# Proofread markdown blog posts with Gemini and Groq: n8n workflow

> Started by an event in a connected app, and works across GitHub. It hands the judgement calls to Gemini and Groq.

Source: https://millionrounds.com/workflow/proofread-markdown-blog-posts-with-gemini-and-groq (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Content](https://millionrounds.com/workflows?category=Content#library)

# Proofread markdown blog posts with Gemini and Groq

Started by an event in a connected app, and works across GitHub. It hands the judgement calls to Gemini and Groq. 22 steps, 2 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: Gemini, Groq

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fproofread-markdown-blog-posts-with-gemini-and-groq)

**22 steps** Large: read it before trusting it with anything live

**2** Branches: places the flow splits

**0** Loops or waits

**1** Service it connects to

## The flow

Starts it 1 Model 6 Logic 10 Service 5

The steps in the order they run, from what starts it.

- 1 **When clicking ‘Execute workflow’** Manual trigger *Starts it*
- 2 **QA Agent LLM** Lm Chat Google Gemini *Model*
- 3 **Editor Agent LLM** Lm Chat Google Gemini *Model*
- 4 **Fallback Chat Model** Lm Chat Groq *Model*
- 5 **Fallback Model** Lm Chat Groq *Model*
- 6 **Github Config** Set *Logic*
- 7 **QA Agent - Analyze Content** Agent *Model*
- 8 **Editor Agent - Generate Edit Ops** Agent *Model*
- 9 **Fetch Blog Post from GitHub** Github *Service*
- 10 **Parse QA Issues JSON** Code *Logic*
- 11 **Parse Edit Operations JSON** Code *Logic*
- 12 **Decode Base64 & Add Line Numbers** Code *Logic*
- 13 **Has Issues?** If *Logic*
- 14 **Apply Line-by-Line Edits** Code *Logic*
- 15 **Format Clean Report** Code *Logic*
- 16 **Edits Applied?** If *Logic*
- 17 **Save QA Report to GitHub Without Issues** Github *Service*
- 18 **Commit Updated File to GitHub** Github *Service*
- 19 **Format QA Report** Code *Logic*
- 20 **Format Failure Report** Code *Logic*
- 21 **Save QA Report to GitHub** Github *Service*
- 22 **Create a file** Github *Service*

## How it's built

- **Starts on:** An event in a connected app
- **Steps:** 22, with 2 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** GitHub
- **Model:** Gemini, Groq

## Questions

What does it need to run?

An n8n account, plus your own GitHub account, and a key for Gemini and Groq. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an event in a connected app.

Does it use AI?

Yes. It calls Gemini and Groq. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 22 steps it is large: read it before trusting it with anything live.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 22 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fproofread-markdown-blog-posts-with-gemini-and-groq)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Connects to

Each opens the other workflows that use it.

[GitHub](https://millionrounds.com/workflows?service=GitHub#library)

## Workflows like it

Also content, with the same services where possible, closest in size first.

- [**Review Terraform pull requests with GitHub and OpenAI** 20 steps · calls a model · GitHub, Postgres](https://millionrounds.com/workflow/review-terraform-pull-requests-with-github-and-openai)
- [**Auto-categorize blog posts with OpenAI and GitHub** 18 steps · calls a model · GitHub, Google Sheets](https://millionrounds.com/workflow/auto-categorize-blog-posts-with-openai-and-github)
- [**Create character-consistent images with FLUX Kontext** 18 steps · GitHub](https://millionrounds.com/workflow/create-character-consistent-images-with-flux-kontext)
- [**Generate content with OpenAI and GitHub** 17 steps · calls a model · GitHub, Telegram](https://millionrounds.com/workflow/generate-content-with-openai-and-github)
- [**Convert GitHub code commits to LinkedIn posts with Gemini** 15 steps · calls a model · GitHub, LinkedIn](https://millionrounds.com/workflow/convert-github-code-commits-to-linkedin-posts-with-gemini)
- [**Auto-generate social posts from GitHub README/CHANGELOG updates** 14 steps · calls a model · GitHub, LinkedIn](https://millionrounds.com/workflow/auto-generate-social-posts-from-github-readme-changelog-upda)