Exam Certified AI Specialist topic 1 question 2 discussion

Actual exam question from Salesforce's Certified AI Specialist

Question #: 2
Topic #: 1

Universal Containers (UC) recently rolled out Einstein Generative AI capabilities and has created a custom prompt to summarize case records. Users have reported that the case summaries generated are not returning the appropriate information.
What is a possible explanation for the poor prompt performance?

A. The Einstein Trust Layer is incorrectly configured.
B. The data being used for grounding is incorrect or incomplete.
C. The prompt template version is incompatible with the chosen LLM.

Show Suggested Answer

Suggested Answer: B 🗳️

by ETH777 at Dec. 6, 2024, 7:39 a.m.

Comments

Submit Cancel

Lovens

5 days, 13 hours ago

Selected Answer: B

Answers come from what was input in the prompt... Response Quality depends on input quality.

upvoted 1 times

...

zwb

5 months, 1 week ago

Selected Answer: B

B. Tip: Better prompt, better reponse.

upvoted 1 times

...

zwb

5 months, 1 week ago

Selected Answer: A

A. You need to use the Sales Email template type when creating a new prompt, so NOT C. Standard email template will not work with the prompt.

upvoted 1 times

...

TopKing

6 months, 1 week ago

Selected Answer: B

Not C: All Prompt Template versions (Field Generation, Record Summary, Sales Email, Flex or Knowledge answers) are compatible with all LLMs. Note that some LLMs could generate less appropriate responses. However, to today, compatibility issue between a prompt templates versions/types and LLMs have not been documented.

upvoted 1 times

...

ETH777

6 months, 3 weeks ago

Selected Answer: B

Not A: Einstein Trust Layer is focused on data security and auditing, not the quality of prompt responses.

upvoted 2 times

...