Question 100
At Fairmont Finance, a regulated client experience team is improving account onboarding during an agent routing evaluation (SF-D14-01). The administrator observes that a high-confidence answer cites an incomplete single chunk when the procedure spans several sections. Any fix must ensure that financial identifiers are masked outside authorized roles. Which underlying Agentforce or Salesforce design principle explains the appropriate approach?
Explanation
Correct Answer
The governing distinction is: Retrieval window and chunk boundaries together affect grounding completeness. In this account onboarding scenario, this separates supported agent behavior from assumptions about the AI model. Because a high-confidence answer cites an incomplete single chunk when the procedure spans several sections, the intended response is to adjust the retriever result count and chunk design to include required related context. An observable check is that test questions return the prerequisite and exception sections needed for a correct response.
Incorrect Answers
The idea “Structured record grounding differs from unstructured chunk search; interpret this independent of the surface wording of the conversation” explains another source-defined situation: An LLM response requires current account status stored in a structured DMO rather than long documents. The correction must ensure that shipment changes remain attributable and reversible. That situation depends on: Structured record grounding differs from unstructured chunk search. The present question instead concerns a high-confidence answer cites an incomplete single chunk when the procedure spans several sections. The correction must ensure that financial identifiers are masked outside authorized roles. Its directly relevant mechanism is: Retrieval window and chunk boundaries together affect grounding completeness.
The idea “Ingestion alone does not provide retriever-ready search access; interpret this rather than assuming a generative instruction is an access rule” explains another source-defined situation: A Data 360 source is ingested but no searchable index exists for its content. The correction must ensure that student records never cross program authorization boundaries. That situation depends on: Ingestion alone does not provide retriever-ready search access. The present question instead concerns a high-confidence answer cites an incomplete single chunk when the procedure spans several sections. The correction must ensure that financial identifiers are masked outside authorized roles. Its directly relevant mechanism is: Retrieval window and chunk boundaries together affect grounding completeness.
The idea “Data Libraries connect managed knowledge sources to grounding tools and retrieval; interpret this as a necessary control for deterministic outcomes” explains another source-defined situation: Support agents answer policy questions from PDFs but there is no managed knowledge grounding resource. The correction must ensure that student records never cross program authorization boundaries. That situation depends on: Data Libraries connect managed knowledge sources to grounding tools and retrieval. The present question instead concerns a high-confidence answer cites an incomplete single chunk when the procedure spans several sections. The correction must ensure that financial identifiers are masked outside authorized roles. Its directly relevant mechanism is: Retrieval window and chunk boundaries together affect grounding completeness.