nerdexam
Salesforce

AI-201 · Question #151

An Agentforce 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 correct answer is A. Use a prompt template grounded on CRH and Data Cloud data using standard foundation model. The constraint here is no-code tools only. Prompt Builder supports prompt templates that can be grounded in CRM (standard/custom objects) and Data Cloud data using the standard foundational model-no coding required. Fine-tuning a model (B) requires ML expertise and…

AI Features for Service (e.g., Einstein Bots, Next Best Action)

Question

An Agentforce 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 the calls by summarizing past purchases, interests in products shown by the Contact captured via Data Cloud, and a recap of past email and phone conversations for which there are transcripts. Which approach should the Agentforce Specialist recommend to achieve this use case?

Options

  • AUse a prompt template grounded on CRH and Data Cloud data using standard foundation model.
  • BFine-Tune the standard foundational model due to the complexity of the data.
  • CDeploy UC's own custom foundational model on this data first.

How the community answered

(37 responses)
  • A
    76% (28)
  • B
    16% (6)
  • C
    8% (3)

Explanation

The constraint here is no-code tools only. Prompt Builder supports prompt templates that can be grounded in CRM (standard/custom objects) and Data Cloud data using the standard foundational model-no coding required. Fine-tuning a model (B) requires ML expertise and infrastructure, not a no-code process. Deploying a custom foundational model (C) is even more complex and far beyond no-code. For summarization tasks using existing Salesforce and Data Cloud data, a well-crafted prompt template with the standard LLM is sufficient and appropriate.

Topics

#AI Integration#Prompt Engineering#Foundation Models#Data Grounding

Community Discussion

No community discussion yet for this question.

Full AI-201 Practice