# AI website scraper & company intelligence with Mistral: n8n workflow

> Started by someone submitting a form, and works across Google Drive and Supabase. It hands the judgement calls to Mistral.

Source: https://millionrounds.com/workflow/ai-website-scraper-and-company-intelligence-with-mistral (Millionrounds; every figure on the page links to its filing or article)

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

# AI website scraper & company intelligence with Mistral

Started by someone submitting a form, and works across Google Drive and Supabase. It hands the judgement calls to Mistral. 28 steps, 1 branch: large, and worth reading before you trust it with anything live.

Large Calls a model: Mistral

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fai-website-scraper-and-company-intelligence-with-mistral)

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

**1** Branch: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 1 Model 11 Logic 2 Service 14

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

- 1 **Mistral Cloud Chat Model3** Lm Chat Mistral Cloud *Model*
- 2 **list tools** Mcp Client Tool *Service*
- 3 **execute tools** Mcp Client Tool *Service*
- 4 **Structured Output Parser** Output Parser Structured *Model*
- 5 **Crawl and Scrape** Crawlee Node *Service*
- 6 **On form submission** Form trigger *Starts it*
- 7 **Mistral Cloud Chat Model5** Lm Chat Mistral Cloud *Model*
- 8 **Mistral Cloud Chat Model6** Lm Chat Mistral Cloud *Model*
- 9 **Firecrawl tools1** Mcp Client Tool *Service*
- 10 **Mistral Cloud Chat Model2** Lm Chat Mistral Cloud *Model*
- 11 **Firecrawl list1** Mcp Client Tool *Service*
- 12 **Structured Output Parser1** Output Parser Structured *Model*
- 13 **Web Search tool** Tool Http Request *Model*
- 14 **find competitor** Agent *Model*
- 15 **Switch** Switch *Logic*
- 16 **basic web scraper** Agent *Model*
- 17 **Information Extractor1** Information Extractor *Model*
- 18 **MCP based scraper FIRECRAWLER** Agent *Model*
- 19 **Supabase4** Supabase *Service*
- 20 **save to Supabase** Supabase *Service*
- 21 **Convert to File for storage1** Convert To File *Service*
- 22 **Supabase** Supabase *Service*
- 23 **Convert to File for storage** Convert To File *Service*
- 24 **No Operation, do nothing** No Op *Logic*
- 25 **save to Google Drive1** Google Drive *Service*
- 26 **social media db** Supabase *Service*
- 27 **keywords** Supabase *Service*
- 28 **Google Drive2** Google Drive *Service*

## How it's built

- **Starts on:** Someone submitting a form
- **Steps:** 28, with 1 branch
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Google Drive, Supabase
- **Model:** Mistral

## Questions

What does it need to run?

An n8n account, plus your own Google Drive and Supabase accounts, and a key for Mistral. You connect your own accounts after importing it; none are included.

What starts it?

It starts on someone submitting a form.

Does it use AI?

Yes. It calls Mistral. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 28 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 28 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%2Fai-website-scraper-and-company-intelligence-with-mistral)
- **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.

[Google Drive](https://millionrounds.com/workflows?service=Google+Drive#library)[Supabase](https://millionrounds.com/workflows?service=Supabase#library)

## Workflows like it

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

- [**Enrich FAQ sections on your website pages at scale with OpenAI** 29 steps · calls a model · Google Drive, Google Sheets](https://millionrounds.com/workflow/enrich-faq-sections-on-your-website-pages-at-scale-with-open)
- [**Speed to Lead: SMS Qualification (Solar Installers)** 25 steps · calls a model · Supabase, Twilio](https://millionrounds.com/workflow/speed-to-lead-sms-qualification-solar-installers)
- [**Automated WhatsApp messaging & lead nurturing with Gallabox** 31 steps · Supabase](https://millionrounds.com/workflow/automated-whatsapp-messaging-and-lead-nurturing-with-gallabo)
- [**Find and email website-less local businesses** 25 steps · Gmail, Google Drive](https://millionrounds.com/workflow/find-and-email-website-less-local-businesses)
- [**Qualify mortgage leads and collect documents with Gemini** 24 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/qualify-mortgage-leads-and-collect-documents-with-gemini)
- [**Send CRM lead outreach emails with Notion and Gmail** 32 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/send-crm-lead-outreach-emails-with-notion-and-gmail)