AI-201 · Question #256
An Agentforce Specialist at Universal Containers (UC) is building with no-code tools only. They have many small accounts that are only touched periodically by a specialized sales team, and UC wants…
The correct answer is C. Use a prompt template grounded on CRM and Data Cloud data using standard foundation. The key constraints in this question are (1) no-code tools only and (2) the need to surface data from both standard CRM (past purchases, email/phone transcripts) and Data Cloud (product interest signals). Salesforce Prompt Builder supports grounding prompt templates directly on…
Question
An Agentforce Specialist at Universal Containers (UC) is building with no-code tools only. They have many small accounts that are only touched periodically by a specialized sales team, and UC wants to maximize the sales operations team's time, UC wants to help prep the sales team for calls by:
- Summarizing past purchases
- Displaying products the contact has shown interest in (with data
captured via Data Cloud)
- Providing a recap of past email and phone conversations that have
transcripts Which approach should the Agentforce Specialist recommend to achieve this goal?
Options
- ADeploy UC's own custom foundational model on this data first.
- BFine-tune the standard foundational model due to the complexity of the data.
- CUse a prompt template grounded on CRM and Data Cloud data using standard foundation
How the community answered
(19 responses)- A5% (1)
- B21% (4)
- C74% (14)
Explanation
The key constraints in this question are (1) no-code tools only and (2) the need to surface data from both standard CRM (past purchases, email/phone transcripts) and Data Cloud (product interest signals). Salesforce Prompt Builder supports grounding prompt templates directly on CRM objects and Data Cloud data without writing any code, making it the ideal no-code solution. The standard foundation model (e.g., the Einstein LLM) can then use this grounded context to generate the desired summaries and recaps. Option A (deploying a custom foundational model) requires significant ML infrastructure work and is not no-code. Option B (fine-tuning the standard model) also requires technical ML expertise and tooling - it is not a no-code approach and is overkill for a task where prompt grounding on existing data is sufficient. Prompt templates with CRM and Data Cloud grounding are precisely designed for this use case.
Topics
Community Discussion
No community discussion yet for this question.