Skip to main content

n8n workflows

AI-School can start n8n workflows through a production webhook. This is useful when you want to trigger an automated process outside AI-School, for example creating a task, updating a CRM record, starting a report workflow, or forwarding form data to another system.

Example: news article on the school website​

Suppose the school has created an n8n workflow that publishes a news article on its WordPress website. In AI-School, the user only enters a short piece of text, for example a few sentences about a project week, sports day, or open day. That text starts the workflow in n8n.

The n8n workflow can then, for example:

  1. Turn the short text into a polished draft with an LLM node and a prompt that fits the school's tone of voice.
  2. Create a suitable illustration with a second LLM node, for example using the school colors and a recognizable illustrative style.
  3. Prepare or publish the text and image as a blog post on the WordPress website.

This is how AI-School and n8n work together: in AI-School, the user chooses the workflow and enters the required information. n8n then performs the automated steps and makes sure the news article appears neatly on the website.

What does this integration do?​

You start an n8n workflow from the workflow overview. If the workflow has fields, you fill them in first. Without fields, the workflow starts immediately.

  • If the workflow has no fields, the webhook is triggered immediately.
  • If the workflow has fields, a dialog opens first. The user fills in the form and then starts the workflow with the button.
  • The entered values are sent as JSON in a POST request to the n8n webhook.

Create an n8n workflow in AI-School​

An administrator can register the workflow as follows:

  1. Go to Assistants.
  2. Open Workflows.
  3. Choose New n8n workflow.
  4. Enter the workflow name and the n8n production URL.
  5. Set Header authentication with a header name and secret header value.
  6. Optionally add the fields that must be sent in the POST request.
  7. Save the workflow.

Fields​

  • Fields are optional.
  • Each field has one field name and a type.
  • Supported field types are short text, long text, number, yes/no and date.
  • Required fields must be completed before the workflow can be started.
  • The field name becomes the key in the JSON body sent to n8n.

Create a compatible workflow in n8n​

  1. Create a new workflow in n8n.
  2. Add a Webhook Trigger as the first node.
  3. Set HTTP Method to POST.
  4. Configure header authentication in n8n. Use the same header name and value that you enter in the application.
  5. Copy the Production URL of the webhook. Do not use the test URL.
  6. Activate the workflow in n8n.
  7. Use the received JSON body in the following n8n nodes.

Example JSON body​

If you define fields named prompt, customerName and date, n8n receives a JSON body like this:

{
  "prompt": "Create a short summary of the request.",
  "customerName": "Example organization",
  "date": "2026-09-22"
}

Important limitations​

  • Only webhook triggers are supported.
  • Only production webhook URLs are supported.
  • Test webhook URLs containing /webhook-test/ are rejected.
  • Only POST is supported.
  • Only generic header authentication is supported.
  • The header value is treated as a secret in the application.
  • The tenant is determined server-side from the signed-in user, not from a value sent by the browser.

Troubleshooting​

  • 404 or webhook not registered: activate the workflow in n8n and use the production URL.
  • Authentication error: check whether the header name and value are identical in both systems.
  • Missing data: check whether the field names in the application match the keys expected in n8n.
  • No request in n8n: verify that the workflow starts with a webhook trigger and uses POST.
WhatsApp