A compliance-focused insurance company is building a Copilot Studio agent to answer customer questions about policy coverage. The legal team requires that the agent only answer from pre-approved knowledge sources, that it never infers or synthesize answers beyond what is explicitly stated in those sources, and that all AI-generated content can be traced back to a specific document. Which Generative answers configuration best meets these requirements?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Classic mode with citations is the compliance-safe configuration—it's like having a lawyer who only quotes from the exact contract paragraphs, with footnotes, rather than paraphrasing from memory. The AI stays grounded in approved documents.
Full explanation below image
![Portrait infographic 1536x2048 titled 'Generative Answers Classic Mode for Compliance'. Show a configuration diagram: Generative Answers Node settings panel with Mode selector showing 'Classic' selected (highlighted). Below, Knowledge Sources section listing three approved sources: Policy Document Library (SharePoint), Product Coverage Guide (PDF), Claims FAQ (uploaded file). Arrow from node to answer bubble showing sample answer text with citation marker [Source: Policy Document Library, p.12]. Side comparison panel: Classic Mode vs Orchestration Mode table comparing Source Control, Citation Support, Best For columns. Insurance/legal color scheme: navy blue, gold, white. Clean, professional Fluent design.](/media/microsoft/ab-620/AB-620-e5-q014-infographic.webp)
Full Explanation
Copilot Studio's Generative answers node in Classic mode offers more controlled, predictable behavior than Orchestration mode. In Classic mode, the developer explicitly specifies which knowledge sources the agent may draw from, and the AI generates answers grounded exclusively in those documents. When citation display is enabled, the agent surfaces references to the specific source documents used in its answer, enabling traceability required for compliance environments.
Option C is correct because Classic mode restricts the agent to configured, approved knowledge sources (e.g., specific SharePoint libraries, public URLs, or uploaded files) rather than allowing broad source selection. Combined with citation display, every answer is traceable to a specific policy document, satisfying the legal team's requirements for source attribution and scope control.
Option A is wrong because Orchestration mode's dynamic source selection is the opposite of what compliance requires. While it produces more flexible answers, the AI may draw from multiple sources or make inferences beyond explicit document content, which violates the 'never infer beyond stated content' requirement. Traceability to a specific document is also harder in Orchestration mode.
Option B is wrong because disabling Generative answers entirely and using only manually authored nodes eliminates the scalability benefit of AI-powered Q&A. A large insurance policy corpus would require thousands of manually authored question-answer pairs to cover all possible customer questions—this is not operationally feasible and is an exam anti-pattern.
Option D is wrong because content moderation is a reactive filter for harmful/inappropriate content, not a source restriction mechanism. It cannot determine whether a response came from an approved versus non-approved source, nor can it enforce grounding in specific documents.
Exam tip: Classic mode = controlled, scoped, grounded in specified sources (compliance-friendly). Orchestration mode = dynamic, flexible, potentially broader source selection (innovation-friendly). For regulated industries or strict legal requirements, Classic mode with citations is the correct answer pattern.