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 Reply Context (Validate_reply)
AI-generatedSummary
Sends an agent message and the user's reply to the NaLU AI service to analyze conversational context, such as whether the user is making a counter-proposal (e.g. changing installments vs. currency amounts). Returns the service's JSON response as-is.
Inputs
- agent_message (required) — The message the agent sent, e.g. an offer like "Posso parcelar em 20x de R$100. Topa?".
- user_reply (required) — The user's reply to that message, e.g. "Bora em 48?".
Output shape
One JSON object per input item, containing the parsed response from the NaLU AI endpoint (POST https://naluai.dev/v1/extract/reply). Each output is paired to its input item.
The response fields are not defined in the node source; they come directly from the API. Requires the naluAiApi credential. The Language parameter is not sent for this operation. If Continue On Fail is enabled, a failed item returns {error: message} instead of stopping the workflow.
Examples
Example 1: Interpret a customer's counter-offer in a debt negotiation chatbot.
Validator: Validate Reply Context; Agent Message: "Posso parcelar em 20x de R$100. Topa?"; User Reply: "Bora em 48?"
Example 2: Map chat history fields to the validator using expressions.
Agent Message: {{ $json.lastBotMessage }}; User Reply: {{ $json.userText }}