Universal Containers built a Field Generation prompt template that worked for many records, but users are reporting random failures with token limit errors. What is the cause of the random nature of t

Question

Options

• AThe template type needs to be switched to Flex to accommodate the variable amount of tokens
• BThe number of tokens generated by the dynamic nature of the prompt template will vary by
• CThe number of tokens that can be processed by the LLM varies with total user demand.

• A
  8% (3)
• B
  90% (36)
• C
  3% (1)

Explanation

Field Generation prompt templates use dynamic merge fields that pull live data from Salesforce records at runtime. Because different records contain varying amounts of text (e.g., a case with a long description vs. a short one), the total token count of the resolved prompt varies per record. For some records the resolved prompt stays within the model's token limit; for others it exceeds it - producing the random, record-dependent failures users are experiencing. Option A is wrong because switching to Flex does not raise the LLM's token limit. Option C is incorrect because LLM token limits are fixed per model, not dynamically reduced by user demand.

No community discussion yet for this question.