Mindket
English
English简体中文
Sign inSign up
StoreMCPSkillsCalculatorLearnPriceBlog
Discover
Research311Writing59Business95Legal13Finance & accounting33Marketing & SEO175Developer1,420Productivity390Education81Companions14
Help and support
Language
English简体中文

Google Sheets form feedback summarized by AI and emailed

by Mindketn8n workflowBusiness
Newversion 1 · updated
Nodes6Apps3Like

Overview

  1. When clicking "Test workflow"
  2. Get Google Sheets records
  3. Aggregate responses into arrays
  4. Summarize via GPT model
  5. Convet from Markdown to HTML
  6. Send via Gmail
Google Sheets form feedback summarized by AI and emailed, picture 1
‹2 / 2›

An n8n workflow that gathers the answers of a feedback form from a Google Sheet, has OpenAI write a short report and emails it as HTML through Gmail.

Google Sheets form feedback summarized by AI and emailed 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 there and run it by hand
  • Your own n8n server: the same file and steps
  • Google Sheets: the form answers
  • Gmail: where the report arrives

Platform

n8nWorkflow automation, in n8n’s cloud or on your own server
Connects 3 apps

How it works

Trigger

Manual run

It starts when you click Test workflow in n8n:

  • The sheet and tab to read, set in Get Google Sheets records
  • The three question fields, set in Aggregate responses into arrays
  • The address to email, set in Send via Gmail

Actions

  1. The rows of the Google Sheet tab are read
  2. The answers to each question are gathered into one list
  3. OpenAI writes a report with an overall sentiment and ideas to improve
  4. The Markdown reply is turned into HTML
  5. Gmail emails the report

Result

An HTML summary of the form’s feedback, in your inbox

Integrations

What you need before you start.

Google Sheets

Form answers

Holds the rows of answers the workflow reads.

NeedsA Google Sheets credential and the sheet’s id

OpenAI

Language model

Writes the report from the lists of answers.

NeedsAn OpenAI API key

Gmail

Mail

Emails the finished report as HTML.

NeedsA Gmail credential and an address

Workflow check

Checked by Mindket on 13 Nov 2026

Steps
6 steps, starting by hand
AI
No step calls an AI model
Sign-ins
Signs in to: Google Sheets, OpenAI and Gmail
API keys
No API key is left in the file
Step types
Mindket’s checker reads all 6 of its step types

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

About

What it is

This n8n workflow turns the answers of a feedback form into one short report. It reads the rows of a Google Sheet and gathers the answers to each question into a list. OpenAI writes a report with an overall sentiment and ideas to improve, and Gmail emails it as HTML. Six nodes run it, beside four sticky notes.

Who it suits

Event organizers and small teams who collect feedback in a sheet and want a quick read of it. Skip it if the answers hold personal details you cannot send to OpenAI.

Who uses it, and how
IndustryWho uses itHow they use itExample
EventsEvent organizersRead what went well and what to fixAn organizer gets a one-page report after a workshop.
EducationCourse teamsSummarize learner commentsA course lead sees the main requests from a long list of comments.
Customer careSupport leadsCondense survey answersA lead reads one mail instead of a long sheet.
ProductProduct ownersSpot repeated ideasAn owner sees which improvement ideas came up again and again.

You need a little n8n and a sheet of answers: import a file, add three credentials and paste your sheet’s id.

Where to use it

Any n8n that can reach Google Sheets, OpenAI and Gmail will run it. The report arrives in the inbox you set.

  • n8n Cloud: import the file there and run it by hand
  • Your own n8n server: the same file and steps
  • Google Sheets: the form answers
  • Gmail: where the report arrives

Setup

Download saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. Setup takes three credentials, a sheet id and an address.

What you need first
NeedDetail
n8nOn n8n Cloud or on a server of your own
GoogleAn account for Sheets and Gmail
SheetA tab named Form Responses 1, with one column for each question
OpenAIAn API key
  1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json.
  2. Add credentials for Google Sheets, OpenAI and Gmail, and select them in the nodes that ask for one.
  3. In Get Google Sheets records, replace <YOUR_SHEET_ID> with your sheet’s id.
  4. In Send via Gmail, replace <YOUR_EMAIL_ADDRESS> with the address that should get the report.
  5. If your form asks other questions, change the three question names in Aggregate responses into arrays.
  6. Click Test workflow and read the mail.

How to use it

Click Test workflow. The report reaches your inbox a short while later. For a regular report, swap the manual trigger for a schedule. Try it first on a sheet with a few answers.

What to change for a different result
To changeWhere
The shape of the reportThe system message in Summarize via GPT model
The questionsAggregate responses into arrays and the user message
Who gets the mailSend via Gmail
When it runsThe trigger node

Example

An organizer runs a workshop and collects answers to three questions in a sheet. Some people wrote one line, and others wrote a paragraph.

The report opens with an overall sentiment, which is mostly positive, and then lists the ideas to improve, such as a longer break and a clearer schedule. It arrives by email as formatted text.

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. Here one box reads the sheet, one gathers the answers, one asks OpenAI, one converts the text and one sends the mail. Try it with a sheet that holds a few rows.

For experts. An Aggregate node builds one list per question, and an HTTP Request posts them to Chat Completions. A Markdown node converts the reply to HTML for Gmail.

Where to look closer
NodeWhat it doesWhat to know
Aggregate responses into arraysCollects each question’s answers into a listA field path such as ['What went great?'] comes out as the plain field name
Summarize via GPT modelAsks Chat Completions for the reportIt names gpt-6-luna and sets no temperature
Convet from Markdown to HTMLTurns the reply into HTMLIt reads choices[0].message.content
Send via GmailEmails the HTMLThe node’s attribution line is switched off

Good to know

This workflow sends every answer in one request, so a long form with many answers can pass the model’s limits.

  • The repair: n8n’s older OpenAI chat node named gpt-4-turbo-preview. OpenAI’s deprecations page, read on 12 November 2026, lists it as shut down on 26 March 2026. This copy calls Chat Completions with gpt-6-luna, the replacement the page names for the gpt-4.1 family
  • Temperature: the old setting of 0.3 is gone, since the model page lists no temperature
  • Placeholders: the sheet id and the address are yours to fill in
  • Not run: this copy was not run against Google Sheets, OpenAI or Gmail
  • Your data: the answers go to OpenAI, and the report goes to your address
  • Credentials: the JSON holds none

README and files

README

Google Sheets form feedback summarized by AI and emailed

An n8n workflow that reads the answers of a feedback form from a Google Sheet, gathers them into one list per question and asks OpenAI for a short report. The report is turned into HTML and emailed through Gmail.

What is inside

  • workflow.json: the workflow as n8n exports it, ten nodes: six that do the work and four sticky notes. It holds no credential.
  • README.md: these notes.

What we changed from the original copy

  • The credential links are gone. Select your own for Google Sheets, OpenAI and Gmail.
  • The summary step was n8n's older OpenAI chat node with the model gpt-4-turbo-preview. OpenAI's deprecations page, read on 12 November 2026, lists gpt-4-0125-preview, which includes gpt-4-turbo-preview, as shut down on 26 March 2026, and points to gpt-5 or gpt-4.1. The same page lists the gpt-4.1 family for shutdown on 14 January 2027 with gpt-6-luna as its replacement, so this copy names gpt-6-luna.
  • The step is now an HTTP Request to Chat Completions, so the model name is plain text in the body. The temperature of 0.3 is gone, because the model page for gpt-6-luna lists no temperature setting. Convet from Markdown to HTML now reads the answer from choices[0].message.content.
  • The sheet id and the address are placeholders: <YOUR_SHEET_ID> and <YOUR_EMAIL_ADDRESS>. The tab is still named Form Responses 1.
  • The notes are rewritten. One of them linked to the author's own sheet, and that link is removed.
  • Nothing else.

Before you start

  • An n8n instance, on n8n Cloud or your own server.
  • A Google account for Sheets and Gmail, and an OpenAI API key.
  • A sheet with the answers in a tab named Form Responses 1. Its first row holds the headers What went great?, How can we improve? and What is the chance of recommending our event?. The workflow's own note says a sheet linked to Google Forms or a standalone sheet both work.

Set it up

  1. In n8n, create a workflow, open its menu and choose Import from File. Pick workflow.json.
  2. Add a Google Sheets credential and select it in Get Google Sheets records. Replace <YOUR_SHEET_ID> with your sheet's id and check the tab name.
  3. Add an OpenAI credential and select it in Summarize via GPT model.
  4. Add a Gmail credential and select it in Send via Gmail. Replace <YOUR_EMAIL_ADDRESS> with the address that should get the report.
  5. If your form asks other questions, change the three field names in Aggregate responses into arrays and the matching lines of the user message in the request body.
  6. Click Test workflow and look at the mail.

How a run goes

  1. When clicking "Test workflow" starts the run by hand.
  2. Get Google Sheets records reads the rows of the tab.
  3. Aggregate responses into arrays gathers the answers to each question into one list. The result is a single item with one field per question.
  4. Summarize via GPT model posts two messages to OpenAI. The system message asks for an overall sentiment and then ideas to improve, in Markdown. The user message holds the three lists, each joined with | .
  5. Convet from Markdown to HTML turns the reply into HTML.
  6. Send via Gmail emails the HTML with the subject Feedback form response, and leaves out n8n's attribution line.

Change the look

  • The shape of the report: the system message in the body of Summarize via GPT model.
  • The questions: the field names in Aggregate responses into arrays and the lines of the user message.
  • Who gets the mail, and its subject: Send via Gmail.
  • When it runs: swap the manual trigger for a schedule.

Good to know

  • All rows go into one request. A long form or a great many answers can pass the model's limits, so split the questions in that case, as the workflow's own note advises.
  • Each run costs one OpenAI call.
  • gpt-6-luna reasons at medium effort by default. Add "reasoning_effort" to the body to change that.
  • This copy was not run against Google Sheets, OpenAI or Gmail.
  • The answers go to OpenAI, and the report goes to the address you set.
  • The JSON holds no credential.
Files
NOTICE.md  659 B
README.md  4 KB
workflow.json  7 KB

3 files, 12 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