Mindket
English
English简体中文
Sign inSign up
StoreMCPSkillsCalculatorLearnPriceBlog
Discover
Research311Writing59Business95Legal13Finance & accounting33Marketing & SEO174Developer1,416Productivity387Education81Companions14
Help and support
Language
English简体中文

Mock user CSV files generated by OpenAI and saved to disk

by Mindketn8n workflowDeveloper
Newversion 1 · updated
Nodes9Apps1Like

Overview

  1. When clicking "Execute Workflow"
  2. OpenAI
  3. Split In Batches
  4. Parse JSON
  5. Make JSON Table
  6. Convert to CSV
  7. Strip UTF BOM bytes
  8. Create valid binary
  9. Save to Disk
Mock user CSV files generated by OpenAI and saved to disk, picture 1
‹2 / 2›

An n8n workflow that makes test data. It asks OpenAI for three lists of ten made-up users and saves each list as a CSV file in a folder you choose.

Mock user CSV files generated by OpenAI and saved to disk is an n8n workflow in the Developer 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
  • Your own n8n server: write to a folder that n8n may use
  • n8n Cloud: use a folder under /home/node/, and note that files there may not last
  • Other records: change the prompt for another kind of data
  • More or fewer files: change the number of completions in the options of OpenAI

Platform

n8nWorkflow automation, in n8n’s cloud or on your own server
Connects 1 app

How it works

Trigger

Manual start

It starts when you press Test workflow, with:

  • Nothing: the prompt is part of the workflow

Actions

  1. OpenAI is asked for three lists of ten made-up users in one request
  2. Each answer is passed on one at a time and turned into a list
  3. The list is split into ten items and written as a CSV file with a header row
  4. The byte order mark is removed and the file is rebuilt as a text file
  5. The file is saved to your folder, and the loop takes the next answer

Result

Three CSV files in your folder, each with ten made-up users

Integrations

What you need before you start.

OpenAI

Language model

Writes three lists of ten made-up users as JSON.

NeedsAn OpenAI API key

Workflow check

Checked by Mindket on 13 Nov 2026

Steps
9 steps, starting by hand
AI
1 step calls an AI model: OpenAI
Sign-ins
No sign-in
API keys
No API key is left in the file
Step types
Mindket’s checker reads all 8 of its step types

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

About

What it is

This n8n workflow makes test data. It asks an OpenAI model for three lists of ten made-up users, and each list is saved as a CSV file with a name such as funny_names_1.csv. The names come from famous fiction characters. Nine nodes do the work, beside two sticky notes.

Who it suits

Developers and testers who need sample users to try an import, a report or a database load. The data is invented, but an address may belong to a real person, so do not send mail to it. The files land on the machine that runs n8n.

Who uses it, and how
IndustryWho uses itHow they use itExample
SoftwareDevelopersFill a test database with sample usersA developer loads the three files into a staging table.
QualityTestersTry an import form with files of a known shapeA tester uploads the files and checks that every column is read.
DataAnalystsPractice a CSV cleanup on harmless dataAn analyst builds a pivot on the subscribed and date columns.
EducationTeachersGive a class a file to exploreA teacher hands each student one of the three files.

You need some n8n skill: import a file, add one account and choose a folder on the machine. Nothing in the file states a setup time.

Where to use it

Any n8n that can reach OpenAI and write to a folder will run it.

  • Your own n8n server: write to a folder that n8n may use
  • n8n Cloud: use a folder under /home/node/, and note that files there may not last
  • Other records: change the prompt for another kind of data
  • More or fewer files: change the number of completions in the options of OpenAI

Setup

Download saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. Two things need your choice, an OpenAI account and a folder.

What you need first
NeedDetail
n8nA server of your own, or n8n Cloud with a path under /home/node/
OpenAIAn API key
A folderOne that n8n may write to, written out in full
  1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json.
  2. Add an OpenAI credential and select it in OpenAI.
  3. In Save to Disk, replace <YOUR_N8N_FILES_FOLDER> with the full path of a folder that n8n may write to. On a self-hosted n8n of version 2 or later, the default is the .n8n-files folder in the home folder of the user that runs n8n.
  4. Choose Test workflow and open the folder.

How to use it

Run the workflow by hand. Three files appear in the folder, each with ten users. Open one to check the columns.

What to change for a different result
To changeWhere
The number of filesThe number of completions in the options of OpenAI
The number of users and the columnsThe prompt in OpenAI
The file namesThe file name in Convert to CSV and in Create valid binary
The folderThe path in Save to Disk

Example

You run the workflow with the prompt as it comes.

First OpenAI returns three answers, and Split In Batches passes them on one at a time. Then Parse JSON turns the text of an answer into a list, and Make JSON Table splits the list into ten items. After that Convert to CSV builds one file from the ten items, and the two byte order nodes clean it. At the end Save to Disk writes funny_names_1.csv, and the loop takes the next answer.

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. A loop hands items to the steps after it one at a time and takes them back at the end, so the same steps run once for each file. A CSV file is plain text, with one user in each row and the column names in the first row.

For experts. Four of the nodes are old ones that n8n now hides from its node list, and they still run.

Where to look closer
NodeWhat it doesWhat to know
OpenAIAn OpenAI node 1.8, Text resource, Message a Model, set to gpt-5.6-sol with 3 completionsIt sends a limit of 6000 tokens and a low reasoning effort, and returns one item for each answer
Parse JSONA Set node 3 that runs JSON.parse on message.contentIt breaks if the model wraps the list in Markdown fences
Convert to CSVA Spreadsheet File node 2 that writes a CSV with a header rowThe file name uses the index of the answer
Strip UTF BOM bytesA Move Binary Data node that moves the file into a text field without the byte order markCreate valid binary turns the text back into a file
Save to DiskA Write Binary File nodeIt stops with an access error outside the folders n8n allows

Good to know

It calls OpenAI on every run, and it writes files to disk.

  • Hidden nodes: n8n’s source, read on 12 November 2026, hides Item Lists, Spreadsheet File, Move Binary Data and Write Binary File from the node list, and they still run. In a new workflow, Split Out, Convert to File and Read/Write Files from Disk do the same jobs
  • The model: the original asked for gpt-4, which OpenAI’s deprecations page says is shut down on 23 October 2026, with gpt-5.6-sol as its replacement. Mindket’s copy uses gpt-5.6-sol
  • Tokens: the limit counts the reasoning tokens too, so Mindket’s copy sets 6000 and a low reasoning effort. Raise the limit if an answer is cut
  • Where files go: the original wrote into ./.n8n/, the folder n8n keeps for its own state. n8n’s documentation says not to write there, and n8n 2.0 limits file access to ~/.n8n-files by default. Mindket’s copy asks for a folder you choose
  • n8n Cloud: its documentation says files written there are not guaranteed to last across restarts
  • A sample answer: the original carried pinned sample output, so it ran without OpenAI. This copy carries none, so each run costs a little
  • Mindket did not run it. It read OpenAI’s and n8n’s documentation and n8n’s source

README and files

README

Mock user CSV files generated by OpenAI and saved to disk

An n8n workflow that makes test data. It asks an OpenAI model for three lists of ten made-up users and saves each list as a CSV file. The files are named funny_names_1.csv, funny_names_2.csv and funny_names_3.csv.

What is inside

  • workflow.json: the workflow as n8n exports it, 9 nodes beside 2 sticky notes. It holds no credential.
  • README.md: these notes.

What we changed from the original copy

  • The model gpt-4 is shut down on 23 October 2026, says OpenAI’s deprecations page, read on 12 November 2026. It names gpt-5.6-sol as the replacement. The step was the old OpenAI node at version 1, which cannot send the limit that the newer models need. Mindket rebuilt it as the OpenAI node at version 1.8 with gpt-5.6-sol, three completions, a limit of 6000 tokens and a low reasoning effort. The temperature is left out, because the node sends it only when it is set.
  • The original wrote to ./.n8n/. That is the folder n8n keeps for its own state, and n8n’s documentation says not to write there. Mindket’s copy writes to <YOUR_N8N_FILES_FOLDER>, a folder you choose.
  • The original carried a pinned sample answer from the model. Mindket’s copy carries none.
  • The sticky notes are reworded.
  • No credential is inside.

Before you start

  • An n8n instance. On a self-hosted n8n you may write to the folder you set. On n8n Cloud the node reaches only paths under /home/node/.
  • An OpenAI API key.
  • A folder that n8n may write to.

Set it up

  1. In n8n, create a workflow, open its menu and choose Import from File. Pick workflow.json.
  2. Add an OpenAI credential and select it in OpenAI.
  3. In Save to Disk, replace <YOUR_N8N_FILES_FOLDER> with the full path of a folder that n8n may write to. On a self-hosted n8n of version 2 or later, the default is the .n8n-files folder in the home folder of the user that runs n8n. The setting N8N_RESTRICT_FILE_ACCESS_TO changes it.
  4. Choose Test workflow and open the folder.

How a run goes

  1. When clicking "Execute Workflow" starts the run, and OpenAI asks for ten random users in a JSON list, three times in one request. It returns three items.
  2. Split In Batches passes the items on one at a time.
  3. Parse JSON turns the text of the answer into a list in the field content. Make JSON Table splits it into ten items.
  4. Convert to CSV writes the ten items as one CSV file with a header row. The name uses the index of the answer.
  5. Strip UTF BOM bytes moves the file into a text field without its byte order mark. Create valid binary turns the text back into a CSV file.
  6. Save to Disk writes the file to your folder, and the loop goes back to Split In Batches for the next answer.

Change the look

  • The number of files: the number of completions in the options of OpenAI.
  • The number of users and the columns: the prompt in OpenAI.
  • The file names: the file name in Convert to CSV and in Create valid binary.
  • The folder: the path in Save to Disk.

Good to know

  • n8n’s source, read on 12 November 2026, hides Item Lists, Spreadsheet File, Move Binary Data and Write Binary File from the node list, and they still run. In a new workflow, Split Out, Convert to File and Read/Write Files from Disk do the same jobs.
  • The limit of 6000 tokens counts the reasoning tokens too. Raise it if an answer is cut.
  • Parse JSON breaks if the model wraps its list in Markdown fences. The prompt asks for a single line of JSON.
  • The names come from fiction and the addresses are made up, but an address may belong to a real person. Do not send mail to them.
  • n8n Cloud’s documentation says files written there are not guaranteed to last across restarts.
  • Mindket did not run this workflow. It read OpenAI’s and n8n’s documentation and n8n’s source.
  • The JSON holds no credential.
Files
NOTICE.md  594 B
README.md  4 KB
workflow.json  8 KB

3 files, 12 KB, downloaded as a zip.

What’s new

  • Version 1 · 2026-11-13

Reviews

No ratings yet

Write a review

No reviews yet.

More from Mindket

See all from Mindket

upscaler

uwg · Kit

Holds a set of image upscaling models gathered from the OpenModelDB community, for people who want to enlarge low-resolution pictures with AI on their own comp…

New

Pixel Art XL

nerijs · Kit

A pixel art style add-on for Stable Diffusion XL that turns text prompts into pixel-style images, with an optional LCM LoRA for faster runs. For game makers, d…

New

VibeVoice-1.5B

microsoft · Kit

Turns written conversations into spoken audio with up to four speakers and about 90 minutes of speech, an open Microsoft text-to-speech model for research on p…

New

Similar in Developer

See all in Developer

voicetut-egyptian-tashkeel

masterofaudio2077 · Kit

Reads Egyptian Arabic text aloud and follows the short vowel marks you write into it. A fine-tune of VoiceTut-TTS that keeps its 19 built-in voices and voice c…

New

Meta-Llama-3.1-8B-Instruct-AWQ-INT4

hugging-quants · Kit

Runs Meta's Llama 3.1 8B Instruct chat model in 4-bit AWQ form, so it fits on a GPU with about 4 GiB of free memory for the weights. For developers who want a…

New

Ru-Jev

besktech · Kit

Scores a Russian-first decision from a context and a list of options, giving a probability for yes/no, choice or rating questions. Runs on a plain CPU, for tea…

New