AI-201 · Question #9
Universal Containers (UC) wants to implement an AI-powered customer service agent that can: - Retrieve proprietary policy documents that are stored as PDFs. - Ensure responses are grounded in…
The correct answer is A. is the correct starting point. A Data Library allows UC to upload PDFs containing policy. The correct first step is to create an Agentforce Data Library and upload the proprietary PDF policy documents into it. Once uploaded, the files are indexed into Data Cloud's vector store, making them available for semantic retrieval to ground the AI agent's responses in…
Question
Universal Containers (UC) wants to implement an AI-powered customer service agent that can:
- Retrieve proprietary policy documents that are stored as PDFs.
- Ensure responses are grounded in approved company data, not generic
LLM knowledge. What should UC do first?
Options
- Ais the correct starting point. A Data Library allows UC to upload PDFs containing policy
- BExpand the AI agent's scope to search all Salesforce records.
- CAdd the files to the content, and then select the data library option.
How the community answered
(18 responses)- A78% (14)
- B17% (3)
- C6% (1)
Explanation
The correct first step is to create an Agentforce Data Library and upload the proprietary PDF policy documents into it. Once uploaded, the files are indexed into Data Cloud's vector store, making them available for semantic retrieval to ground the AI agent's responses in approved company content rather than generic LLM knowledge. This is the foundational setup step before the agent can retrieve and use the documents. Option B is incorrect and counterproductive - expanding scope to all Salesforce records does not address the need to ground responses in specific policy PDFs. Option C is out of order; content must be added to a Data Library first before it can be referenced as a data source.
Topics
Community Discussion
No community discussion yet for this question.