Content & Ecommerce Automation (LLMs + n8n)


Use Data Or Be Used By Data!

The August 10 issue of Seotistics is here for you!

The last time we talked about DeepSeek and how cheap it is to enable Analytics automation.

Now it's time to actually show you some more examples.

My favorite ones come with tools like n8n, DeepSeek and Hermes.

This is a nice introduction to give you ideas, feel free to ask for more!

Please move this email to your Primary inbox or reply to it. This is to prevent Seotistics goes into spam by accident. Gmail users can read this tutorial to do it.

​Read this in your browser​

πŸ“£πŸ“£ Important Announcements πŸ“£πŸ“£

The Seotistics Summer Sales are live with 30% off on ALL products.

Code "SUMMER26" at checkout, until August 19.

Including my new course below, so have a look now:

What you see in this issue and more will be made available this week in this course.

I am also working on new updates and content as we speak.

As for conferences, I will be present at:

  • ​Belgrade SEO (you can guess the city lol)- 18th September 2026 (use code MARCO for a good % off)
  • ​SEO On Stage (Athens) - 24th October 2026

And there are 2 more to be announced later I guess πŸ‘€

For Content

I've already mentioned in the past that you can and should work on content research with LLMs.

Manual work doesn't cut it anymore unless:

  • it's for improving the LLM output
  • you are reviewing work

but it's delusional to expect people in 2026 to actually spend hours a week to do something this simple.

There are several ways to proceed with content, depending on your goals.

For content research, you normally need to check what's out there and then craft a better article OR provide a different angle.

I've seen too many automations created by people who have never done Content Marketing and it shows.

They stuff a bunch of keywords from different tools and call it a day.

AirOps has created a super marketing stunt the "Content Engineer".
​
In reality, you need technical people with good content understanding, not content marketers with some tech skills πŸ’€

Example 1

This for Seotistics and I need more time to spend on it lol

The idea is very simple, doing research and getting advice on what I can do in terms of content.

In this specific use case:

  • Provide list of keywords, get SERP data, group into clusters based on SERPs
  • inspect competitors and your website to detect pages, analyze all
  • provide content recommendations for new AND existing pages

I should revamp my blog section and publish more content and this will be my starting point.

The output is quite solid and saves me quite some time.

Most of the automations for content I do involve this magic trio:

I've already talked about Hermes Agent and it's legitly useful for a LOT of automation use cases.

But the full breakdown is for another day.

Example 2

This is one example I'm working on recently for an enterprise project.

Similar gist to example 1 but with much more complexity and different processes.

Unfortunately, I am obliged to use Microsoft hence you have the extra step with PowerAutomate to ingest MS Forms data.

This workflows is incredibly more complex and has me to go through multiple hoops.

I can't show you the actual one, of course, but tell you some of the steps:

  • identification of existing pages is much harder across 100s of domains
  • detecting intent of queries and pages can be done in multiple ways
  • some steps should be validated and the output saved

I skipped some passages but it requires a lot of engineering work and understanding the full picture.


As usual, we don't automate writing but purely the boring and time-consuming research part.

Actual writing is where the difference is made and what (also) makes you stand out.

What's good here is that all of these examples can be expanded later on and include more:

  • start from your GSC data in BigQuery instead (or combine other sources)
  • provide more business context
  • find alternative ways of analyzing content (or scraping)
Processes always evolve and aren't static.
​
Sticking to old and reliable practices doesn't pay off in the long run!

The Ideal Setup

For ALL the use cases, the setup always involves data storage, so a warehouse like BigQuery.

This is always needed for your GA4 and GSC data.

Then, you need to define your business as context for the LLMs.

Obsidian is a great partner for this because you can actually document all your content and ideas.

The key part is having the sources to give context to LLMs so they avoid generic output.

Most often:

  • business_context.md
  • examples (can be files or whatever)
  • skills for scraping
  • style.md

Spend time on your context and figure out what's the content angle.

Ecommerce

That's one of the most automatable business models in terms of web operations.

Common areas include:

  • improving your catalog (titles, content, descriptions, etc.)
  • checking market prices
  • recommendations and/or how to sell more products

You aren't supposed to waste hours or weeks over such pointless tasks.

Most of them aren't revenue-generating and don't require that much customization.

I was recently testing an automation based on DataForSEO for keywords:

This is me experimenting, not an actual workflow for now.

I will show you some more examples once I finish them πŸ‘€

The Ideal Setup

Apart from the usual BigQuery stuff, I'd also consider data sources like Google Merchant Center and your CRM+ERP data.

This is a very common pain point and not many people use them (and they should).

But GA4 has revenue data!

Yeah and even with server-side tracking it's either wrong or you are using the wrong tool.

Tools like GA4 are to be used for attribution and understanding what people do on your website.

They aren't supposed to tell you about your revenue or costs.

Measuring Expectations

Automation like this doesn't create new time from thin air or make you stop working.

This is the wrong expectation of many managers.

You still need people and someone to actually do the job, including yourself.

Where many SaaS lie is that they claim to boost "revenue".

Automation optimizes efficiency, aka the capability to achieve your goals with fewer resources.

It's never been about effectiveness, so achieving your goals.

More content doesn't equal better marketing results but...

more efficiency, in the long run, will indirectly help you with effectiveness.

It's quite hard to achieve your goals and run a company if your processes are slow and lagging behind.

More cool stuff in the next issue as time is short πŸ‘€

πŸ‘₯ Join Our Community

Our Discord community offers a small place where we can talk business and web data.

If you hate all the noise of social media, then this place is for you.

I will start posting more there as we have a forum channel now.

This is the best way to stay updated in real time on Seotistics:

πŸ”Ž Analytics For SEO Ebook - Course / Ebook

Always use code "SUMMER26" at checkout for 30% off.

You will:

βœ… Use GSC and GA4 Data to their fullest potential

βœ… Learn Python/SQL for your needs

βœ… Get a complete blueprint for auditing websites

βœ… Learn how to 10x your productivity

βœ… Learn BigQuery to work on large websites

I teach you what's needed to go from 0 to a professional Data Analyst.

Even if you leave SEO, the foundations are the same for other jobs!

Also in ebook:

Think Like A Web Analyst

Always use code "SUMMER26" at checkout for 30% off.

This course teaches you to:

βœ… frame Analytics problems

βœ… understand which metrics matter

βœ… managing Web Analytics projects successfully

πŸ“š Recommended Reads - Peak Content πŸ—»

Read the weekly peaks:

As usual, my most recent LinkedIn content is here.

❗️ Feedback and Recommendations

If you have ideas/recommendations for the next issues of Seotistics, you can simply reply to this email.

Marco Giordano
​
Data/Web Analyst

Follow me on πŸ”½πŸ”½πŸ”½:

Bernerstrasse SΓΌd 167, Zurich, Switzerland
​Unsubscribe Β· Preferences​

Seotistics - Web Analytics + Business + Strategy

The Seotistics newsletter is written by Marco Giordano, a Data/Web Analyst with the goal of combining business and web data. Tired of the usual boring Analytics content without any business impact? Seotistics teaches you how to use Analytics, web data and even content in your workflow while helping you with Strategy.

Read more from Seotistics - Web Analytics + Business + Strategy

Hey , I’m currently finishing up some new content + updates for Seotistics for this and next week. Btw, I opened up a 30% discount across all my products until August 19. You can use the code SUMMER26 at checkout. Pick your path to analytics mastery: Analytics for Real Work: This covers real-world GA4/GSC/other data pipelines and LLM workflows. Analytics for SEO (Course): My full program to master BigQuery, Python, and SQL. If you want to move beyond basic SEO audits and start doing data...

Use Data Or Be Used By Data! The August 3 issue of Seotistics is here for you! DeepSeek is the buzz of the moment and it's not even random hype. Chinese models are revolutionizing the LLM world because they are sooo cheap and good. This has some consequences on Web Analytics too, mind you! Please move this email to your Primary inbox or reply to it. This is to prevent Seotistics goes into spam by accident. Gmail users can read this tutorial to do it. Read this in your browser πŸ“£πŸ“£ Important...

Use Data Or Be Used By Data! The July 27 issue of Seotistics is here for you! Dashboards are everywhere and tbqh often overengineered for simple use cases. I've audited too many organizations having this issue here. So what can we do instead? The answers here are simple and feasible, you just need to know them! Please move this email to your Primary inbox or reply to it. This is to prevent Seotistics goes into spam by accident. Gmail users can read this tutorial to do it. Read this in your...