Mindket

Customer feedback form scored for sentiment in a sheet

Newversion 1 · updated

Overview

An n8n workflow with a feedback form. An OpenAI chat model labels each answer Positive, Negative or Neutral, and Google Sheets gets one new row with the answers, the contact details and the label.

Customer feedback form scored for sentiment in a sheet is an n8n workflow in the Business category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n.

At a glance

Runs in
  • n8n Cloud: import the file into a new workflow there
  • Your own n8n server: the same file and steps
  • Google Sheets: sort, filter or chart the rows there
  • A help desk or team chat: add a node after the sheet node to pass a row on

Platform

Connects 2 apps

How it works

Trigger

Feedback form

It starts when someone sends the Customer Feedback form with:

  • Their name
  • What the feedback is about: product, service or other
  • Their feedback
  • How to get in touch, which can stay empty

Actions

  1. The feedback is sent to an OpenAI chat model that labels its sentiment
  2. The label is joined to the form answers
  3. One new row goes into the Google Sheet with the time, topic, feedback, name, contact and label

Result

A row in your Google Sheet for every answer, with the sentiment label beside the customer’s own words

Integrations

What you need before you start.

OpenAI

Language model

Runs gpt-5.6-terra through a Basic LLM Chain to label each answer Positive, Negative or Neutral.

NeedsOpenAI API key

Google Sheets

Feedback log

Adds one row for each answer, with the time, topic, feedback, name, contact and sentiment.

NeedsA Google account to sign in with, and a sheet with eight headers

Workflow check

Checked by Mindket on 13 Nov 2026

Steps
4 steps, starting on a form
AI
1 step calls an AI model: Classify feedback with OpenAI
Sign-ins
Signs in to: Google Sheets and OpenAI
API keys
No API key is left in the file
Step types
Mindket’s checker reads all 4 of its step types

Read from the workflow’s file, not from a run.

About

What it is

This n8n workflow sorts customer feedback by mood and keeps it in a Google Sheet. A customer fills in a short form with a name, a topic (product, service or other), their feedback and a way to reach them. An OpenAI chat model reads the feedback and labels it Positive, Negative or Neutral. A Merge node joins that label to the form answers, and the sheet gets one new row. Five nodes do the work, beside five sticky notes.

Who it suits

Small shops, cafes, clinics and software teams who collect feedback through a link and want it in a sheet they already use. Skip it if you need a score, an alert for angry customers or a reply to the sender. As imported, the form only confirms the send, and the Urgent? column stays empty.

Who uses it, and how
IndustryWho uses itHow they use itExample
Restaurants and cafesOwnersPut the form’s link on receipts and table cardsA cafe owner sees at week’s end which comments mention slow service.
SoftwareSupport leadsLink the form from a help page or an app menuA support lead filters the sheet to Negative and reads those rows first.
RetailStore managersAsk online buyers about the product or the serviceA shop owner counts Product against Service comments each month.
Health and wellnessPractice managersCollect comments after a visit, with no medical details in themA physiotherapy clinic reads the Negative rows at Monday’s staff meeting.

You need a little n8n: import a file, add two credentials and make a sheet with eight headers.

Where to use it

Any n8n that can reach OpenAI and Google Sheets will run it. Rows land in the sheet of the Google account you sign in with.

  • n8n Cloud: import the file into a new workflow there
  • Your own n8n server: the same file and steps
  • Google Sheets: sort, filter or chart the rows there
  • A help desk or team chat: add a node after the sheet node to pass a row on

Setup

Download saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. Make the sheet before you import the file.

What you need first
NeedDetail
n8nOn n8n Cloud or on a server of your own
OpenAIAn API key that can use gpt-5.6-terra
GoogleAn account for a Google Sheets OAuth2 credential
A sheetA first tab named Sheet1, with eight headers in row 1
The sheet’s headers
ColumnWhat goes in it
TimestampThe time the form was sent
CategoryThe topic the customer picked
Customer FeedbackTheir words
Customer Name and Customer contactThe name and the contact detail they gave
Entered byForm, always
SentimentThe label from the model
Urgent?Nothing. The workflow leaves it empty
  1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json.
  2. Copy your sheet’s ID: the long part of its address between /d/ and /edit.
  3. Add a Google Sheets OAuth2 credential and select it in Add customer feedback to Google Sheets. Replace YOUR_SHEET_ID in that node with the ID.
  4. Add an OpenAI credential and select it in OpenAI Chat Model.
  5. Save, open the form’s test address and send one answer. A new row should appear in the sheet.
  6. Press Publish, then share the form’s production address.

How to use it

Open the form’s address, fill in the fields and send. The form says the response has been recorded at once, and the row follows a few seconds later. Open the sheet to read it.

What to change for a different result
To changeWhere
The labelsThe system message of Classify feedback with OpenAI, which asks for one of three words
The modelOpenAI Chat Model, gpt-5.6-terra in Mindket’s copy
The formThe title, description and topic choices in Submit form with customer feedback
Where rows goAdd customer feedback to Google Sheets, or a node you add after it

Example

A bike shop adds the form’s link to its order emails. A buyer named Mei picks Service and writes that the delivery came two days late, but the person on the phone was kind.

The sheet gets a row with the time, Service, Mei’s words, her name, her contact detail, Form in Entered by and a label in Sentiment. A mixed comment like hers can land on any of the three words, so read the text beside the label.

For newcomers and experts

If you are new. n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. This one is short. The form feeds two paths at once: one through the model, one straight to the Merge node. After a test, open Merge sentiment with form content to see the two halves joined.

For experts. Mindket’s copy swaps the older OpenAI text node for a Basic LLM Chain, so the reply still leaves as text.

Where to look closer
NodeWhat it doesWhat to know
Submit form with customer feedbackForm Trigger 1 with four fieldsIt answers when the form is sent, so the label never goes back to the sender
Classify feedback with OpenAIBasic LLM Chain 1.5 with a fixed prompt, a system message and the chat modelThe reply leaves as text, which the sheet node reads as Sentiment
Merge sentiment with form contentMerge 2.1, combine mode, multiplexThe model’s reply is its first input and the form its second
Add customer feedback to Google SheetsGoogle Sheets 4.1, append, with each column set by handUrgent? is in the node’s schema, but no value is set for it

Good to know

The model in the original copy is gone, and the form is open once published.

  • Model: the original copy used n8n’s older OpenAI node, whose default gpt-3.5-turbo-instruct OpenAI shut down on 28 September 2026. Mindket’s copy uses a Basic LLM Chain with gpt-5.6-terra, the replacement OpenAI’s deprecations page names, read on 12 November 2026. That page lists no shutdown date for it
  • One word: the older node cut its answer at 16 tokens. A chain has no such cut, so Mindket’s copy asks for one word in a system message
  • The label: the model writes it, and a mixed comment can land on any of the three words
  • Billing: OpenAI bills one chat call for each answer
  • Open form: once the workflow is published, anyone with the form’s address can add rows and spend your OpenAI key
  • Your data: only the feedback text goes to OpenAI. The name and the contact detail go to your sheet alone
  • Credentials: the JSON holds none

README and files

README

Customer feedback form scored for sentiment in a sheet

An n8n workflow with a four-field feedback form. A visitor gives a name, a topic, their feedback and a way to reach them.
An OpenAI chat model labels the sentiment of the feedback, and a Google Sheet gets one row with the answers and the label.

What is inside

  • workflow.json: the workflow as n8n exports it, ten nodes, five of them sticky notes. It holds no credential.
  • README.md: these notes.

What we changed from the original copy

  • Classify feedback with OpenAI was n8n's older OpenAI node, which sends a text-completion request. Its default model,
    gpt-3.5-turbo-instruct, was shut down by OpenAI on 28 September 2026, and the replacement it names, gpt-5.6-terra,
    does not take completion requests. The node is now a Basic LLM Chain with an OpenAI Chat Model node set to
    gpt-5.6-terra. It keeps its name and its prompt, and its answer still leaves as text.
  • The chain also has a short system message that asks for one word: Positive, Negative or Neutral. The older node stopped
    its answer after 16 tokens by default, which kept it short. A chain has no such stop.
  • The Google Sheets node pointed at the author's own sheet. Its ID is now YOUR_SHEET_ID and its tab is named Sheet1.
  • The note with the instructions linked to the author's example sheet. It now lists the eight column headers instead.
  • The form's description read orproducts. It now reads or products.
  • The credential links and the form's webhook ID are gone, so you select your own.
  • Nothing else. The file has no Code node, and its expressions needed no repair.

Before you start

  • An n8n instance, on n8n Cloud or your own server.
  • An OpenAI API key that can use gpt-5.6-terra.
  • A Google account for a Google Sheets OAuth2 credential.
  • A Google Sheet with a first tab named Sheet1 and these headers in row 1: Timestamp, Category, Customer Feedback,
    Customer Name, Customer contact, Entered by, Urgent? and Sentiment.

Set it up

  1. In n8n, create a workflow, open its menu and choose Import from File. Pick workflow.json.
  2. Copy your sheet's ID: the long part of its address between /d/ and /edit.
  3. Add a Google Sheets OAuth2 credential and select it in Add customer feedback to Google Sheets. Replace
    YOUR_SHEET_ID in that node with the ID. You can also pick the sheet from the node's list.
  4. Add an OpenAI credential and select it in OpenAI Chat Model.
  5. Save, open the form's test address and send one answer. A new row should appear in the sheet.
  6. Press Publish, then share the form's production address.

The form confirms with "Your response has been recorded" at once, and the run goes on behind it.

How a run goes

  1. Submit form with customer feedback (Form Trigger 1) takes four fields: Name, What is your feedback about? (a
    dropdown of Product, Service and Other), Your feedback and How do we get in touch with you? (the only optional one).
  2. Two lines leave the form. One goes to Classify feedback with OpenAI, and one goes straight to the Merge node.
  3. The chain puts the feedback into its prompt and sends it to OpenAI Chat Model. The reply leaves as text.
  4. Merge sentiment with form content (Merge 2.1, combine, multiplex) joins the reply and the form answers into one item.
  5. Add customer feedback to Google Sheets (Google Sheets 4.1, append) writes the row: Timestamp from submittedAt,
    the topic, the feedback, the name, the contact, Sentiment from text and Form in Entered by.

Change the look

  • The labels: the system message of Classify feedback with OpenAI. Ask for a score or for your own categories there.
  • The model: OpenAI Chat Model.
  • The form: the title, the description, the dropdown choices and the labels in Submit form with customer feedback. A new
    field needs a column header in the sheet and a line in the columns of Add customer feedback to Google Sheets.
  • Where the rows go: swap the Google Sheets node for Airtable, Slack or a database, or add a node after it.

Good to know

  • Urgent? is one of the columns in the node, but nothing sets a value for it, so it stays empty.
  • The model writes the label. A mixed comment can land on any of the three words, so keep the feedback beside it.
  • OpenAI's deprecations page, read on 12 November 2026, lists no shutdown date for gpt-5.6-terra.
  • Each answer is one chat call. Only the feedback text goes to OpenAI. The name and the contact go to your sheet alone.
  • Once the workflow is published, anyone with the form's address can add rows and spend your OpenAI key.
Files
NOTICE.md  604 B
README.md  5 KB
workflow.json  9 KB

3 files, 14 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-12

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

Huashu Design

alchaincyf · Skill

Turns a one-line request in your AI agent into a finished design: a launch animation, a clickable app prototype, an editable slide deck, an infographic or a se…

New29.4k

Guizang PPT Skill

op7418 · Skill

Skill that makes single-file HTML slide decks, slide illustrations and platform covers in two visual styles, with a presenter mode for rehearsal. For speakers…

New29.8k

Claude Code Skills & Plugins

alirezarezvani · Skill

Adds 411 ready-made skills for Claude Code and other coding agents, grouped by role from engineering and product to marketing, finance and compliance. Installs…

New29.8k

Similar in Business

See all in Business

pplx-decider-v1.1-27b

perplexity-ai · Kit

Picks the best option for a decision from text and images, such as which team should handle a request, with a probability for each choice, for developers who b…

New

NuExtract3

numind · Kit

Reads documents as text or images and fills a JSON template with the fields you ask for, or converts the pages to Markdown. A 4B model for teams that process s…

New

Drex DLM

nace-ai · Kit

Scores yes or no, multiple choice and rating questions about a document in one pass, with a probability for every option. An 8B decision model from Nace.AI tha…

New