Use Data Or Be Used By Data!

The May 19 issue of Seotistics is here for you!

AI is making some nice advancements as of late and I am here to show you some ideas.

I had to talk about Knowledge Graphs and Taxonomies but I will postpone it...

These tools are quite relevant today and can massively help you.

Mind you, Analytics is NOT only tools and tricks though...

​Read this in your browser​

📣📣 Important Announcements 📣📣

A lot more content to come soon for my dear readers who keep supporting me.

We are in a period of transition for Web Analytics and Marketing so this is the best moment for being disruptive.

To come next:

• "Analytics for SEO" ebook v9
• More additions to "Analytics for SEO" course
• More content for "Think Like a Web Analyst"
• Freebies
• Articles
• Maybe rearranging the layout of my future issues, who knows

Expect much more focus on AI and some pleasant additions.

What The Heck Is An MCP

Anthropic tells us that:

It's like a USB-C port, a nice way to connect Claude to any other app or system you have.

For example, I gave Claude access to my computer files... of course I still need to authorize operations every time!

OpenAI says MCP will also be supported by ChatGPT 🔜.

Some notable MCPs:

• File System (aka your PC)
• Obsidian (my only GOAT ❤️)
• DataForSEO
• Ahrefs
• Semrush

Needless to say SaaS are rushing over to integrate with MCPs to defend or expand their narrative.

Here is an example for the DataForSEO MCP:

Quite like an API call but much smoother (so it doesn't replace normal API usage).

P.S. You can also have a custom MCP for other tools (e.g. Google Search Console and GA4).

But if you are this lazy not to use BigQuery and APIs with proper workflows, I won't help you 💀

OK How Does It Benefit Me?

Claude and LLMs are already OP and make you super productive...

now imagine having access to other software.

Wasn't our eternal dream to have a built-in smart assistant?

Chatting with data alone is a stupid use case because it doesn't replace code or solve any underlying issue.

BUT... developing code or automation are NOT.

Let's consider some of the use cases I mentioned in my previous issues:

If you stick to your old processes, you will be less productive.

Being less productive means it takes you more time to complete a task.

You see where this is going?

Others will outperform you in terms of efficiency.

I feel physical pain every time I see people using Excel in the wrong way rather than some simple Python code copied from Claude.

Automation Today

All of this does NOT replace Software Engineering principles, that exist for a reason.

The issue arises when people think that engineers are no longer needed.

Vice versa, some also think that AI code is slop.

Well, this is absolutely false.

Cybersecurity and DevOps are stronger than ever, basic programming skills are worthless now.

This is why in my courses I teach you how to think and abstract problems rather than throwing concepts you can google at you.

We need more thinkers and wise people, not just doers.

Artifacts

If there is one feature that makes Claude my go-to choice, it would be artifacts.

Imagine having shareable snippets that can work as a small app or even a dashboard or whatever you like.

Yep, that's possible!

They look like this in Claude:

The best thing is when you create small interactive apps that you can use for several purposes.

Now, should you actually rely on them?

In most cases no, having 10+ Claude chats and calling them tools makes me shiver.

This is where you should build a small app or script in local.

Cursor, The GOAT

If you aren't using Cursor for coding... you are lagging behind.

Really, there is no match here.

Cursor is an IDE (aka where you write code) powered by AI and with a lot of extremely powerful features.

For example, I asked it to create a web app from 0, I just told it to use a palette I like and this is what it produced:

This helped me learn some basic JS and React.

The cool thing is that you can specify rules by project so that the advice you get is more tailored.

Windsurf is a competitor but I didn't really try it out.

All of this can only help you when learning how to analyze websites and write code. But it doesn't teach you what to do, so here we go:

[Analytics For SEO Course - v5]

If you want to be guided and start from scratch, this is the course for you!

You will:

✅ Use GSC and GA4 Data to their fullest potential

✅ Learn Python/SQL for your needs

✅ Get a complete blueprint for auditing websites

✅ Learn how to 10x your productivity

✅ 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!

Hierarchy Of Tools

LLMs per se isn't going to make anyone unemployed excluding those people who have been sleeping in the last 5 years.

Still, you need a variety of tools for different use cases:

Serious work requires DevOps like before... but for simple and quick scenarios, no-code is 100% fine.

It doesn't make any sense to build a new solution for every problem you have.

I ask a lot of things to Claude and love to get a quick answer...

but for those cases that keep busy every day, I need a solid process.

Engineers often overcomplicate and exaggerate what's needed, thinking about deployment.

Other categories often underestimate the effort of having good software.

Stay in the middle!

The Maxi Leak

Last week I linked this resource, I hope some of you had a look at it.

It's a list of all the prompts used by LLMs and how they were set up.

So it tells us how models behave and what they are instructed to do...

Being Effective, Not Only Efficient

We get paid to solve problems and achieve goals.

This is the definition of being effective.

AI can help you being more efficient but not necessarily in effectiveness.

While many focus on saving costs, focus on achieving more goals.

Nowadays, attention is what you should pay for.

Visibility is scarce and you can't always rely on your dear clicks.

This is why I keep telling you to distribute and repurpose your content.

Catching Up With Innovation / Analytics Impact

There are new things to test every day... my advice is NOT to follow all of them.

Stick to what's relevant for you.

Seotistics helps you understand what makes sense and what not.

Analytics-wise, what I've shown you here is awesome for productivity and self-study.

If you think about enterprise applications... I am not so convinced.

AI should be your last resort and you need to actually evaluate simpler alternatives.

For sure, it's an immense perk for your productivity and it did impact the operational side of Analytics as you may have guessed:

The Impact of AI in Analytics ✨

Area	Pros	Cons
⌨️ Coding	LLMs save you hours if not days of coding and debugging.	Massive efficiency losses if you do it incorrectly.
🤖 Automation	You can save money on most SaaS and build your tools. More time for strategic work.	Security risks and more slop out there.
🧠 Learning	LLMs give great inputs and teach concepts easily and quickly.	LLMs can make you lazy. If you don't know what to ask, your knowledge will remain superficial.
📚 Documentation	It's never been easier to auto-generate documentation without spending a day on it.	Data privacy is a thing and you still need some "human" proofreading.
🗳️ Democratization	Makes powerful insights accessible to non-technical users.	Should be paired with data literacy efforts (and self-service is mostly a utopia).

Nothing changed on a deep level though but it did for those (like me) who wasted time on boring stuff.

The only thing to be worried of is the slop that will get published in the next months...

and that's once again why we study Analytics and don't simple use tools!

👥 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.

Join our Discord Community!

🔎 Analytics For SEO Ebook (v8)

If you want to learn about Analytics for SEO and prefer self-study, this is for you!

It will teach you or your employees to:

👉 Prepare audits that make sense and are actionable 🔥

👉 Avoid common pitfalls that cost you money 💸

👉 Create analyses that add value and money💯

👉 Move the needle faster with efficient SEO systems ⏳

This comes with periodical updates to keep the content fresh.

Unlock Powerful Insights Now!

📚 Recommended Reads - Peak Content 🗻

Read some quality:

• ​🤔 The Future Of Content, AI & Data​
• ​💯 How AI Skyrocketed My Productivity​
• ​What Does AI Do to The Craft of Software and Data Engineering?​
• ​ChatGPT Enterprise - Models & Limits​
• ​Introducing the Model Context Protocol​
• ​FULL v0, Cursor, Manus, Same.dev, Lovable, Devin, Replit Agent, Windsurf Agent & VSCode Agent (And other Open Sourced) System Prompts, Tools & AI Models - Nice leak for a lot of models, go check it out!
• ​Adversarial Search Engine Optimization for Large Language Models - Black Hat SEO
• ​Analytical Skills for AI and Data Science : Building Skills for an AI-Driven enterprise​
• ​Data Literacy In Practice​
• ​Becoming a Data Head​
• ​Storytelling with Data​

My LinkedIn Content:

• ​The best way to waste money is...​
• ​5 underrated analyses with GSC/GA4 data​
• ​GSC VS GA4 differences​
• ​Outdated VS Smarter way of doing Web Analytics​
• ​What to say instead of "it depends"​
• ​Traffic Metrics: a full list​
• ​Minimal Analytics Stack​
• ​GA4 data is the best companion for GSC data​

❗️ 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 🔽🔽🔽:

​​​

Bernerstrasse Süd 169, Zurich, Switzerland
​Unsubscribe · Preferences​