profile

Seotistics - Web Analytics + Business + Strategy

The LLM Stack In Web Analytics

Published about 19 hours agoΒ β€’Β 4 min read

Use Data Or Be Used By Data!

The July 20 issue of Seotistics is here for you!

LLMs are everywhere and they have some interesting applications for our daily tasks in Analytics.

Yeah, they won't make you lose your job as the news claim...

but for sure you can't sit watching and sacrifice opportunities.

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 will start soon, stay tuned!

Seotistics Summer Sales will soon be available, so prepare your wallets in advance πŸ‘€

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

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 some more to be announced later I guess πŸ‘€

The Analytics Shift

The last 6 months have consolidated the dominance of AI in work.

Which means this is no longer an optional thing to do but your baseline.

From visualization to diagramming and even generating mockups or playing with data, LLMs can do all.

I don't see the point of denying that these are essential tools for Analytics now.

If before you could do the bare minimum with GA4 and GTM... now those times are gone.

Companies have more complex needs and the progressive democratizazion of code affected the job industry.

And unlike what many boast online, you do need to know the modern meta to compete.

I still see Analysts and Marketers alike using outdated processes downgrading their services for no reason.

I avoid working in contexts where there is no progress or no possibility to upgrade.

The Best Tools Out There

I constantly update my stack or how I work because there are better solutions.

OK the concepts are the same but it's my duty to keep up to date so I can give you and my clients the best advice.

Needless to say, to do actual Analytics you need data storage, which is often via BigQuery for Web Data.

Then, you need to model your data, DBT and Dataform both work depending on the context.

My favorite part now is definitely Automation... in the past it was close to impossible to make it quick.

Now you can play with n8n and Hermes to automate your stuff easily.

You can pay for a VPS, for example one from Hertzner, and run your n8n there.

If that's the case, you should also test Hermes. This is the closest thing to a self-learning agent today.

And it can be used to save tokens as well!

I still need to test it in depth, actually but my dear friend Henedy talked about it:

If you play a lot with the terminal, I always recommend cmux for macOS.

Building a portfolio years ago was challenging, now you just need the willingness to start and being curious (check past issue).

More about this will be shared (once again) in the next issues.

I don't think the visualization part needs many explanations lol.
​
Claude is also cool for quick artifacts to share.

OK... But Which LLMs?

Anything goes BUT if you ask me, I have some preferences over tools and models:

  • Antigravity IDE (nice but replaceable)
  • Claude Code (nice for most people)
  • Openrouter + OpenWeb UI (great setup for testing all the models)
  • Hermes

Most of this works and will help you get started but even deliver results in projects.

For the models, they change every month now, there is no real advice on this.

My advice is to start small and keep testing more complex models.

Starting with something like DeepSeek V4 Flash or Pro is usually fine.

I'd avoid models like Fable unless you have to prepare a plan of execution.

Takes That Proved Wrong

You may have heard the following bad takes:

  • Generalists are the future, specialization is dead
  • Dashboards aren't needed
  • Analysts are outdated

None of them has proven true and there is no signfor these to remotely true.

Specialization still proves to be superior to being a jack of trades (and master of none).

Once you study Analytics in general, you will realize why most stuff barely matters for us.

In university I studied a lot of statistical methods and stuff that works wonders for other industries.

For Web? Forget about it.

I was also quick enough to realize that Machine and Deep Learning were kinda useless for my career.

Your Competitive Advantage

The biggest advantage you have over others today is how you manage your time and mental space.

Not even joking,

I could spend years on toying with them and that's not feasible.

This is why personal productivity matters a LOT and also how you document your work.

As you know, I am deep in Obsidian and I use it for all my stuff.

Well, enjoy this issue and catch you next week!

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

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

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—»

Will post and update more soon, as I finally have more free time, finally!

Read these 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

by Marco Giordano

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

Use Data Or Be Used By Data! The July 13 issue of Seotistics is here for you! Scraping is one of the most important skills you must have as an analyst AND marketer. But what changed after LLMs? Well, a lot! This issue is about YOU scraping websites to get data, not how LLM providers scrape your website. 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“£...

8 days agoΒ β€’Β 6 min read

Use Data Or Be Used By Data! The July 6 issue of Seotistics is here for you! This is the last issue talking about LLM measurement. I will cover some of the last details because this topic has been covered a LOT. Then, I will start drafting one of the many articles I promised you πŸ‘€ If you are still postponing studying LLMs... I have bad news: they are everywhere. It's also true that AI Search as of now looks like Sci-Fi in terms of measurement (it doesn't exist yet). Please move this email to...

15 days agoΒ β€’Β 6 min read

Use Data Or Be Used By Data! The June 29 issue of Seotistics is here for you! The last time we talked about AI measurement and what changed. Turns out a lot changed indeed! I will go deeper on some concepts that the last time weren't covered with due credit. P.S. Next week the last part of this series. 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“£...

22 days agoΒ β€’Β 6 min read