Explanation:

Why B is correct:
When creating a prompt template that needs to consistently extract specific structured data (like product model numbers and quantities) from unstructured text (an email) and then draft a response, precision and reliability are the top priorities.

Clear, positive instructions tell the LLM exactly what to do (e.g., "Extract the product model number and quantity from the following email. Format your response as a draft reply to the customer."). Positive instructions (telling it what to do rather than what not to do) reduce confusion and improve output quality.

Few-shot examples (providing 1–3 examples of input emails and the exact desired output format) are the single most effective technique for guiding an LLM to produce consistent, formatted outputs. Few-shot learning anchors the model to the specific schema, format, and extraction logic you expect, dramatically improving reliability for structured data extraction tasks.

Why A is incorrect:
Open-ended questions are useful for creative brainstorming or exploratory conversations, but they are counterproductive for structured data extraction. Asking open-ended questions (e.g., "What can you tell me about the product?") will result in verbose, unpredictable, and inconsistent outputs that do not reliably capture the specific model number and quantity fields. This approach introduces variability, exactly what you want to avoid for a template intended for consistency.

Why C is incorrect:
The temperature setting controls the randomness/creativity of the LLM's output. A high temperature increases randomness and creativity, which is useful for creative writing but disastrous for structured extraction tasks. High temperature would cause the model to hallucinate, vary its output format, and extract inconsistent information. For extraction and drafting responses, you want a low temperature (closer to 0) to ensure deterministic, repeatable, and accurate outputs—not high temperature.

References:
Salesforce Official Documentation: "Prompt Engineering Best Practices for Agentforce" – recommends using clear, explicit instructions combined with few-shot examples for structured extraction tasks to maximize consistency and accuracy.

Explanation:

When configuring a file upload-based Agentforce Data Library, Salesforce enforces different size limits depending on file type: files must stay within size limits of 4 MB for text/HTML and 100 MB for PDFs.

This distinction makes practical sense:
Text/HTML files are plain text-based and typically much smaller in raw size, so a 4 MB cap comfortably covers large documents while keeping processing fast.
PDF files often contain embedded formatting, images, and layout data that inflate file size well beyond their actual text content, so a much larger 100 MB cap is needed to accommodate real-world business documents (manuals, policy documents, catalogs, etc.) while Data Cloud extracts and chunks the underlying text content.

Why not A:
This reverses the limits — it's not 100 MB for text/HTML and 4 MB for PDFs. Text/HTML has the smaller limit (4 MB), and PDF has the larger limit (100 MB).

Why not B:
The limits are not the same for both file types (50 MB each). Salesforce applies distinct limits per file type as noted above.

Reference:
Salesforce Trailhead – Create a Data Library for AI Agents / Build a File-Based Data Library for an Agent: Ensure the files are within the size limits (4 MB for text/HTML, 100 MB for PDFs).

Explanation:

Option A (Correct):
The Retriever Playground is designed for no-code testing of retrievers. It allows specialists to input queries and directly observe which chunks are surfaced, making it ideal for validating relevance before production deployment.

Option B:
The Agentforce Testing Center is focused on regression testing of agents and subagents, measuring metrics like Subagent Pass % and Action Pass %. It does not provide direct visibility into retriever chunk relevance.

Option C:
The Data 360 Query Editor is used for querying structured data in Data Cloud. It is not intended for testing retrievers or evaluating semantic chunk retrieval.

Reference:
Salesforce documentation on Retriever Playground highlights its role as the declarative, no-code environment for testing retrievers and validating chunk relevance prior to production rollout.

Explanation:

When grounding an Agentforce agent with complex corporate data ecosystems, information is rarely stored in just one place or in a single format. In this scenario, the company needs to draw knowledge from two completely distinct structures: unstructured PDF documents and a comprehensive structured/semi-structured Knowledge Base.

Why C is correct:
An Ensemble Retriever (configured in AI Models / Einstein Studio) is specifically designed to group multiple individual retrievers into a single operational unit. It allows you to search across multiple independent data sources simultaneously. When the agent executes an ensemble retriever, it queries all child retrievers, aggregates their findings, filters out redundancies, reranks the entire combined list based on real-time semantic relevance, and provides a unified, highly relevant payload to ground the agent's response.

Why A is incorrect:
A dynamic retriever uses runtime inputs or placeholders (such as record IDs passed from a CRM prompt template) to narrow down a search. While powerful for user context filtering, a single dynamic retriever is still mapped to a single underlying index/data object, rather than seamlessly unifying a PDF vector index with a standard Knowledge Base index.

Why B is incorrect:
An individual retriever is strictly bound to a single search index or Data Cloud Unstructured Data Model Object (UDMO). It cannot natively query across structurally separate document buckets and standard Knowledge articles at the same time.

Reference
Salesforce Help: Create an Ensemble Retriever. Use ensemble retrievers to get the most relevant information from multiple searches or data sources. In AI Models, an ensemble retriever acts as a collection of individual retrievers, running them in parallel, combining their results, and reranking the final output for the prompt or agent context.

Explanation:

The Agentforce Specialist should create a custom evaluation with a tailored prompt that outlines the specific criteria of the proprietary “De-escalation Framework” (plus empathy requirements).

Why Custom Evaluation?

The Agentforce Testing Center supports LLM-as-judge evaluations for nuanced, qualitative criteria (tone, empathy, adherence to custom frameworks).

A custom evaluation lets you provide a detailed prompt describing the exact framework steps, success indicators, and empathy markers. The LLM judge then scores responses accordingly.

This is the most flexible and accurate approach for proprietary or company-specific processes.

Why Not the Others?

A: Standard Coherence (or similar fixed criteria) evaluations have limited customization. Adjusting them does not sufficiently capture a proprietary De-escalation Framework.

B: Default Instruction Adherence helps with following general instructions but is not designed for deep qualitative assessment of empathy or custom frameworks.