Explanation:

The requirement specifies a hospitality brand agent grounded in a data library containing 200 FAQ articles. To avoid a three-week manual process of authoring test cases, the specialist needs to leverage the Agentforce Testing Center's built-in automation to generate a comprehensive initial test suite from that existing content.

The correct approach is explained below:

In the Agentforce Testing Center, administrators can choose Generate test cases based on the knowledge available to the agent (also listed as Generate Tests from Knowledge Sources in Salesforce documentation).

When this feature is selected, the underlying generative AI analyzes the connected Data Libraries and Salesforce Knowledge base to automatically formulate realistic user questions (utterances) and Q&A-style test scenarios directly from your indexed documentation.

This process immediately covers the vast majority of your content's surface area, reducing the time required to build a testing baseline from weeks to minutes.

Why the Other Options Are Incorrect
A. ❌ Upload test cases.
Uploading test cases relies on a downloadable CSV template where the project team must have already manually populated the utterances, expected topics, and expected actions. This directly contradicts the requirement to generate a test suite without manual authoring.

C. ❌ Generate test cases based on subagents and actions.
While this is a valid option in the Agentforce Testing Center (Beta), it creates test scenarios aimed at verifying topic routing, intent classification, and flow tool execution based on subagent metadata. It is not optimized to crawl through and evaluate the deep knowledge text inside 200 specific FAQ data library files like option B does.

Reference
Salesforce Help: Generate Tests from Knowledge Sources (Agentforce Testing Center). To quickly evaluate an agent's grounded accuracy, select the option to generate test cases based on the knowledge available to the agent to automatically parse connected libraries.

Exam Tip
When a question emphasizes testing Knowledge Bases, FAQs, or Data Libraries quickly:

✅ Grounded Document / FAQ Verification → Generate test cases based on the knowledge available to the agent
✅ Topic / Flow Tool Execution Verification → Generate test cases based on subagents and actions

Explanation:

Option B (Implement a larger chunk size) is the recommended strategy here.

For long, complex, hierarchically structured documents like legal agreements (with nested clauses inside sections, subsections, etc.), the standard or smaller chunking strategy often breaks context across boundaries. A larger chunk size helps preserve broader structural context, headings, and surrounding sections so the retrieval process (RAG via Agentforce Data Library) can deliver more complete and relevant clauses along with their necessary context.

Why the Other Options Are Incorrect
A. ❌ Smaller chunk size
This would worsen the problem by creating even more fragmented pieces, causing the nested relationships and surrounding context that are critical for legal documents to be lost.

C. ❌ Keyword-based chunking
Keyword-based chunking can help with targeted retrieval in some scenarios, but it does not inherently preserve document structure such as hierarchy, sections, and nested content. It is better viewed as a complementary technique rather than the primary solution for structural context loss.

Additional Context & Tips
In Agentforce Data Library and Salesforce Knowledge implementations, the chunking strategy plays a major role in Retrieval-Augmented Generation (RAG) quality. Larger chunks are generally better for documents with rich internal structure, while smaller chunks are more suitable for uniform, fact-dense content.

For even better results, combine larger chunk sizes with well-defined metadata (such as section titles and clause IDs), hierarchical indexing where available, and prompt instructions that guide the agent on how to synthesize information from retrieved chunks.

Use Agentforce evaluation tools (such as factuality, completeness, and coherence metrics) to validate that the new chunking strategy improves retrieval quality.

This topic aligns with the Data Cloud, Data Library, Prompt Engineering, and Agent Optimization objectives covered in the Salesforce Certified Agentforce Specialist (AI-201) exam.

Explanation:

When configuring a Data Library that uses Salesforce Knowledge as a source, Identifying Fields are used to help Agentforce quickly recognize and label what a piece of content is about—essentially acting as a concise descriptor or title-like reference for the article, rather than the full content itself. Since Knowledge articles can be long and detailed, Salesforce recommends using short, concise summary fields (such as a "Summary," "Title," or similar text/text area field) as Identifying Fields. This allows Agentforce to efficiently reference and surface the correct article without needing to process the entire lengthy body of content just to identify it.

Identifying Fields are meant to be lightweight, metadata-like markers—not the full grounding content—which makes retrieval and matching more efficient and accurate.

Why the Other Options Are Incorrect:
A. The main contents of the article
The full article body is used for grounding and retrieval content (i.e., what gets chunked, vectorized, and retrieved to answer questions), not for identifying the article. Using the entire article body as an Identifying Field defeats the purpose of having a concise identifier and can reduce matching efficiency and accuracy.

C. A formula field with a concatenated key
While a formula field could technically contain a system-generated key, it does not serve the purpose of an Identifying Field. Identifying Fields are intended to be human-readable, concise, and meaningful summaries that help Agentforce—and users or administrators reviewing results—understand what the article is about, rather than acting as synthetic keys for internal deduplication or matching logic.

Reference:
Salesforce Agentforce documentation — "Configure a Data Library with Salesforce Knowledge" (guidance on selecting concise summary or text fields as Identifying Fields for article-based data sources).

Explanation:

The Single-Org, Multi-Agent (SOMA) architecture is designed for organizations operating within a single Salesforce instance that need multiple specialized agents. In SOMA, a primary Orchestrator agent manages shared context, enforces centralized guardrails, and routes subtasks to specialized agents (Fraud Detection, Loan Origination, Billing, etc.). This ensures:

* Centralized security and governance — guardrails are enforced consistently across all agents.
* Shared context — customers don’t need to repeat information when their request spans multiple departments.
* Scalability — new specialized agents can be added without duplicating context management or security logic.

Option A is incorrect:
MCP is about standardizing context exchange between AI models and external systems, not orchestrating multiple agents within a single Salesforce org.

Option B is incorrect:
MOMA is used when multiple Salesforce orgs are involved. GFC operates in a single org, so MOMA introduces unnecessary complexity.

Option C is correct:
SOMA with an Orchestrator agent directly addresses the CIO’s requirements for scalability, centralized control, and seamless customer experience.

Reference:
Salesforce Documentation: Agentforce SOMA Architecture

Salesforce Help: Orchestrator Agent in Agentforce

Trailhead Module: Agentforce Multi-Agent Patterns

Explanation:

Why B is correct:
The question explicitly states that the specialist needs to identify a systematic misclassification pattern across sessions without reviewing individual transcripts. This is exactly the purpose of Agent Optimization within Agentforce Studio.

Agent Optimization automatically analyzes production sessions across the entire agent deployment. It segments conversations into individual "moments" (turns or exchanges) and uses AI to generate system intent clusters—grouping similar user inquiries together based on semantic meaning, regardless of which topic or subagent actually handled them.

These clusters are generated from cross-session analysis (typically on a weekly cadence) and include quality scores that highlight when the agent's topic classification is misaligned with the user's actual intent.

The specialist can look at the intent cluster for "billing dispute" and immediately see:
* How many times it was correctly routed to the Billing subagent.
* How many times it was misclassified under "General Inquiry."
* The score reasons explaining why the misclassification occurred.

This provides a high-level, aggregated pattern view without requiring the specialist to read through hundreds of individual chat transcripts or session traces.

Why A is incorrect:
Session Tracing in Agentforce Observability is a per-session debugging tool. It allows you to drill into the detailed reasoning, variable states, and action selections for a single specific conversation.

While you could query the Data 360 Session Tracing Data Model to analyze many sessions, this would require complex data modeling, custom queries, and manual analysis. It is not designed to automatically detect and surface systematic misclassification patterns across thousands of sessions. Agent Optimization does this work for you out of the box.

Why C is incorrect:
The Agentforce Testing Center is a pre-deployment testing tool. You upload a representative set of utterances, run batch tests, and compare expected vs. actual behavior to validate the agent's configuration before going live.

Testing Center is not designed to analyze production intents or identify misclassification patterns across live sessions. It is for QA and validation in a sandbox or testing environment, not for post-deployment monitoring and optimization of live traffic.

References:
Salesforce Official Documentation: "Agentforce Agent Optimization" – defines Agent Optimization as the tool that analyzes production session data to generate system intent clusters, providing aggregated insights into topic classification accuracy and misrouting patterns.

Trailhead Module: "Monitor and Optimize Agentforce Agents" > Unit: "Optimize Agent Performance with Agent Optimization" – explicitly explains how Agent Optimization surfaces misclassification patterns across sessions without requiring individual transcript reviews.