Mindket
English
English简体中文
Sign inSign up
StoreMCPSkillsCalculatorLearnPriceBlog
Discover
Research308Writing59Business95Legal13Finance & accounting33Marketing & SEO172Developer1,379Productivity382Education81Companions14
Help and support
Language
English简体中文

WordPress posts put in a category by AI from the title

by Mindketn8n workflowWriting
Newversion 1 · updated
Nodes5Apps2Like

Overview

  1. When clicking ‘Test workflow’
  2. OpenAI Chat Model
  3. Get All Wordpress Posts
  4. AI Agent
  5. Wordpress
WordPress posts put in a category by AI from the title, picture 1
‹2 / 2›

An n8n workflow that reads every published post of a WordPress site, asks an AI model to pick one category for each post from its title and saves it on the post.

WordPress posts put in a category by AI from the title is an n8n workflow in the Writing 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
  • Your own n8n server: the same file and steps
  • WordPress: where the posts are read and updated
  • OpenAI: where each title is sorted

Platform

n8nWorkflow automation, in n8n’s cloud or on your own server
Connects 2 apps

How it works

Trigger

By hand

It starts when you click Test workflow in n8n:

  • The category list, set in the prompt of AI Agent
  • The model, set in OpenAI Chat Model
  • Which posts, set in Get All Wordpress Posts

Actions

  1. Every published post is fetched
  2. The title and your category list go to the AI model
  3. The model answers with one category id
  4. The id is saved as the post’s category in WordPress

Result

Each published post sits in one of your categories

Integrations

What you need before you start.

WordPress

Posts

Supplies the posts and receives the categories.

NeedsA WordPress credential with a username, password and site address

OpenAI

Category picker

Chooses one category for each title.

NeedsAn OpenAI API key

Workflow check

Checked by Mindket on 13 Nov 2026

Steps
4 steps, starting by hand
AI
1 step calls an AI model: AI Agent
Sign-ins
Signs in to: WordPress and OpenAI
API keys
No API key is left in the file
Step types
Mindket’s checker reads all 3 of its step types

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

About

What it is

This n8n workflow sorts the posts of a WordPress site into categories. It fetches every published post, gives each title to an AI model together with your list of categories and saves the category the model picks. Five nodes run it, beside four sticky notes.

Who it suits

Bloggers and content teams with many posts that have no clear categories. Skip it if posts already have categories you want to keep, since the update replaces them.

Who uses it, and how
IndustryWho uses itHow they use itExample
PublishingBloggersOrganize an archiveA blogger with 80 old posts gives each one a category in a single run.
MarketingContent teamsTidy a site before a redesignA team sorts its blog into six topics before it builds new menus.
AgenciesWeb agenciesClean up a client’s blogAn agency categorizes a client’s posts after a site move.
EducationCourse sitesGroup articles by topicA school sorts its articles into subjects for easier browsing.

You need a little n8n, a WordPress credential and an OpenAI key: import a file, add two credentials and edit one prompt.

Where to use it

Any n8n that can reach your WordPress site and OpenAI will run it. It starts by hand.

  • n8n Cloud: import the file there and run it
  • Your own n8n server: the same file and steps
  • WordPress: where the posts are read and updated
  • OpenAI: where each title is sorted

Setup

Download saves a zip with workflow.json and Mindket’s setup notes in your downloads folder. Setup takes two credentials and the ids of your categories.

What you need first
NeedDetail
n8nOn n8n Cloud or on a server of your own
WordPressA site with a credential in n8n: a username, its password and the site address
OpenAIAn API key
CategoriesCreated in WordPress, with their ids to hand
  1. In n8n, create a workflow, open its menu, choose Import from File and pick workflow.json.
  2. Add a WordPress credential and select it in Get All Wordpress Posts and Wordpress.
  3. Add an OpenAI credential and select it in OpenAI Chat Model.
  4. In WordPress, open Posts, then Categories, and read each category’s id from the address of its edit page.
  5. In AI Agent, replace each <CATEGORY_ID_n> with an id and each name with your own.
  6. Try it on a copy of the site, then click Test workflow.

How to use it

Click Test workflow and wait for the run to finish. Then open the posts list in WordPress and check the categories. Try a copy of the site first, since the run replaces each post’s categories.

What to change for a different result
To changeWhere
The categoriesThe list in the prompt of AI Agent
The modelOpenAI Chat Model
Which postsThe options in Get All Wordpress Posts, such as Status
When it runsSwap the manual trigger for a schedule

Example

A blogger lists six categories with the id of each and runs the workflow. One post is titled “Ten AI tools for writers”.

The model answers with the id of the AI Tools category, and the post now sits in it. The same happens for every other published post.

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 fetches the posts, one asks the AI for a category number and one saves it. Run it on a test site first.

For experts. The agent is a Tools Agent with no tools and only a model. Its prompt asks for the id alone, and Wordpress sends that text as the post’s categories.

Where to look closer
NodeWhat it doesWhat to know
Get All Wordpress PostsFetches all the published postsReturn All is on
AI AgentPicks one category id from the titleThe prompt reads title.rendered
OpenAI Chat ModelSupplies the modelIt names gpt-5.6-terra
WordpressUpdates the postcategories replaces the post’s categories

Good to know

The update replaces a post’s categories, and nothing checks the model’s answer against your list.

  • The repair: the chat model named no model, so n8n’s default gpt-5-mini would run, which OpenAI’s deprecations page, read on 12 November 2026, lists as shut down on 11 December 2026. This copy names gpt-5.6-terra
  • Placeholders: the category ids in the prompt are <CATEGORY_ID_1> to <CATEGORY_ID_6> until you set them
  • Titles only: the model never sees the body of a post
  • Status: no status is set, so only published posts are fetched, which is WordPress’s default for a list of posts
  • Not run: this copy was not run against WordPress or OpenAI
  • Your data: the titles go to OpenAI, and the categories go to WordPress
  • Credentials: the JSON holds none

README and files

README

WordPress posts put in a category by AI from the title

An n8n workflow that reads every published post of a WordPress site, asks an AI model to pick one category for each post from its title, and saves that category on the post.

What is inside

  • workflow.json: the workflow as n8n exports it, nine nodes: five 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 WordPress and OpenAI.
  • The prompt listed category ids 13 to 19 with names that belong to one site. They are now <CATEGORY_ID_1> to <CATEGORY_ID_6>, so you put in the ids of your own categories.
  • The chat model named no model, so n8n's default gpt-5-mini would run. OpenAI's deprecations page, read on 12 November 2026, lists it as shut down on 11 December 2026, with gpt-5.6-terra as the replacement. This copy names gpt-5.6-terra.
  • The sticky notes were rewritten. One of them linked to a case study and a video. It now says what the workflow does and warns that categories are replaced.
  • Nothing else.

Before you start

  • An n8n instance, on n8n Cloud or your own server.
  • A WordPress site with a credential in n8n: a username, its password and the site address. A WordPress application password works for this.
  • An OpenAI API key.
  • The categories you want, created in WordPress.

Set it up

  1. In n8n, create a workflow, open its menu and choose Import from File. Pick workflow.json.
  2. Add a WordPress credential and select it in Get All Wordpress Posts and Wordpress.
  3. Add an OpenAI credential and select it in OpenAI Chat Model.
  4. In WordPress, open Posts, then Categories. Open a category and read its id, tag_ID, in the address. Do this for each category.
  5. In AI Agent, replace each <CATEGORY_ID_n> with an id and each name with your own.
  6. Try it first on a copy of the site, then click Test workflow.

How a run goes

  1. When clicking ‘Test workflow’ starts the run by hand.
  2. Get All Wordpress Posts fetches all the published posts. Return All is on.
  3. AI Agent receives each post's title, title.rendered, with the category list, and answers with one number.
  4. Wordpress updates the post. The post id comes from the posts node, and categories holds the agent's answer.

Change the look

  • The categories: the list in the prompt of AI Agent.
  • The model: OpenAI Chat Model.
  • Which posts: the options in Get All Wordpress Posts, such as Status, to include drafts.
  • When it runs: swap the manual trigger for a schedule. Then it sorts every post on each run.

Good to know

  • The update replaces the categories a post already has with the one the model picked.
  • No status is set, so the node asks for published posts, the default in WordPress's list of posts.
  • Nothing checks that the answer is an id from your list. An answer with other text reaches WordPress as the category value.
  • The model sees only the title, not the body of the post, and makes one call per post.
  • This copy was not run against WordPress or OpenAI.
  • The titles go to OpenAI, and the categories go to WordPress.
  • The JSON holds no credential.
Files
NOTICE.md  608 B
README.md  3 KB
workflow.json  5 KB

3 files, 9 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

Nanosaur2-670M

well9472 · Kit

Makes illustrations from text prompts with a small 670M-parameter diffusion model, run through ComfyUI. Built as a low-budget research model for people who wan…

New

waqf-ocr-hand-written-v1

Waqf-AI · Kit

Reads handwritten Arabic text from images and returns it as text. A fine-tuned PaddleOCR-VL model for people digitizing Arabic handwriting.

New

Wan2.2-TI2V-5B-Diffusers

Wan-AI · Kit

Makes video clips from a text prompt or an image plus text, at up to 720P and 24 frames per second, in the Diffusers format for a single consumer GPU.

New

Similar in Writing

See all in Writing

t5-base-grammar-correction

vennify · Kit

Rewrites English text with fewer grammar mistakes, using a T5 model trained on the JFLEG dataset. Made by vennify for writers, students and developers who want…

New

Hy-MT2-1.8B-1.25Bit-GGUF

tencent · Kit

Translates between 33 languages on your own device with a 1.8B model squeezed to 1.25 bits, about 440 MB as GGUF files for llama.cpp. For developers adding off…

New

Qwen3.8-27B-Longbook27-v2

summerAIO · Kit

Summarizes, answers questions about and continues book-length text with a fine-tuned 27B model that uses Gated DeltaNet layers, in English and Japanese. For pe…

New