NaLU AI icon

NaLU AI

Semantic data validation and extraction for chatbots using NaLU AI.

Validate Yes/No (Validate_yes_no)

AI-generated

Summary

Classifies whether a user's chatbot reply means yes or no, including indirect answers, by sending the agent's question and the user's reply to the NaLU AI API.

Inputs

  • Agent Prompt/Question (required) — The question or statement the chatbot sent to the user (sent as agent_input). It gives the model context for interpreting the reply.
  • User Reply (required) — The user's response to be evaluated for yes/no intent (sent as user_input).
  • Language — Conversation language: English (en), Portuguese (Brazil) (pt-BR, the default), or Spanish (es).

Output shape

One output item per input item, whose json is the parsed response from the NaLU AI API (POST https://naluai.dev/v1/extract/yes_no).

The exact response fields are not defined in the node source; they come straight from the API. Requires naluAiApi credentials. With Continue On Fail enabled, a failed item returns {error: message} instead of stopping the workflow. Each output is paired to its input item.

Examples

Example 1: Confirm a user agreed to a proposal in a Portuguese chatbot.

Agent Prompt/Question: "Posso confirmar seu agendamento?"; User Reply: "Pode ser, claro"; Language: pt-BR.

Example 2: Interpret an indirect English answer.

Agent Prompt/Question: "Do you want to receive the invoice by email?"; User Reply: "Not really, send it by mail"; Language: en.

Links

Discussion