Unverified50% confidenceDecision RuleExact time
Intent recognition should not be handed to the LLM on every call; the more reasonable approach is to build a lightweight classifier sitting upstream.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLLM nodes are typically used only when parsing pure natural language input or when upstream output is unclear and there are too many downstream branches to handle with if-else; when upstream data is structured, code nodes should be used instead.69% similarUnverifiedWhen the number of categories is small and definitions are clear, using prompts to have the LLM perform end-to-end classification directly is reasonable, with low cost and fast deployment.68% similarVerifiedThe root cause of prompt injection lies in the fact that LLM architecture encodes system prompts, user inputs, and externally retrieved content uniformly into the same continuous token sequence, making it impossible for the model to distinguish trusted instructions from untrusted data at the semantic level.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1009553API
curl https://kongchang.com/api/v1/knowledge/claims/1009553MCP
get_claim(id=1009553)