Build an FAQ support chat in n8n

Download a small workflow, connect a MandAPI credential, and answer support questions from an editable business FAQ.

Configure this n8n FAQ workflow for MandAPI in a local reviewable copy. Use Chat Trigger, Basic LLM Chain and an OpenAI Chat Model; keep the final Edit Fields mapping from text to output. Create an OpenAI-type credential named MandAPI with Base URL https://api.mandapi.com/v1, and let me enter the secret myself. Never put the key in exported JSON or use an OpenRouter credential for it. Set a real Chat Completions MODEL_ID available to my key and explicitly keep responsesApiEnabled false. Preserve the private, inactive trigger until I choose to publish it. Replace the sample FAQ only with facts I provide. Unknown questions and refund requests should show a human-review message without sending email or taking financial actions. Verify node parameters locally; do not claim import or runtime success without actually checking it. A live model request requires my authorization.

Download the workflow

Download the English FAQ template. A Spanish template is also available.

The demonstration uses four nodes: Chat Trigger → Basic LLM Chain → Edit Fields, with an OpenAI Chat Model attached to the chain. It answers from a static FAQ for a fictional shop. You do not need email, a vector database or a WhatsApp account to try the editor chat.

Import and connect MandAPI

In your existing n8n instance, use the workflow menu's Import from File option and select the downloaded JSON. The workflow is inactive and its Chat Trigger is private.

Open MandAPI Chat Model and create an OpenAI credential named MandAPI. Enter your own MandAPI API key and set the credential's Base URL to https://api.mandapi.com/v1. Leave Organization ID empty unless your own setup requires it. Select that credential on the model node.

Use the OpenAI credential type. The dedicated OpenRouter credential is tied to OpenRouter's service and is not the right place for a MandAPI key.

Choose a model and edit the FAQ

In the model node, choose ID mode and replace MODEL_ID with a Chat Completions model available to your MandAPI key. Keep Use Responses API disabled; its saved JSON parameter is responsesApiEnabled: false. The template also sets the model node's Base URL to MandAPI.

Open Answer from the FAQ, expand its System message and replace the demonstration business, hours and policies with your own verified information. The example asks the model to use only those facts. It has no order lookup, persistent memory or external tools.

Try three questions

Open n8n's test chat and ask:

Question	Expected behavior
What are your opening hours?	State the hours in the demonstration FAQ.
Where is order 12345 right now?	Suggest a person review the case; do not invent tracking.
I want a refund.	Show the human-support suggestion.

The suggestion is text only: this template does not notify support, create a ticket, cancel an order or process a refund. Each test sends a real model request and uses your API credits.

Check and customize

Edit Fields maps the chain's text field to output, which the chat receives in When Last Node Finishes mode. If the chat displays no answer, inspect these fields in the execution. Check the selected credential, model ID, balance and Base URL if the model call fails.

This download was checked for JSON structure and node parameters against n8n's official source on 30 October 2026. It has not been imported into a running n8n instance or tested with a live MandAPI call here. If your n8n version does not recognize a listed node version, update or recreate that node using the same settings before testing.