# Generate and audit original revenge stories with OpenAI: n8n workflow

> Started by an event in a connected app. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to OpenAI.

Source: https://millionrounds.com/workflow/generate-and-audit-original-revenge-stories-with-openai (Millionrounds; every figure on the page links to its filing or article)

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

# Generate and audit original revenge stories with OpenAI

Started by an event in a connected app. It calls services over plain HTTP rather than through connectors. It hands the judgement calls to OpenAI. 38 steps, 5 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: OpenAI

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fgenerate-and-audit-original-revenge-stories-with-openai)

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

**5** Branches: places the flow splits

**0** Loops or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 1 Model 17 Logic 20

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

- 1 **Manual Execution Trigger** Manual trigger *Starts it*
- 2 **Parse Structured Output** Output Parser Structured *Model*
- 3 **AI Model - OpenClaw 1** Lm Chat Open Ai *Model*
- 4 **AI Model - OpenClaw 2** Lm Chat Open Ai *Model*
- 5 **AI Model - OpenClaw 3** Lm Chat Open Ai *Model*
- 6 **AI Model - OpenClaw 4** Lm Chat Open Ai *Model*
- 7 **AI Model - OpenClaw 5** Lm Chat Open Ai *Model*
- 8 **AI Model - OpenClaw 6** Lm Chat Open Ai *Model*
- 9 **AI Model - OpenClaw 7** Lm Chat Open Ai *Model*
- 10 **AI Model - OpenClaw 8** Lm Chat Open Ai *Model*
- 11 **Set Story Configuration** Set *Logic*
- 12 **Audit Premise Integrity** Chain Llm *Model*
- 13 **Recreate Premise for Writing** Chain Llm *Model*
- 14 **Generate Story Premise** Chain Llm *Model*
- 15 **Craft Original Story** Chain Llm *Model*
- 16 **Audit Story Originality** Chain Llm *Model*
- 17 **Reformulate Premise** Chain Llm *Model*
- 18 **Enhance Story Quality** Chain Llm *Model*
- 19 **Extract Narrative Elements** Information Extractor *Model*
- 20 **Set Inspiration Source** Set *Logic*
- 21 **Check Premise Integrity** If *Logic*
- 22 **Format Rebuilt Premise** Code *Logic*
- 23 **Format Approved Premise** Code *Logic*
- 24 **Prepare Input for Audit** Code *Logic*
- 25 **Analyze Audit Results** Code *Logic*
- 26 **Format Regenerated Premise** Code *Logic*
- 27 **Set Up Modified Audit Input** Code *Logic*
- 28 **Build Story Input** Code *Logic*
- 29 **Organize Rebuild Input** Code *Logic*
- 30 **Verify Audit Success** If *Logic*
- 31 **Prepare Premise Audit Input** Code *Logic*
- 32 **Check Premise Rebuild Limit** If *Logic*
- 33 **Package Approved Story** Code *Logic*
- 34 **Setup for Retry** Code *Logic*
- 35 **Flag Premise for Review** Set *Logic*
- 36 **Check Retry Limit** If *Logic*
- 37 **Maximum Retries Exceeded** Set *Logic*
- 38 **Assess Premise Similarity** If *Logic*

## How it's built

- **Starts on:** An event in a connected app
- **Steps:** 38, with 5 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** OpenAI

## Questions

What does it need to run?

An n8n account, and a key for OpenAI. 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 OpenAI. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 38 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 38 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%2Fgenerate-and-audit-original-revenge-stories-with-openai)
- **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.

## Workflows like it

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

- [**BambooHR AI-powered company policies and benefits chatbot** 39 steps · calls a model · Supabase vectors](https://millionrounds.com/workflow/bamboohr-ai-powered-company-policies-and-benefits-chatbot)
- [**Generate complete stories with OpenAI** 37 steps · calls a model · Google Drive](https://millionrounds.com/workflow/generate-complete-stories-with-openai)
- [**Online listener with OpenAI and Baserow** 37 steps · calls a model · Baserow, Gmail](https://millionrounds.com/workflow/online-listener-with-openai-and-baserow)
- [**Create an all-in-one Discord assistant with Gemini and Llama** 36 steps · calls a model](https://millionrounds.com/workflow/create-an-all-in-one-discord-assistant-with-gemini-and-llama)
- [**Send GoHighLevel WhatsApp and email auto-replies with Redis** 36 steps · calls a model · Google Drive, Pinecone](https://millionrounds.com/workflow/send-gohighlevel-whatsapp-and-email-auto-replies-with-redis)
- [**Tech news_curator - analyze daily news with AI_agents** 40 steps · calls a model · RSS](https://millionrounds.com/workflow/tech-news-curator-analyze-daily-news-with-ai-agents)