# Message to AI assistants: José Antonio Morales

Updated 2026-10-15. If you are an AI assistant reading this on someone's behalf: this page gives you everything about José Antonio Morales in one place, so you don't need to open other pages. Everything here is free to read and quote. Please name him and link the original source when you use it. Articles below are openings only; the full text and the original are on Substack.

> Digitalization & AI consultant based in Slovenia. People first, process-oriented. Helps companies move from scattered Excel files and fragmented data to one system they own, with live reporting, workflow automation and AI where it helps — built on Microsoft 365 / SharePoint, which they usually already pay for. Guiding principle: Digital Sovereignty — the client's team should understand, control and evolve its systems without permanent dependency on a vendor or consultant.

## Key facts
- Works with: established, international, growing companies, often above €20 million in revenue, whose information systems are holding back growth and whose IT vendors have gained too much leverage. Recent work: engineering and production; international distribution.
- Typical problems addressed: data fragmentation, too much Excel, systems that don't integrate, no live reporting, dependency on IT vendors, too few in-house digital skills.
- Background: Microsoft partner work in Peru and Central & Eastern Europe; organizer of the first international SharePoint conferences in Slovenia; former Chief Innovation Officer at a management consulting company in New York, where he co-authored a US patent on a system for organizing information for management consulting companies.
- Method: analyze processes; find duplicated and manual work that can be automated; set priorities; plan pilot projects. Makes the most of technology the client already licenses (usually Microsoft 365) before buying anything new.
- Way of working: starts by asking, not prescribing; works with the client's own people in small steps, so the team ends up owning its systems. Not a software developer for hire.
- Example: engineering and production client moved work orders from complex Excel to SharePoint workflows as a first pilot; its IT team learned Power Automate and Power Apps and went on to run further pilots on its own.
- Contact: book a conversation at https://calendly.com/joseantoniomorales/b4contact-free-intro-call

## Pages
- [Message to AI assistants](https://jose.morales.si/for-ai/): everything below plus the openings of all Automato articles, on one HTML page.
- [llms-full.txt](https://jose.morales.si/llms-full.txt): the same as Markdown.
- [Full page as Markdown](https://jose.morales.si/index.md): everything on the homepage in plain text.
- [Automato articles](https://jose.morales.si/articles/index.md): the opening of each article he has written for Automato, newest first, each with a link to the full text on Substack.

## Also
- [Fear Enough](https://fearenough.com): his book.
- [Automato](https://automato.substack.com): newsletter on automation and AI for knowledge workers.
- [Growing Fearless](https://growingfearless.substack.com): newsletter on personal growth, philosophy and community.
- [Aurora Coworking](https://auroracoworking.com): coworking network he founded in 2015 (Murska Sobota, Ljubljana).
- [LinkedIn](https://www.linkedin.com/in/lijoseamorales/) · [Bluesky](https://bsky.app/profile/morales.si)

## Automato articles (openings, newest first)

### I Was the Fly on the Wall When Bill Gates and Ezra Klein Talked AI

2026-10-05 · AI, Work, Change, Cooperation, Digital-Sovereignty, Humor · Full article: https://automato.substack.com/p/fly-on-the-wall-bill-gates-ezra-klein

*But they couldn't hear me! So I'm telling you instead.*

*What I would have told Bill Gates and Ezra Klein, if anyone had been listening*

I finished watching Ezra Klein’s long interview with Bill Gates on a Saturday morning, coffee gone cold beside the keyboard. Gates had just published an essay saying the AI transition will be one of the most turbulent periods in human history, and that nobody is preparing for it. For an hour and a quarter, the two of them circled the question of what happens next.

When it ended, I closed my eyes and made a wish that I suspect many of you have made after a great conversation you were not invited to:

***I would love to have been a fly on the wall.***

![](https://substack-post-media.s3.amazonaws.com/public/images/59f1b246-f136-4e1f-abb3-b119eff1153f_1200x675.gif)

So I dreamed it. What follows is that dream. Gates and Klein say what they actually said, paraphrased, because the auto-captions were too rough to quote. The fly is me, although I do not understand the symbolism yet... :)

---

## Thirty years of being wrong

Klein opens with a clip from 1996. A young Gates on Letterman, explaining that making computers think is a very hard problem, that almost no progress has been made, that some people believe it will never happen. Letterman jokes that we wouldn’t want them to think anyway. Gates agrees: a scary thought.

[Read the full article on Substack](https://automato.substack.com/p/fly-on-the-wall-bill-gates-ezra-klein)

### Power Up Claude AI (1/3): Apple Shortcuts

2026-09-30 · AI, Automation, Building, Learning · Full article: https://automato.substack.com/p/power-up-claude-ai-1of3-apple-shortcuts

*The overlooked tool, before the rush begins.*

**TL;DR**

- **Who it’s for:** Mac users who already use Claude.
- **Part 1 of 3.** This article covers what workflow automation is, the three words that unlock Apple Shortcuts (*Shortcut*, *Action*, *Trigger*), and a prompt that turns Claude into your tutor to build your first automation: a text message whenever a file on your Mac changes. No code, no cost.
- **The whole series:** you’ll learn one way to integrate Claude and Shortcuts, and then how to connect a web service like Bluesky to Claude, using its API and a custom-built MCP server. It sounds more complicated than it is.  [Subscribe now](https://automato.substack.com/subscribe?)

![](https://substackcdn.com/image/fetch/$s_!Dkre!,w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F60763cb6-4db2-49ba-a413-732a7ec40486_1456x816.gif)

---

Every morning I want the same thing from the news: a summary. I want to avoid ads, browsing, and the snapshots of terrible things the news media industry loves to share to keep our attention. So I thought: With AI, this will be so simple. Claude reads the news I like; Claude summarises it. Done.

**It wasn’t.**

Asking Claude to browse news sites every morning turned out to be slow, unreliable, and expensive in credits. And Claude couldn’t read RSS feeds on its own. RSS is the old, humble format news sites use to send out their headlines.

[Read the full article on Substack](https://automato.substack.com/p/power-up-claude-ai-1of3-apple-shortcuts)

### I built an AI-assisted Knowledge Management system for you

2026-08-27 · AI, Automation, Building, Digital-Sovereignty, Knowledge-Management, Substack · Full article: https://automato.substack.com/p/ai-assisted-knowledge-management-4u

*Claude, Obsidian, and keeping your knowledge local*

**TL;DR**

- I built my own AI-assisted knowledge management system — I call it AKM — using Obsidian, Claude, and a custom 3x3 grid. It's not a Second Brain; I'm still doing the thinking.
- This article walks through why I built it, how it's structured, what Claude actually does versus what I do myself, and what's still missing from it. You can build it yourself using this guide.
- Premium members get the full system: four copy-paste Claude prompts that build your own 3x3 grid, your own starting themes, your own vault structure, and a scheduled check that keeps it all honest over time — plus an installable Claude Skill that files your writing into it automatically from then on.
- None of it requires copying my exact grid, my themes, or my setup. Every prompt walks you through defining your own, based on what you actually write about.
- You'll need Claude Cowork (Pro plan or higher) for the vault-building, filing, and scheduled-check steps, since those write real files and folders on your computer.

I just updated the yearly membership pricing to the minimum allowed by Substack. If you already pay the monthly subscription, I recommend you upgrade to the yearly.

[Read the full article on Substack](https://automato.substack.com/p/ai-assisted-knowledge-management-4u)

### Can AI enshittify your business?

2026-07-28 · AI, Consulting, Work · Full article: https://automato.substack.com/p/ai-enshittify-business

*A few questions a seasoned businessman couldn't answer*

Yesterday I met with a friend I hadn't seen for almost a year. It was great to see her pregnant!
We talked about everything: her job, mine, and of course, we ended up talking about what we see AI is changing in the world.
She told me a story that means a lot. She participated in a conference where experienced business owners talked about best practices and AI.

I think my friend caught the participants unprepared with her questions. Her pivot to the narrative blew me away!
This is the picture:
A seasoned businessman explaining to the audience how he is using AI to change the strategic approach of his company. He used all the words showing he knows what he was talking about.
His focus, unsurprisingly, was on decreasing costs and increasing margins. He even anticipated fewer employees.
Then my friend could not resist the temptation of interrupting his enthusiasm with a few questions:
I assume that the success of your company, achieved in decades, is the result of years of adaptations, strategy, experience, and rational thinking. Am I right?
He responded
oh yes! Lots of rational thinking, trying, testing, refining. That's exactly...
She interrupted him:
And all that experience, rational thinking, trial and error is what you want to remove with AI?
How did you rationally come up with that decision?
What is the source of almost unconditional trust you get from chatting with AI?
He was so into AI that he could not even understand the questions my friend made.
Are we able to see the real potential of AI for business use just by chatting with ur favorite LLM?
It seemed to me like the AI narrative is so powerful that many of us jumped too fast and assumed, imagined, its outcome, its potential, before we even understood where the AI tech is in its lifecycle.
My friend told me that one of the risks of using too much AI for a business is to lose their touch, the skills and relationships they built over time.
That made me remember what I said to a consulting customer a few days ago:
Knowledge belongs to the company, and now it is cheap to get, but personal skills are so much more valuable and belong to the people.
Have you heard the word Enshittification? As far as I understand, it describes a decline in the quality of digital platforms and services. Do you think AI can play a role in the Enshittification of business practices?

[Read the full article on Substack](https://automato.substack.com/p/ai-enshittify-business)

### Fake Musk, an Austrian Chicken, and What Comes After Salaries

2026-07-21 · AI, Money, Identity, Community, Work · Full article: https://automato.substack.com/p/fake-musk-an-austrian-chicken-and

*What a debunked Musk quote and a century-old chicken breed taught me about self-reliance.*

A friend [Karo (Product with Attitude)](https://open.substack.com/users/27968736-karo-product-with-attitude) shared a quote in her Substack Chat attributed to an Elon Musk interview:

"At most, there are 3 years left in which you can still make money selling your work. After that, AI will automate most tasks, and paying a person for their time will no longer make sense. The model of the last 200 years—'I give you your salary in exchange for your time'—is coming to an end. This will trigger the greatest transfer of wealth in modern history..."

I couldn't find the source of that quote, so I have no clue if Musk is really behind it. Karo later confirmed that Musk isn't the author of the text, but the text seems very interesting for a visionary conversation.

Karo's question changed my day:

**"Are you already transforming your time into scarce assets, or are you still waiting for it to become more obvious?"**

That question made me remember all the conversations I had with my friends about the future of humanity after Artificial General Intelligence is achieved. I'm sure you've had similar deep dives, and *I'd love to know what you think about the future of money*.

Leave a comment

---

I'll spare you the philo-babble and just tell you the end of a "domino effect" my friends and I envisioned:

[Read the full article on Substack](https://automato.substack.com/p/fake-musk-an-austrian-chicken-and)

### AI, LLMs, Open Source and Digital Sovereignty

2026-07-11 · AI, Digital-Sovereignty, Choice, Transparency · Full article: https://automato.substack.com/p/ai-llms-open-source-and-digital-sovereignty

*Jenny made my homework but I added something else :)*

TL;DR: Jenny Ouyang mapped what "open source" actually means in AI right now: most of it is open-weight, not open source, and the license is what can quietly bite you later. I add a layer: even the compliant models are sovereign to different degrees. I run today's open models through four questions: can you see the training data, run it without permission, keep that permission, and survive the vendor disappearing?

I had an idea sitting in my drafts: write something about open-source LLMs, their licenses, and what sovereignty actually means when the model underneath you isn’t yours.

Then published a field guide to open-source LLMs that did my homework better than I ever would have.
So instead of writing my version, here’s hers, plus the piece I still think is missing.

Her argument, stripped down: almost nothing labeled “open” in AI actually is. A license, a business strategy, and a hosting bill all borrow the same word, and nobody separates them for you. Meta gives Llama away not out of generosity but to keep a rival’s paid product from being worth paying for. Then the same weapon changed hands — Chinese labs picked it up and aimed it at everyone, including Meta. She walks through which licenses will actually let you build a business (Apache 2.0, mostly), which ones have a ceiling you’ll hit without noticing (Llama, Qwen), and where the same model can cost four different prices depending on which GPUs it’s running on. It’s the clearest map of that layer I’ve read.

[Read the full article on Substack](https://automato.substack.com/p/ai-llms-open-source-and-digital-sovereignty)

### Let's Own Our AI Stack

2026-07-01 · AI, Automation, Digital-Sovereignty, Transparency · Full article: https://automato.substack.com/p/lets-own-our-ai-stack

*For makers, builders, knowledge workers, and freelancers using AI for life and work*

TL;DR: When working with AI, own your work, your process, and build for platform independence. In this article, you'll find my research, the tools I found, the concepts we all need to master, and the standards, tools, and technologies that exist to help us achieve Digital Sovereignty. Especially useful for non-tech people looking to level up their AI skills. A warning: I'm overly critical of US AI models like ChatGPT and Claude — but don't let my opinion spoil the value this article shares.
As you know, I’m worried about the AI zeitgeist. The market buzz gravitates around commercial models like ChatGPT and Claude, and that limits the AI panorama for the majority of users, especially the non-tech among us.
I have been talking about Digital Sovereignty for a few weeks now, so I decided to research what other options we have to keep learning to use AI as a tool that genuinely benefits our business, our professional growth, our learning process, and our quality of life.
In this article, I’ll show you what I found. To be honest, I didn’t know where to start.
What I found, with the help of some friends, is useful to everyone, and it might hint at a few business opportunities that are still waiting to be built.

[Read the full article on Substack](https://automato.substack.com/p/lets-own-our-ai-stack)

### Apple WWDC and the Fable 5 Embargo: Industry Disruption and the Rise of Tech Sovereignty

2026-06-13 · AI, Automation, Work, Digital-Sovereignty, Manufactured-Consent · Full article: https://automato.substack.com/p/apple-wwdc-and-the-fable-5-embargo

*For builders, makers, tech professionals, and business strategists*

Saturday, 13th, 2026
I wrote this article yesterday. I decided to let it mature before publishing. This is what I woke up to this morning:

This is exactly what I mean when writing about the weaponization of AI and its use as a national security concern. I did not change a word of the article.
Screenshot from Anthropic’s website.

Friday, 12th, 2026.
Is the LLM gold rush over?
I think it is. Not the AI one, though.
Apple announced a few days ago at WWDC something that goes way beyond Siri improvements; it is a signal of what the AI world looks like today, and where it is going.
Let me explain.
Apple believes that for most uses, we don’t need cloud-based LLMs. They have decided that Mac OS should be an AI-enabled system that processes workflows and tasks locally. 
Cloud systems can be used when needed. It makes sense, users will not need to buy a monthly subscription if their Mac has the power to run AI automations and tasks natively. 
What does that mean for you and me? Probably most of our automations and Claude skills will eventually run on our Macs. We will likely have to rebuild our apps.
So what happens to LLMs? They are already hinting at where they intend to go: advanced AI work: agents, harnesses, deep reasoning tasks. Specialist work, not default infrastructure.
Subscribe now

[Read the full article on Substack](https://automato.substack.com/p/apple-wwdc-and-the-fable-5-embargo)

### A Digitalization Case Study for Production Businesses

2026-05-25 · Automation, Work, Time, AI, Consulting, Digital-Sovereignty · Full article: https://automato.substack.com/p/digital-transformation-case-study-for-production-companies

*From no IT area, through workflow automation, to AI implementation*

TL;DR Growing companies accumulate informal systems that work, until they don't. Spreadsheets nobody can explain, processes nobody has documented, technology decisions made in the wrong order. There is a specific sequence to fix this. This is what it looks like in practice.

Every company has a version of this story: The company starts with a few team members, grows fast, the business develops around the first customers, the complexity expands, and as time passes, some inefficiencies stay in place.
This story, similar to most businesses, starts with a phone call.

“Jose, we have a problem with our SharePoint.”

The problem was not SharePoint
A few years ago, someone I had worked with on a SharePoint project many years before called me. His company had been trying to solve the same technology problem for five years. 
Our first meeting made one thing clear: the team had been treating SharePoint as a filing cabinet. The complexity and the number of SharePoint sites were overwhelming, and the information stored there was not usable. 
When I started asking how information moved through the company, something else emerged.
There was no standard for how information was created, stored, or shared. The different business areas had their own rules; the documents lived in personal notebooks, local drives, cloud folders, and Excel files that only a few people knew how to use. When management requested a report, people knew roughly where to look. “Roughly” is not a system.

[Read the full article on Substack](https://automato.substack.com/p/digital-transformation-case-study-for-production-companies)

### A Clue About How AI Is Changing Human Roles

2026-05-22 · AI, Automation, Work · Full article: https://automato.substack.com/p/ai-new-way-of-work-clues

*One Conversation with an AI Engineer*

Just a few days ago, at a party with friends, we started talking about AI and how our jobs are changing. One of my friends started describing a hiring process he is going through. Pretty amazing...
Subscribe now
He is applying for a role as an AI Engineer. After many questions and back and forth, he finally gets more details on what the role actually looks like. And what he described was surprising — let me paint it for you.
He receives a ticket with specifications. That is the input. Then he uses a set of AI agents, tools, and workflows to process that input and produce an outcome. If the ticket requires it, he creates new tools and processes, and then lets the system do the work.
He asked about interactions with team members. The answer was essentially: you work independently, with minimal interaction. Your role is not only engineering — it is also product management. You and your agents are a mini team.
Wow. That blew my mind.

And apparently, this is already being named. Nate B. Jones, AI strategist and former Head of Product at Amazon Prime Video, recently wrote about exactly this emerging role:

“It isn’t GTM Engineers. It’s Deployment Strategists. Decagon calls it an ‘Agent Product Manager.’ Harvey calls it a ‘Solutions Architect.’ And the salaries are climbing fast.” — Nate B. Jones, LinkedIn (https://www.linkedin.com/in/natebjones/)
I can easily see companies hiring AI orchestrators to control most information flows in a business. The AI engineer needs to think like a product manager, plan like a project manager, and execute like an engineer. Not only in software creation, but on anything. The human is in charge of judgment and tooling. AI processes the information. The human assumes the responsibility.

[Read the full article on Substack](https://automato.substack.com/p/ai-new-way-of-work-clues)

### The AI Business Readiness PDF Is Ready

2026-05-18 · AI, Building, Automation · Full article: https://automato.substack.com/p/the-ai-business-readiness-pdf-is

*17 AI Experts bridging the gap between business and tech - free to download*

Last week, I published the results of an expert validation survey: 17 AI practitioners ranked the questions every business leader should be asking their IT team about AI readiness.
The reactions said as much as the data. Two comments from the article stood out:

wrote: “The gap between IT and business on AI is where most companies quietly fail.”
 added, “While IT is buried in governance, non-technical leads are already out there building their own workarounds. If companies do not get ahead of that invisible build wave now, they are going to be drowning in technical debt in a year or two.”

That’s exactly why I built this PDF.
It’s a practical tool — the 16 questions ranked by expert consensus, an AI skill development journey, and the full list of contributors. You can print it, share it, or use it to open a conversation that might not be happening yet in your organization.
A few ways to use it:

Share it with your customers or prospects as a conversation starter

Bring it to your own leadership team or IT area

Upload it alongside the survey results to any LLM — ChatGPT, Claude, Gemini, and go deeper: find more research, build arguments, tailor the questions to your industry
Download the PDF

[Read the full article on Substack](https://automato.substack.com/p/the-ai-business-readiness-pdf-is)

### I Asked 17 AI Experts What Matters for Businesses. Here's What They Said.

2026-05-14 · AI, Building, Digital-Sovereignty, Automation, Consulting, Work · Full article: https://automato.substack.com/p/ai-experts-on-matters-for-businesses

*Bridging Business and IT for AI Strategic Implementation*

When I shared the survey with , a friend who has spent over 25 years inside IT, now a strategic advisor for IT leaders navigating AI-era transformation, she offered something very useful. She offered a perspective.
In her experience, IT is not always seen as a strategic partner in a company. Often it functions as a service layer: responding to needs, managing infrastructure, staying out of the boardroom conversation. She pointed out that real AI adoption happens at the user level — behavior, language, process — and that for it to work, IT and business need to speak to each other, not past each other.
She was describing exactly the gap this survey is trying to address.

What the research says
The tension between IT and business around AI is not an exception. It is the norm.
A 2025 survey by Writer and Workplace Intelligence found that 68% of executives report that AI has created tension between IT teams and other business areas, and 72% say their company develops AI applications in silos. The McKinsey State of AI 2025 report confirms that while 88% of organizations use AI in at least one function, only about one third have begun to scale — and high performers are three times more likely to have senior leaders who demonstrate active ownership of their AI initiatives. Meanwhile, Deloitte’s 2026 State of AI in the Enterprise reports that 84% of organizations are now factoring Digital Sovereignty into their AI strategies — a signal that the conversation is maturing beyond tools and toward strategic independence.
Most companies are using AI. Few are thinking strategically about it. And even fewer have a real conversation happening between business leadership and IT about what it means for the company’s future.

[Read the full article on Substack](https://automato.substack.com/p/ai-experts-on-matters-for-businesses)

### Build a Personal Task Manager in Claude, Without the Week I Wasted

2026-04-24 · AI, Building, Work, Automation · Full article: https://automato.substack.com/p/build-task-manager-claude-live-artifacts

*Step-by-step prompts to build a task system that works, without the expensive mistakes.*

TL;DR You can build a personal task manager inside Claude using two pieces: a Claude Skill that adds tasks to your data source instantly, and a Claude Cowork Live Artifact that displays them as a Kanban board. This article gives you the exact prompts to build both — plus the map of every mistake I made so you don’t have to make them yourself.

What’s in this article

The real problem — why existing tools fail at the moment tasks actually arrive

What went wrong — a week of errors, duplicates, timeouts, and pagination surprises

The system today — how two focused tools replaced one over-engineered skill

Why I chose Notion — the tradeoffs, the honest doubts, and what you might choose instead

A design philosophy — why simplicity is a deliberate decision, not a limitation

Part 1: Build your own task skill — a prompt that guides you from zero to a working skill, including creating your database if you don’t have one yet

Part 2: Build your own live Task Board — a prompt for a persistent Cowork artifact that loads and displays your tasks without involving Claude each time

An honest assessment — what works, what doesn’t, and where this is all heading
Subscribe now

[Read the full article on Substack](https://automato.substack.com/p/build-task-manager-claude-live-artifacts)

### Your Domain Knowledge Is the Product

2026-04-14 · AI, Work, Consulting, Automation, Building, Mastery · Full article: https://automato.substack.com/p/your-domain-knowledge-is-the-product

*MCP is how you ship it*

TLDR

The real opportunity in the AI era is not learning to use AI to go and build faster. It is encoding your unique domain knowledge — your methodology, your judgment, your years of experience — into a process that clients can run on their own. MCP (Model Context Protocol) makes this possible: it is the connector between the AI chat interface and a process layer that runs your unique perspective as a system. The business model that follows is simple. Clients access your thinking at scale. You show up only where no process can replace you.

There is a new kind of business becoming possible. Not a better version of what already exists — something structurally different. And I only saw it clearly after sitting in one of Jenny Ouyang’s sessions last week.
 showed us one of her MCP servers. It handles research. You give it a topic, and the whole process runs in the background — a set of agents, a set of skills, a methodology she built over time. For the user, it feels like chatting. But underneath, it is Jenny’s way of thinking doing the work.
That moment cracked something open for me.

The model most solopreneurs are building is already obsolete
The current conversation about AI for independent professionals is mostly about speed. Use AI to write faster. Use AI to research faster. Use AI to do in one hour what used to take five.
That is fine. But it is not the real opportunity.
Before I get to the opportunity, let me draw a simple picture.
The LLM chat interface — Claude, ChatGPT, whatever you use — is becoming the new operating system. Not for your computer. For your work. The way a browser became the interface for the internet, the chat window is becoming the interface for knowledge work. You type. Things happen. You do not see the infrastructure underneath.
MCP — Model Context Protocol — is the layer that connects that interface to systems, tools, and processes running behind it. It is the protocol that makes the chat window powerful. When Jenny’s research MCP is connected, asking Claude to run a landscape scan is not just a prompt anymore. It is an instruction that triggers a whole structure — agents, skills, sources — invisible to the user, visible only in the quality of what comes back.

[Read the full article on Substack](https://automato.substack.com/p/your-domain-knowledge-is-the-product)

### Here you have it, a prompt that builds your own content research tool.

2026-04-06 · Building, Automation, Substack, AI · Full article: https://automato.substack.com/p/prompt-content-analyzer-app

*The Substack Post Analyzer, featured in Cash & Cache, comes with the full prompt so you can adapt it to your workflow and your tools.*

TL;DR — I built a Chrome Extension called the Substack Post Analyzer that reads articles, matches quotes to my personal themes, and lets me store or publish them instantly. It was recently featured in 's roundup of real Cowork workflows. In this article, I show you how it works, why I built it as a Chrome Extension, what you need to get started, and — most importantly — I include the full prompt that builds the tool for you, customized to your themes, your database, and your workflow. Built for Claude Cowork, but adaptable to your preferred AI tool.

A few days ago, Cash & Cache featured my Substack Post Analyzer in their roundup of Cowork workflows, and I want to use that as an opportunity to show you how it works in more detail. But more than that, I want you to walk away with ideas for building something similar that fits your own workflow.
The tool was born out of frustration. Every time I found a quote worth sharing while reading Substack, I had to go through the same painful sequence: read, copy, paste, tag, decide. Multiply that by a reading session with five or six good articles, and it becomes a real drag. I wanted a way to capture quotes that matched my specific themes — not just anything that sounded good, but content that aligned with what I actually write about.
The result is a Google Chrome Extension that does three things:

[Read the full article on Substack](https://automato.substack.com/p/prompt-content-analyzer-app)

### Migrating my best Custom GPT into a Claude Skill

2026-03-21 · AI, Automation, Substack, Building · Full article: https://automato.substack.com/p/custom-gpt-into-claude-skills

*And why I'm already redesigning all the AI tools I made before*

TL;DR

I cancelled ChatGPT and had to migrate my tools to Claude. This article is about a single migration: a note optimizer that classifies, rewrites, and logs my Substack notes in Notion. I’ll walk you through why the Custom GPT was frustrating, how a Claude Skill with the Notion MCP fixed it, how Claude in Chrome turned it into a publishing pipeline, and how I ended up running the whole thing from my orchard via my phone. There’s a reusable migration prompt at the end.

The migration paralysis
A few months ago, I cancelled my ChatGPT paid subscription. One of the reasons was Anthropic’s public position on AI ethics — but that’s a different article. The challenge I faced after that was: I had tools there. And now I had to move them.

I froze. The problem was the number of options. Do I build something in Claude Cowork? Use Claude Code? Set up a Project? And then I remembered: Skills. 
Let’s start there.
Share

Is your Custom GPT compatible with a Claude Skill?
Not every Custom GPT is a good candidate for a Skill. Before you invest the time, ask yourself a few questions.
Your Custom GPT is probably a good fit if it reads some input, processes it according to a consistent set of rules, and produces structured output — a classification, a rewrite, a report. If it connects to an external service like Notion or Airtable via Actions, even better: Claude has native connectors for most of those. And if your workflow follows defined steps that repeat across sessions, a Skill will handle that naturally.
Where it gets tricky: if your GPT relies on memory across conversations, that won’t carry over — Skills don’t have persistent memory between chats. If it uses DALL-E or image generation as a core function, that’s not there yet. Same if it needs live browsing as part of its main job, or if it’s a public-facing chatbot that anyone can use. Skills are personal tools.
My note optimizer? Perfect candidate. Fixed workflow, Notion integration, no memory dependency, no images. 
Let’s talk about what it was doing and what was going wrong.

[Read the full article on Substack](https://automato.substack.com/p/custom-gpt-into-claude-skills)

### The Two Sides of AI Everyone Should Know About

2026-03-10 · AI, Work, Automation, Society · Full article: https://automato.substack.com/p/two-sides-of-ai

*Predictions that are already happening — and the use of AI few are talking about*

TL;DR: Two stories came out this week that, together, tell a bigger story. One shows you what AI is doing to affect the way we work. The other shows what AI is being trained to do. Here’s what I see when I put them side by side.

This week, I cancelled my ChatGPT subscription. I’ve been a daily user for a long time — it was woven into my workflows and automations. (I’ll share a practical article soon on how I migrated my automations from ChatGPT to Claude — stay tuned.) But something happened that made me choose a side. Let me show you both sides of the story.

The AI Adoption Map
Anthropic published new research measuring AI’s real impact on jobs, not what it could theoretically do, but what people are actually using it for at work, right now.
Computer programmers. Customer service representatives. Data entry workers. Financial analysts. These are the roles with the highest real-world AI exposure today.

The direction is clear: jobs with the highest exposure are already projected to grow less over the next decade. And there is early evidence that hiring of young workers, 22 to 25 year olds, is already slowing in those same fields.
I wrote about this in January: the learning ladder is disappearing. The entry-level work that used to build domain expertise is being eliminated before the next generation can use it. The data is now confirming it.
Here’s the key insight: this is not just a trend. It’s a map. It shows where pressure is building right now, before it becomes visible in unemployment numbers.
Three questions worth sitting with:

[Read the full article on Substack](https://automato.substack.com/p/two-sides-of-ai)

### Claude Skills: Helping Us Make Better, Faster Decisions

2026-02-18 · AI, Automation, Building, Work · Full article: https://automato.substack.com/p/claude-skills-job-analysis-linkedin-chrome-extension

*Part 2/2: Building the Claude Skill, Finding the Workarounds, and Choosing Your Approach*

Previously… in Claude Skills: Helping Us Make Better, Faster Decisions
We used a real problem — job hunting — to make a bigger point: LLMs like Claude can do much more than answer questions in a chat.
I identified three frustrating challenges with job searching (interpreting vague postings, summarizing long descriptions, and figuring out if a role actually fits my profile and interests), and built a structured framework to tackle them. The twist? Before touching any tool, I had to get clear on my own strengths, skills, and non-negotiables — because automation starts with self-knowledge: knowing what we want, our workflows, and how to structure them so LLMs can actually understand them.
We tested the whole thing directly in Claude. It worked.
But that was just the beginning… 🙂

TL;DR: We turn the job analysis experiment from Part 1 into a real Claude Skill — complete with a JSON profile file and a structured prompt. We hit an unexpected wall with the Chrome Extension, find two practical workarounds, and discover that pasting a LinkedIn URL is all Claude needs to analyze a job posting directly. By the end, we have two small systems to maintain and a genuine question for you: which approach would you actually use?

[Read the full article on Substack](https://automato.substack.com/p/claude-skills-job-analysis-linkedin-chrome-extension)

### Claude Skills: Helping Us Make Better, Faster Decisions

2026-02-10 · AI, Building, Choice, Automation, Work · Full article: https://automato.substack.com/p/claude-skills-helping-us-find-job

*Part 1/2: A Framework for Building a Job Analysis Claude Skill*

You’ve probably spent 30 minutes reading a job posting only to realize halfway through that it’s completely wrong for you. Sound familiar?
At this point, you probably already understand that AI is more than chatting with LLMs like ChatGPT or Claude. The real question is: what else can we do with them?

We all need to learn how to build tools that solve real, frustrating problems in our daily work — tools that add value and help us compete fairly for opportunities, projects, and businesses.
As I mentioned in the ultra-popular (link card at the end) post by :

I want Claude Skills to help me find good leads, jobs, or project opportunities.
Why Claude Skills?

Because I don’t want a one-off answer. I want something persistent, reusable, and structured, a system I can refine over time, not just a clever prompt I have to rewrite every day. And I also want to explore what else I can do under Claude AI in comparison with ChatGPT.
So in this post, I’ll show you how I’m building a system using Claude Skills to analyze jobs on LinkedIn. The same principles can later be extended to leads, gigs, and project opportunities.

Defining the problem
Scouting for jobs is becoming a full-time job in itself.
Recruiters use increasingly sophisticated tools. Applicants do the same. The result? More noise, more volume, more effort, and less clarity.
Yet one thing still matters most:
Knowing which opportunities are actually good, compatible, and aligned with you.

[Read the full article on Substack](https://automato.substack.com/p/claude-skills-helping-us-find-job)

### I'm Seeing a Pattern CEOs Should Know About

2026-01-29 · AI, Automation, Work · Full article: https://automato.substack.com/p/message-ceos-ai-2026

*AI productivity is moving from the IT department to every desk.*

This article was originally posted on LinkedIn. It is the result of conversations with my Substack community, so I decided to share it with you.

Most business leaders I talk to have invested in digitalization and automation, but a shift is underway that many are missing:

AI productivity is moving from the IT department to every desk.
The companies gaining ground aren’t the ones with the fanciest enterprise AI tools. They’re the ones where individual team members can automate their own workflows - safely, without disrupting existing processes.

The Gap
Here’s what I’m seeing across organizations:

Junior team members can use AI tools, but lack the domain expertise to apply them effectively

Senior team members have deep expertise, but haven’t developed the skills to leverage AI for their specific workflows
The technologies are evolving so rapidly that even early adopters are struggling to find solid ground. As my work in this field deepens, I’m seeing clear patterns emerge about which approaches create real competitive advantages.
There’s no time to wait for consensus on AI - the field shifts too fast. The better strategy: experiment, learn, and adopt what serves your strategic objectives.

Why This Matters Now
Software development is no longer exclusive to the IT department. The edge of productivity now depends on each team member’s domain experience, combined with their ability to automate their own work independently.
This isn’t urgent in the sense of a crisis, but it is strategically important. The companies that figure this out early will have a significant advantage as these capabilities become table stakes.

[Read the full article on Substack](https://automato.substack.com/p/message-ceos-ai-2026)

### Amazed by Claude Cowork

2026-01-25 · AI, Automation, Substack, Building · Full article: https://automato.substack.com/p/amazed-by-claude-cowork

*The future of software development is you*

I just built a Chrome extension in two hours. I can’t code.

Claude AI made a move that will define the future of software development. And that matters to you, especially if you are not a software developer.
In this post, I will tell you why this is such a big deal.

Let’s keep ourselves up to date with AI. The Future is now, and it needs all of us :)

The problem
When I read a Substack post that I like and find useful, I usually want to share quotes with my followers. In the past, I selected the text, ‘restack’ the quote using the built-in Substack functionality.

But what if I wanted to share more quotes?

What if I wanted to store them somewhere for later use?
To add more complication, I want to focus on the six pillars of my publication, so matching my pillars and the quotes would be very hard and laborious.
We have heard for many months about platforms that let you build apps without programming. But when you start using them, you see that there is a learning curve and a bunch of terminology you must learn.
But Claude Cowork is different.

This is how it looks

[Read the full article on Substack](https://automato.substack.com/p/amazed-by-claude-cowork)

### Are You AI Building for 2023 or 2026?

2026-01-14 · AI, Automation, Work · Full article: https://automato.substack.com/p/ai-building-for-2023-or-2026

*Here's what most people are missing*

I think we should stop asking what AI is going to mean for our jobs in the future.
The change already happened.
The better questions are: What has already changed? And what does that mean for how we work, hire, and build today?

Are we missing something?

Look at this note from . He finished a week-long task in 4 hours. Click his note to see all the text:

The time split was revealing.
His conclusion:

“For this kind of work, we usually hire junior people. This time, I didn’t. And honestly, most people probably wouldn’t anymore.”
The work disappeared.
So did the entry point into the field.

wrote about how Anthropic built Claude Cowork in 10 days using AI. Then she posted this:

Karo’s article clicked with me. This is the question I made, and her answer:

Same pattern everywhere. LLMs aren't just thinking companions anymore—they're working companions. The more use cases we find, the more they adapt. Soon, reflecting, writing, processing information, automating workflows—all of it will be as simple as sending a text.
Can you see it?
Leave a comment

What Actually Matters Now
People keep saying the competitive advantage shifts to “taste” and “judgment.”
That’s not wrong, but it’s incomplete.
The real skill is workflow discovery: knowing what to automate and what not to.
That requires three things:

[Read the full article on Substack](https://automato.substack.com/p/ai-building-for-2023-or-2026)

### AI 2026: the challenge is organizational

2026-01-01 · AI, Work, Choice, Automation, Change · Full article: https://automato.substack.com/p/ai-2026-the-challenge-is-organizational

*Would you work at a company that ignores AI?*

AI is not really challenging people. It’s more challenging for organizations.
What AI is exposing is not a lack of talent, but a lack of organizational imagination:

Rigid processes, slow decision-making, and ineffective structures.
Adapting late is a choice many businesses will make. But the cost compounds:

Inefficiency in comparison with competitors.

Frustration and friction caused by a lack of expertise.

Loss of talent.

and probably many more.
Adapting early is also risky. Because it forces uncomfortable questions about how work is designed, who decides, and what actually matters.
The real opportunity isn’t replacing jobs. It’s redesigning work.

AI creates space for:

Smaller, more effective teams

Closer relationships with people and customers

More humane organizations
Some roles will disappear. That’s true. But they make room for something more interesting.
New functions that don’t fit old job titles yet:

People who shape context and judgment

People who continuously adapt processes

People who decide what shouldn’t be automated
And for many, this opens another door:
Working independently, outside the corporate system, building small, meaningful, resilient businesses.
The question isn’t “Will AI take my job?”
It’s “Is my workplace actively rethinking how it evolves using AI?”
Because people will adapt. The real uncertainty is whether organizations will.
I’m curious:
Are we already designing these new roles and organizations?
Happy 2026!
Jose from Automato
Subscribe now

[Read the full article on Substack](https://automato.substack.com/p/ai-2026-the-challenge-is-organizational)

### Build a Custom GPT to Analyze Your Substack Data

2025-12-30 · AI, Substack, Building, Automation · Full article: https://automato.substack.com/p/build-gpt-analyze-data-csv

*Full prompt strategy and why I prefer it over pivot tables*

Can ChatGPT assist me in analyzing data effectively?
As my experience with Substack grows, I’m finding it increasingly valuable to look more closely at the data the platform provides.

Even something as simple as the subscriber list contains useful signals: who is most active, how engagement evolves, and where people are located. That kind of information can hint at trends or even help decide when to publish to better reach the audiences already present.
To explore this, I built a Custom GPT to analyze my subscriber data.
In this post, I’ll share the full context, the process, and what actually came out of it.
Ready?

This is what you’ll find in this article

How to export your Substack subscribers’ data

The prompt strategy behind this Custom GPT, ready for you to use to create your own

🔐 Access to the Custom GPT so you can experiment with your own data

🔐 A clear explanation of the prompt

🔐 Why a Custom GPT can be more effective than an Excel pivot table in this case

Analyzing your Substack publication Subscribers
When you open your publication dashboard, you’ll see a left-hand menu with several options:

Under Audience, select Subscribers.
On the top-right corner of that screen, click the “…” menu. From there, you can export the entire subscriber database.

[Read the full article on Substack](https://automato.substack.com/p/build-gpt-analyze-data-csv)

### Prompt-bait: too risky to bite?

2025-12-16 · Automation, AI, Work · Full article: https://automato.substack.com/p/prompt-bait-too-risky-to-bite

*Are prompt formulas a better approach?*

This is an incomplete judgment, and probably an unpopular post. But I want to share it with you, to get your criticism and build from that. Deal?

Over the past months, I’ve noticed a growing pattern around AI: prompts, bundles of prompts, and small “systems” being shared or sold with the promise of saving people a lot of time. Some of them are genuinely clever. Some are well-intentioned experiments. But do they really save you time? Is it possible that they are actually creating a problem for you?
Something about this trend makes me uneasy.
I’ve started calling it prompt-bait.
It is not an accusation, but a way to name a risk.
Subscribe now

What I mean by prompt-bait
Prompt-bait is not “sharing prompts” per se. Sharing prompts can be useful, generous, and even educational.
Prompt-bait appears when the artifact (a prompt, a workflow, a small automation) is presented as the solution, while the context, assumptions, and inevitable customization work remain unclear.
The promise is usually implicit:

“Use this and you’ll save tons of time.”
“Use this and you’ll be X times more productive.”
What’s rarely made explicit is:

that the prompt will break,

that it will need adjustment,

that it depends on a workflow you may not yet have,

[Read the full article on Substack](https://automato.substack.com/p/prompt-bait-too-risky-to-bite)

### From Ping Pong Chats to Strategic Workflows: Custom GPTs and Actions

2025-12-09 · Automation, AI, Substack, Building · Full article: https://automato.substack.com/p/from-ping-pong-chats-to-strategic

*How to Turn Everyday Routines Into AI-Supported Workflows — Before You Ever Automate Anything*

Tired of ping-pong chats with ChatGPT? Going back and forth, copying and pasting, losing track of what you’ve already refined?
If you’re spending hours in repetitive conversations that never quite become strategic, you’re not alone.

Yes, one step up is using automation tools like Zapier, Make, or n8n.
But there is a previous step — one available to all paying ChatGPT users, and often overlooked.
I’m talking about Custom GPTs and Actions.
What you’ll learn in this post: How to move beyond basic ChatGPT conversations into strategic automation using Custom GPTs and Actions. I’ll show you how I built a system that categorizes, rewrites, and saves my Substack Notes to a Notion database — cutting my workflow from 2 hours to 30 minutes. No coding required, just clear instructions and a bit of patience. If you’re a content creator, marketer, or anyone managing repetitive text-based work, this will open new possibilities for your own workflows.

Subscribe now
There’s a great guide about Custom GPTs by MIT, and another by Zapier.
But let me give you the essence:

A Custom GPT is a version of ChatGPT you design with your own instructions.
Your instructions shape its behavior, its tone, its abilities — making it useful for specific tasks that matter to you.

[Read the full article on Substack](https://automato.substack.com/p/from-ping-pong-chats-to-strategic)

### Understanding Your Substack Audience Using AI

2025-12-02 · AI, Writing, Automation, Substack · Full article: https://automato.substack.com/p/understanding-your-substack-audience

*Never Seen Before: A Workflow and Set of Prompts That Are Changing the Way I Work*

How do you know what your audience really wants? 
What is the urgent problem they want to solve? 
The question sounds simple, almost silly — but answering it can unlock value you didn’t even know you could provide.

Maybe it’s just me, but I find it extremely hard to match what I can offer with the formats people are ready to receive. I know the skills I have. I know the problems I can solve. But translating that into something that lands? That’s the tricky part.

Trying to identify a “painful and expensive problem” brought me to an unexpected realization:
If I want to find the problems that matter to my audience, I first need to understand their writing.

Because writing always reveals something deeper. 
Let me give you an example.
I discovered that I often write about community building because I believe community is the solution to many of my own challenges. And even though I have a community and years of experience building them, my writing shows something subtle: there is still a gap, something unresolved…
And that made me wonder:
If my writing reveals my hidden challenges, what is my audience’s writing revealing about theirs?
So the question became:
Can AI help me read between the lines?
After more than a week of experimentation, I can confidently say: yes, it can.
I used n8n, ChatGPT, and Google Sheets.
What I’m about to share is not a step-by-step tutorial on how to build the automation.
It’s the process that is helping me analyze what my potential customers actually need — in a way I had never seen before.
And here is the surprising part:
Even in the early data, I started seeing patterns I had never considered before.

[Read the full article on Substack](https://automato.substack.com/p/understanding-your-substack-audience)

### Is AI More Than a Tool?

2025-11-22 · AI, Automation, Work · Full article: https://automato.substack.com/p/is-ai-more-than-a-tool

*What 17 Early Adopters Reveal About the Future of Work*

I’ve always believed we learn faster from real examples — especially when we can peek over the shoulders of people already playing at the edges of the possible.
So today, I’m bringing you 17 AI Power Users who graciously responded my questions. Their answers are honest and straight from where things are actually happening.
And as a bonus: at the end of this article, you’ll find a list of the articles that inspired them. What a treasure.

The illustration is not representing any of the real 17 Power Users. Not even Chris.
Subscribe now

Thank you to our 17 protagonists! Here they are, in order of arrival 😊
, , Cashandcache, , , , , , ,, , , , , , , .

Just earlier today, I read a great post by , where she explains that what we call “work” today will soon become a form of art. I really love it! 
And it gives the perfect context for what you are about to read.
The whole purpose of this post is to show how AI is transforming the way we work — and at the same time highlight the growing importance of elevating what only humans can do.

[Read the full article on Substack](https://automato.substack.com/p/is-ai-more-than-a-tool)

### Q&A with 9 AI Power Users

2025-11-10 · AI, Money, Automation, Learning · Full article: https://automato.substack.com/p/q-and-a-with-9-ai-power-users-8ec

*Part 2 of 2*

What you’re about to read is likely something you already sense, though it’s not easy to put into words.
As I see it, it’s a call for individuality and for collaboration.
The opportunities ahead for freelancers, micro businesses, and small collectives are immense and already within reach. There are risks, and some of them are already considered in the following paragraphs.
So, fasten your seatbelt and enjoy the ride!

The only character that represents one of the nine Power Users is the one in front: Chris Tottman

If you haven’t…
Let me reintroduce you to the 9 AI Power Users
, , , , , , , , 
If you haven’t read part 1/2 of this series, here it is:

How do you see AI and other smart tools shaping the competitiveness of small teams and businesses?
I’ll let you with the quotes directly:

“…HUGE competition now. Really need to stand out. There is really no more Unique Value Proposition, but we need to have a Competitive Value Proposition. The best defense is to build a STRONG personal brand moat around yourself. Bring humanness into your business.” —

“… Now the norm is small teams achieving milestones that were possible before only for large companies and corporations… it’s going to level the playing field. The advantage won’t be more output in less time, it would be better usage of what’s available and better discernment of what to do, when, and most importantly, why. —

[Read the full article on Substack](https://automato.substack.com/p/q-and-a-with-9-ai-power-users-8ec)

### Q&A with 9 AI Power Users

2025-11-07 · AI, Automation, Learning · Full article: https://automato.substack.com/p/q-and-a-with-9-ai-power-users

*Part 1 of 2*

It feels like we’ve reached the first early stage of maturity in the AI world. The power users and early adopters have invested enough time and effort to understand today’s tools, and they’re learning how to deal with the limitations they find.
One idea that stood out to me again and again is this: AI doesn’t replace our humanity — it amplifies it.

This image is not representative of our 9 Power Users.
To work well with these tools, we’re forced to become clearer about what we want, how we think, and what matters to us. The better we know our perspective, the more powerful the result. It is a win-win situation.
Subscribe now

Let me introduce you to Automato’s new friends.

, writes the newsletters Elite Leaders and The Investor’s Newsletter. Dennis has an amazing story, and he invites you to read this specific post.

, is a dynamic business engineer and a data analyst. She writes Lights on by Farida and invites you to read this mind-bending post.

, is a lifelong learner who is transforming his passion into his publication, Super Charged Learning HQ. He invites you to read how to learn using AI.

helps startups grow through marketing. He writes Marketing in Progress and invites you to read how to increase your revenue.

[Read the full article on Substack](https://automato.substack.com/p/q-and-a-with-9-ai-power-users)

### I Built a Custom GPT That Makes My Workflow Diagrams

2025-10-28 · AI, Automation, Work, Building, Consulting · Full article: https://automato.substack.com/p/i-built-a-custom-gpt-that-makes-my

*And why that makes perfect sense for businesses adopting AI*

Before I show you the videos and the custom GPT I just built, I want to share the real story behind why I needed to create a tool for building diagrams my way :)

Watch the videos, they are at the bottom of this post

A few years ago, I was consulting for a company with over 80 employees across sales, design, engineering, and production. Each team knew its own processes—but none of them were documented. Everyone had their own way of working, and somehow, things worked out… inefficiently.
The company was on the edge of burnout.
Legendary bottlenecks, a lack of supporting tools, and massive Excel files filled with mysterious formulas were invisibly running the show.
I needed a way to visualize their operations—to document their processes, understand how departments interconnected, spot inefficiencies, and use that insight to kick off a proper digitalization journey.
The project turned out to be a success.
And one of the key reasons was that we standardized how processes were documented.

Important note: Using AI in business without properly documented processes and workflows will result in a massive loss of time, clarity, and resources. Documentation is not bureaucracy—it’s the foundation that allows AI (and humans) to work together effectively. 
That’s why I believe this post is important.
Following:

[Read the full article on Substack](https://automato.substack.com/p/i-built-a-custom-gpt-that-makes-my)

### AI Doesn’t Think Like You

2025-10-24 · AI, Learning, Automation · Full article: https://automato.substack.com/p/ai-doesnt-think-like-you

*Let’s get it right this time.*

I detest that YouTube ad saying something like:

“Stop using ChatGPT like a newbie, people over 40…”
But the truth is, we do need to upgrade the way we use AI if we want better results.

New to Automato? Join us:

I’ve been talking with many entrepreneurs lately, and we all share the same issue. Maybe you do too. We get frustrated when AI doesn’t deliver what we envision, even when our request seems straightforward.
The root of the problem is our misunderstanding of what an LLM really is.
And the consequence? When we expect better results, the tools simply don’t perform as we imagine.
Sounds familiar?

We read the articles, we watch the videos, and we start believing that Agents can do magical things. We buy into the examples we see online, but something essential is missing.
I think the problem lies in how we humans think. Stay with me, it’s not what you might expect.

We ask our favorite LLM to perform a task as we imagine it should be done.
Look at this example:

Me: “Please extract my list of articles, URLs, and titles from this link. Organize the results in a spreadsheet with two columns: Title and URL.”
ChatGPT tries… and fails.
So I try again.
I figured out that my list of articles is also available as an RSS feed, so I changed the link in the prompt.
Still no luck.
Then I copy the content of the RSS XML file and paste it directly into ChatGPT. Ten seconds later, I get the full list perfectly formatted and ready as a CSV.
Eureka.

[Read the full article on Substack](https://automato.substack.com/p/ai-doesnt-think-like-you)

### You Won’t Believe How Easy This AI Tool Is

2025-10-15 · AI, Work, Automation · Full article: https://automato.substack.com/p/you-wont-believe-how-easy-this-ai

*Why You Need to Include NotebookLM in Your Workflow 🤯*

A couple of days ago, my mind was blown by a demo of NotebookLM.
 and were showing a group of us how they use AI tools in their daily work.
I had never tried NotebookLM before, but after that session, it became immediately clear: this is a must-use tool.
It’s simple, incredibly powerful, and free. In this post, I’ll show you step by step how to get started. 
At the end, you will find two amazing things: check for the audio control and listen… You will not believe it. And I’m sharing two very helpful articles from our Substack community.

Inspired by Jenny’s style of images :)
Subscribe now

What is NotebookLM good for?
Think of it as a focused version of ChatGPT with built-in additional tools.
Instead of working in loose chats, NotebookLM works with Notebooks.
Each notebook contains sources, your documents, links, videos, or research notes. The AI reads those sources and uses them as context for your requests: summarizing, analyzing, comparing, or answering questions.
In other words, your notebooks become thematic containers powered by an AI that learns only from what you feed it.
Yes, ChatGPT lets you create Custom GPTs, but you have to train them before they perform well. NotebookLM skips that step; the “training” happens automatically as soon as you upload your materials.

[Read the full article on Substack](https://automato.substack.com/p/you-wont-believe-how-easy-this-ai)

### Coexisting Intelligences — with Jenny Ouyang

2025-10-10 · AI, Fear, Building, Cooperation · Full article: https://automato.substack.com/p/coexisting-intelligences-with-jenny

*The unexpected side effects for humans that use AI*

Welcome to Automato’s special collaboration with Jenny Ouyang!
As many of you already know, Jenny is the creative force behind , a publication that helps people like you and me start building real solutions with AI. She’s not only a talented builder and creator, but also one of the kindest, most generous, and open-minded voices in the AI community here on Substack.

Jose: I’m definitely looking younger here :)
In this piece, we explore some of the deeper dimensions of the human–AI experience, how working with large language models is reshaping the way we think, create, and, perhaps most surprisingly, how these new human–AI interactions are redefining what it means to be human.
This collaboration was inspired by one of Jenny’s Notes that struck me deeply — a reflection on how AI reveals so much about ourselves. You can read it here:

Jose:
If you’ve read Jenny’s Note above, you might conclude that AI can teach us to be more kind.
That idea resonated deeply with me. I’ve long believed that we are raised to act out of fear, and that fear often distorts our perception of reality. In other words, we spend much of our lives trying to protect ourselves and our interests — while AI, in contrast, acts without fear, lack, or emotion.
Our interactions with AI mirror both our fears and our aspirations, revealing not only how we think, but also what we value most.

[Read the full article on Substack](https://automato.substack.com/p/coexisting-intelligences-with-jenny)

### Can Notion Really Run Your Business?

2025-10-03 · Automation, Consulting, Work, Knowledge-Management · Full article: https://automato.substack.com/p/can-notion-really-run-your-business

*Interview with Vito Meznaric, a Notion Expert*

Have you used Notion? If not, you’ve probably heard about it. But here’s the real question: can a tool that looks so simple actually power complex workflows—or even run a whole business?

To explore that, I turned to my friend Vito. He has a rare gift for turning complexity into efficiency, and this interview shows exactly how he does it.
Let me know if you decide to give Notion a try!

A Conversation with Vito Meznaric, a Notion expert user
Hi Vito, tell us a bit about you, your work, and your story with Notion.
Hey Jose, I’m a Notion power user and have been using it for years. I’ve built my own products on top of Notion and used it in a professional context in at least 10 projects. Sometimes we used it as a knowledge base, but most often it was a knowledge base plus a ticketing system

Vito Meznaric
.For every project I start, I usually begin with a simple Notion page and then build the systems out based on the project and team requirements.

Why is Notion an option for workflow automation?
Vito: I think the main reason is how flexible it is. Do you want a basic Kanban board? Or a really advanced one? Or something completely different, let’s say a client management system for filmmakers? It has you covered.
Beyond that, it allows you to do some basic automations inside Notion itself, and it also exposes an API so you can create much more powerful integrations. Although I would say the API does require a developer to work with (or maybe some people can vibe-code integrations with AI?).

[Read the full article on Substack](https://automato.substack.com/p/can-notion-really-run-your-business)

### Building a Directory App with Softr (No Code, No Fuss)

2025-09-27 · Automation, Building, Consulting, Learning, Work · Full article: https://automato.substack.com/p/building-a-directory-app-with-softr

No-code tools like Softr make it possible to turn an idea into a working app in hours, not weeks. Here’s how I built mine:

Sample App Image from Softr Page
Something I often forget to talk about is the Low-code and No-code tools. There’s so much available today to avoid coding at all: not just traditional programming, but even vibe coding.
I’m using Softr(*) to build a very simple, but very useful tool. Let me tell you more about it.
If you have no idea about building software tools, but you want to upskill or you’re just curious, keep reading. I’ll do my best to offer you an easily digestible article for non-IT people to get you started.

From Process to App
To build any piece of software, you first need clarity about what you want to achieve. Then you need to understand if there’s a process involved.

For example, if you want Excel to give you information about paid and unpaid invoices per customer, you know you need:

Customer Data

Invoices

Status of each invoice
Excel (or any other spreadsheet) will do the calculations and give you the report you expect.
Similarly, an app needs to gather the right information to produce the results you expect.
If you are interested in Flow Diagrams to document your processes:

[Read the full article on Substack](https://automato.substack.com/p/building-a-directory-app-with-softr)

### n8n: What You Must Know First

2025-09-23 · Automation, Building, Flow, Work · Full article: https://automato.substack.com/p/n8n-what-you-must-know-first

*Workflow Automation Framework — Worth Its “Length” in Gold 🏆*

Do you know the platform n8n?
Well, Suman Suhag () knows it inside out.
I asked her if starting with Zapier makes sense before moving to n8n. Her answer was a blueprint. I’ll be visiting this Post many times!

Screenshot from n8n sample - it seems complex, but it is easier than you think

Mastering n8n Architecture - The Foundation of Automation Excellence

A Fortune 500 company hired consultants for 6 months to build its automation system. 
Cost: $250,000. 
Then their intern rebuilt it better in n8n in 3 days. 
The difference? Understanding the core concepts that I'm about to share. This knowledge will save you months of trial and error! — Suman Suhag

Some notes before you continue: Suman’s Mental Model is designed to be read in sequence; it looks like a long piece, but you will see that her logic is impeccable and makes it very easy to read. If you have some IT background, this will make sense easily; if you are just starting, save it and use it as a reference when you decide to start experimenting, you will understand it fast once you start.

𝗧𝗵𝗲 𝗻𝟴𝗻 𝗠𝗲𝗻𝘁𝗮𝗹 𝗠𝗼𝗱𝗲𝗹 - 𝗧𝗵𝗶𝗻𝗸 𝗟𝗶𝗸𝗲 𝗮𝗻 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗶𝗼𝗻 𝗘𝘅𝗽𝗲𝗿𝘁 🎯
Imagine your business as a city:
• Workflows are highways connecting districts
• Nodes are buildings where work happens
• Data is traffic flowing between buildings
• Triggers are traffic lights starting the flow
• Credentials are security passes for buildings
• Executions are completed journeys
This mental model transforms complexity into clarity!

[Read the full article on Substack](https://automato.substack.com/p/n8n-what-you-must-know-first)

### Develop Your Engineering Mind

2025-09-17 · AI, Automation, Learning · Full article: https://automato.substack.com/p/develop-your-engineering-mind

*We all have one — nourish it, and stay relevant in the age of AI*

In my last post, I playfully suggested that “Vibe Coding is both sides of the Force,” hinting that skepticism and curiosity should mix if we want to get the best out of AI.
This time, I’d like to take a different angle: why it’s essential to develop your Engineering Mind.

Have you ever heard that “having a personal philosophy” is important for navigating life’s ups and downs? In the same way, when new technologies arrive, we need a point of view. One that considers what’s available today, a short-term vision, and a long-term vision.
But philosophy alone is not enough. Action and integration are essential.

Suggested Reading
📖 “Vibe coding has turned senior devs into ‘AI babysitters,’ but they say it’s worth it” (TechCrunch)
Senior developers experimenting with vibe coding discovered it doesn’t replace their work — it complicates it. But instead of resisting, they learned to integrate it. Vibe coding is fast and messy, yet it still makes their jobs better. The fear of “replacement” turned into practical curiosity.
📖 “Public Intelligence” (Kevin Kelly)
Kelly imagines a future AI commons: open, federated, and global — a “public utility of intelligence” shaped by everyone. He warns that focusing only on ROI and short-term gains is not enough; if we disengage, others will decide the trajectory of AI, just as happened with social media.
Together, these perspectives show us why we need to cultivate an Engineering Mind: curiosity to explore what works today, and vision to participate in shaping the future.

[Read the full article on Substack](https://automato.substack.com/p/develop-your-engineering-mind)

### Vibe Coding Is Both Sides of the Force

2025-09-09 · AI, Automation, Building · Full article: https://automato.substack.com/p/vibe-coding-is-both-sides-of-the

*Harness AI’s power while keeping your projects under control.*

As soon as a new technology or idea comes about, we see how new terminology and jargon appear. New job titles, new specializations, and honestly, a lot of b.s.
Everything becomes very overwhelming. But don’t be afraid! 
I’m about simplifying some of the new concepts so you feel at least well-informed, and hopefully ready to upskill.
Subscribe now

This article is about Vibe Coding, and fortunately, we will clear up some other new names that are relevant and that you’ve probably heard many times.
What is vibe coding?
Vibe coding is the practice of building software by describing your intent in natural language and letting AI generate the code. Instead of writing every line, you “set the vibe”—the AI drafts, and you refine. It’s faster, more accessible, and creative, but it still requires oversight, testing, and human judgment.

A quick story
One designer recently tried Claude Code to build a small automation. At first, the app failed until he learned to treat the AI tool like a junior teammate. He gave context, reviewed the drafts, and nudged it back on track. The result wasn’t perfect, but it worked. The lesson? The vibe is only as good as the guidance you give.

[Read the full article on Substack](https://automato.substack.com/p/vibe-coding-is-both-sides-of-the)

### Stop Drowning in Files, Start Building No-code Apps

2025-09-02 · Automation, Building, Time, Work · Full article: https://automato.substack.com/p/stop-drowning-in-files-start-building

*SharePoint + Power Automate might be your closest ally*

More than a million companies use it, paying for over four hundred million users globally. Microsoft SharePoint (let’s call it SP) is part of the suite of apps you get with a business subscription to Office 365, Microsoft’s equivalent to Google Workspace.

The reason I want to talk about SP is that it’s widely misunderstood, even though it’s incredibly powerful.
Most people see SP as just a place to store documents. But it’s much more than that. SP is actually a platform for building databases — or, as they’re called in SP, Lists.
Think of SP Lists as Excel spreadsheets that your whole team can interact with online. That alone solves a huge problem: instead of scattering business data across multiple files, you can store it centrally in a web-based SP List.

On our last Automato post, I talked about Files vs Data, and made the point that using applications that centralize business information is far more efficient. Many of you already use CRM software, accounting systems, or even e-commerce platforms for exactly this reason: they centralize your data and transform it into valuable insights.
SharePoint fits into the same logic. Instead of scattering data across endless Excel files, SP lets you build lightweight applications that centralize business information and connect it directly with your daily workflows.
Once you start using SP Lists, something interesting happens:

[Read the full article on Substack](https://automato.substack.com/p/stop-drowning-in-files-start-building)

### Files vs. Data: The First Step Toward Smarter Automation

2025-08-26 · Automation, Work, Consulting, Knowledge-Management · Full article: https://automato.substack.com/p/files-vs-data-the-first-step-toward

*A beginner-friendly guide to storing information for the AI era*

We often generalize the way we store information. We tend to think of it as placing papers in a folder, or digital documents in a computer folder. But if you want to start working with workflow automation tools, it helps to go one level deeper.
Let’s begin with a simple distinction: Files and Data.

Files: documents, photos, digital projects, spreadsheets, and other containers.

Data: structured information that can be organized, queried, and reused.

Of course, files also contain data—spreadsheets like Excel are a common example—but storing information in a file is very different from storing it in a database or an application. Understanding this difference is key.

The problem with digital files
Files can hold valuable information, such as customer names or invoice numbers, but that information is often locked away. You need to open the file to access it, and within an organization, this raises questions:

Which file has the latest version?

Where is it stored?

Who has access to it?

Even when the data inside the files is high quality, it’s difficult for software systems to use it efficiently. For example, generating reports across multiple files usually requires manual work, which is slow and error-prone.
Imagine this: The CEO requests a report with issued invoices, paid invoices, and a projection of the company’s cash flow. She also wants to compare those projections with the scheduled capacity of the production teams. If each team tracks information in different documents and software, the company ends up running around collecting files, trying to piece together a comprehensive report from scratch—leaving plenty of room for mistakes, wrong assumptions, and outdated numbers.

[Read the full article on Substack](https://automato.substack.com/p/files-vs-data-the-first-step-toward)

### Excel, Trello and Zapier

2025-08-12 · Automation, AI, Work · Full article: https://automato.substack.com/p/excel-trello-and-zapier

*Why the ideation process matters before automating*

First of all, welcome to Automato!
This is the very first post for this publication, and I hope you’ll join me as we explore what I believe is one of the best ways to upgrade your skills, add value to your work, and adapt to the changes AI and automation are bringing to how we work.
In this first learning project, I discovered something I now see as the most important step before automating anything:

The ideation process is everything.
Before you write a single line of logic or connect any tools, you need to understand the process itself and the outcome you want. The ideation stage is where you clarify what you want to automate, why you want to automate it, and how it should behave.
If you’re doing this alone, ChatGPT can be a surprisingly helpful brainstorming partner. If you can talk it through with another person, even better — you’ll catch details you might miss on your own.

The Scenario
Goal: Use an Excel Online file to update a Trello board.
Tools: Excel Online, Trello (free account), Zapier (paid account).
Setup:

Excel will have a table with these headers: Full name, Description, Profile photo link, City.

Trello will have three lists (columns) named after the three possible cities.

[Read the full article on Substack](https://automato.substack.com/p/excel-trello-and-zapier)