Actions13
- Validate Birthdate (Validate_birthdate)
- Validate Cancel Intent (Validate_cancel_intent)
- Validate CEP (Validate_cep)
- Validate CNPJ (Validate_cnpj)
- Validate CPF (Validate_cpf)
- Validate Email (Validate_email)
- Validate Handoff (Validate_handoff)
- Validate License Plate BR (Validate_plate_br)
- Validate Name (Validate_name)
- Validate Phone (Validate_phone)
- Validate Postal Code (Validate_postal_code)
- Validate Reply Context (Validate_reply)
- Validate Yes/No (Validate_yes_no)
Validate Yes/No (Validate_yes_no)
AI-generatedSummary
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.