Home/Insights/Automation

I Built a Full n8n Workflow in Minutes Using Claude AI (FREE TOOLS)

By Ani BjörkströmPublished 20 January 2026Reviewed 20 September 20267 min video + articleAutomation

I Built a Full n8n Workflow in Minutes Using Claude AI (FREE TOOLS)
▶ Watch the full 7-minute tutorial · free on YouTube

AI TOOLS

How do you build a full n8n workflow in minutes with Claude AI and free tools?

In short: Claude generated a complete, importable n8n workflow JSON file from one detailed prompt, no manual node-building required.

Key takeaways

  • Claude generated a complete, importable n8n workflow JSON file from one detailed prompt, no manual node-building required.
  • Apify gives every account $5 in free credits per month, and at $1 per 1,000 results the YouTube scraper delivers up to 5,000 scraped results monthly at zero cost.
  • The finished workflow scraped YouTube and wrote results into Google Sheets, matching on the ID column so duplicate rows are never inserted twice.

Building an n8n workflow by hand means wiring nodes one by one; asking Claude for the JSON file skips straight to a working automation. The stack in this build by Ani Björkström, a Stockholm-based tech consultant, was entirely free: Claude's free tier, a self-hosted local n8n instance, Apify's monthly free credits, and Google Sheets for storage.

How does Claude create the n8n workflow for you?

Prompt Claude to "create an n8n workflow JSON file for a YouTube scraper that sends data to Google Sheets", followed by a detailed description of what it must do. A detailed prompt raises the odds the JSON works from the beginning; with a short prompt, you upload the file and return to Claude if anything breaks. When Claude finishes, one click on the download button gives you the workflow file ready for import.

Why use Apify as the scraping engine?

Apify is a platform full of ready-made scrapers, and every account receives $5 in free credits each month. The YouTube video and comment scraper costs about $1 per 1,000 results, so the free credits cover roughly 5,000 results every single month. In Apify, open the API button, choose API endpoints, scroll to "run actor synchronously and get key value", and copy that full URL including your token, then tell Claude to call that endpoint in the JSON it writes; never share the token, since anyone holding it can spend your credits.

ComponentRole in the workflowCost
ClaudeGenerates the importable n8n workflow JSONFree tier, limited prompts
n8nRuns the automation, self-hosted locallyFree
Apify YouTube scraperScrapes video data, $1 per 1,000 results$5 free credit monthly, about 5,000 results
Google SheetsStores results, deduplicated on the ID columnFree

How do you import and run the workflow in n8n?

In n8n, click the plus button for a new workflow, open the three-dots menu, choose "import from file", and select the JSON Claude produced. Executing the workflow opens a form with the scraper's parameters: search term (n8n in the demo), max videos per search, shorts and streams set to zero to exclude them, results sorted by view count, and any upload date, content type, and duration. The demo run scraped four n8n videos from YouTube and saved them straight into the connected sheet.

How do you stop duplicate rows in Google Sheets?

Set the Google Sheets node's "column to match on" to ID, so every incoming record is checked against existing rows before insertion. If the ID already exists the row is skipped; if not, it is added, which keeps repeated runs from filling the sheet with duplicates. The sheet's columns, ID, URL, title, channel name, and so on, mirror the fields n8n receives, and any unmapped field can be fixed by dragging and dropping it into place.

FAQ

Is the whole setup really free?

Yes. Claude's free tier generates the JSON, n8n runs self-hosted on a local computer at no cost, and Apify's $5 monthly free credit covers about 5,000 YouTube results.

What if the generated workflow does not work?

Go back to Claude, describe the error, and ask it to adjust the JSON. Then re-import the corrected file into n8n.

Which Apify endpoint does the workflow need?

The "run actor synchronously and get key value store" endpoint, copied with the token included, pasted into the workflow's URL field.

Full transcript of the video (1,102 words, 9 sections)

0:16 Hey, my name is Annie. I'm a tech consultant based in Stockholm. In this tutorial, I will show you how to create any NATM workflow for free. Let's get started. For this tutorial, we will create an NAN workflow that scrapes YouTube. For that reason, I will log into cloud. You can use cloud for free for limited prompts. Now, I will use this prompt that says create an NM workflow JSON file for YouTube scraper that sends data to Google Sheets. Then, I have a detailed description what it needs to do. So the reason I'm sending very detailed prompt is because I want to get a JSON file that works from the beginning. However, you can write just a short prompt and upload the file into anything and if something doesn't work, you can come back to cloud and ask to adjust it.

1:07 For this tutorial, I will use an Epifi scraper. Epifi is a platform where you will get a lot of different scrapers. And Epifi will give you $5 free credit every single month. And if you choose a very cheap scraper, you can run a lot of Nit workflows within those $5. So we will choose YouTube video and comment scraper because this one is almost free. You can see that for every single dollar we can get 1,000 results. And keeping in mind that we have $5 that is free on API. You can scrape 5,000 results for free every single month using this scraper. Now we will click on API button and from there API endpoints and then we will scroll down and we'll choose run actor synchronously and get a key value and from here we will just copy the whole URL with the token.

2:05 So if for example I click on this button then I can see what my token is but I don't recommend sharing your token with other people because they can simply use your credits from EPI. So here we will just copy this URL and we will tell cloud to involve this endpoint in the JSON file that it will create. Now after this we can just click on enter button and cloud will start to work in couple of seconds. It will create a JSON file for us. Now if you want to get this NAN workflow for free stay until the end of this video and I will show you how to do it. We can see that cloud already created the workflow.

2:51 And at this point, we can just click on download button and download our NAN workflow. Next, we will go to N8. So, right now, I'm hosting N8 on my local computer for free. If you want to do the same thing, I have a video explaining how to do it. Just check it down below. Next we will click on the plus button workflow and then from here we will click on those three dots and from there we will choose import from file and the next step is basically uploading the file into NAN. So we will click on import from file and we will find the file and we'll click on open button. So in here you can see that we have an actual workflow and let's save this and test it.

3:38 We will click on execute button. We can see that the window is popping up. Here we have search terms. I will enter N8N. Next, we have max video per search. I'm not interested in shorts, so I will enter zero here. Same thing with streams. I'm not interested in streams, so I will enter zero. Then we have search result by. In here, I will choose view count because I want to get the videos that got most views. Next, I will go to upload date. And in here I will choose any time. Next we have content type filter. Here I will choose any type. And for video duration I will choose any duration. Then we will click submit button. Now we can see that our workflow is running and epify scraper is thinking.

4:27 And then we have all the results saved into Google Sheets. So our workflow actually worked. But before we see the results, I want to show you how to set up your EPI scraper in here under the URL. I basically pasted my API endpoint from Appify including the token. Go to Appify and click on APIs. Then API endpoints. If we scroll down, we have the endpoint that says run actor synchronously and get key value store. So this is the end point that you will copy from here and make sure that you are even copying the token information. Now back to N8N. Once this is done then we need to also configure Google sheet.

5:17 And before you will configure Google sheet you will basically go to your Google drive account and you will create a new Google sheet. You can see that I have already did that. And if I come back to N8N, you can see that I have chosen that file in my Google sheet that was called viral YouTube videos. Then I'm choosing sheet one where I want the result from EPI to be saved. And from there I'm choosing column to match on. And the idea with this column to match on is that every time we get data from EPI, we want to check if that data already exists in Google sheet. And if it doesn't exist, it will be entered. But if it already exists, it will not be entered. So that is why in here we will choose the ID because ID stands for identification.

6:09 Next, in here you can see all the columns that we have on our Google sheet. If I go back, you can see that we have ID, URL, title, channel name, and so on. And those are exactly the same fields that we have even in N8N. So those fields will be populated automatically. But if they aren't populated, then you can just drag and drop. For example, for ID, you will drag [snorts] and drop ID in here. And then the same thing you will do also for URL, title, channel, and that's it. And now we can go to our Google sheet. And we can see that we have four NAN videos that were scraped from YouTube and saved in here. If you like to get this NAN workflow for free, like this video and comment NAT down below.

6:58 See you in the next one. Bye.

Want this working inside your finance team?

Ani Björkström

Ani Björkström — founder of QvantX Sweden AB, a Stockholm consultancy building AI solutions for banks, asset managers and finance teams. Anthropic partner. Every article starts from a real client build, minus the confidential parts. LinkedIn →