after account creation, independent of LLM reasoning.

Why Not the Others?

B:

This relies on the reasoning engine deciding to call the action in a later step based on a condition (account_created == True). It is not guaranteed to be immediate and introduces non-determinism.

C:

While the run keyword is used for chaining actions in Agent Script, simply using it inside the "create account" action (without proper procedural context) may not enforce the exact automatic, no-interaction behavior described. Procedural instructions provide the strongest guarantee for sequential automation.