TL;DR;

You can build a personal AI newsletter with n8n that wakes up every Friday, pulls the latest AI news from 6 sources, lets an AI pick the 5 most interesting stories, and emails you a clean digest. Zero code. Zero manual effort.

It runs itself every week. I built it in one afternoon using an automation tool called n8n, and I'm going to walk you through every single step; including every mistake I made so you don't have to repeat them.

At the end of the article, I’ll show you 6 more things and share 9000+ workflow automation examples with you, so you can build anything you want with n8n.

Merhaba👋🏻

I am a Software Engineer with 10+ years of experience. My goal is to close the gap between the technical and the non-technical, making AI accessible to everyone, regardless of their background.

Subscribe now

It’s Sunday night. You’re thinking, “I should really keep up with what’s happening in AI.” So you open TechCrunch. Then Wired. Then The Guardian. Then you’re 14 tabs deep, half the articles are hype, the other half assume you have a PhD, and you still don’t know what actually matters this week.

I got tired of that loop. So I built something to fix it.

A simple automated workflow that collects AI news from trusted sources, asks an AI to pick the best stories and explain them in plain English, and sends the result to my inbox every Friday morning. No fluff, no jargon, no endless scrolling through tech sites.

Here’s exactly how I did it.

What You'll Build: A Self-Running AI Weekly Digest

Before we get into the steps, here’s the full picture. You’re building a workflow that:

1. Wakes up every Friday morning on its own

2. Pulls the latest AI news from 3 sources across the US and Europe (you can add as much source as you want)

3. Lets an AI pick the 5 most interesting stories and summarize them in plain English

4. Sends a clean email to your inbox with real links, real sources, zero manual effort

Once it’s set up, you never touch it again. It just runs.

Why n8n Is the Best No-Code Tool for This Workflow

This process called “workflow automation”, but it is actually a visual recipe builder for your apps.

Think of n8n like LEGO. You connect blocks together, each block does one small thing (fetch articles, merge them, ask an AI a question, send an email) and together they create something powerful.

You tell it: when THIS happens, do THAT.

Each block is called a node. A node can be almost anything: a website you already use (Gmail, Notion, Slack, Google Sheets), an AI model, a scheduler, or a simple rule like “only continue if the subject line contains the word urgent”. You drag them onto a canvas, draw a line between them, and you have just built a small automated brain.

Here is what makes n8n different from just writing yourself a reminder or a checklist: it runs without you. Once your workflow is active, n8n sits quietly in the background, waiting for a trigger and when that trigger fires, every step executes on its own. You do not have to be there. You do not have to remember. It just happens.

A few things n8n can do that might surprise you:

• Monitor the web for you. Set it to check a blog or news source every morning and only notify you when something matches your interests.

• Be your AI assistant’s hands. Ask an AI to summarize a document, then automatically drop that summary into a Notion page or send it to a colleague.

• Connect apps that were never meant to talk to each other. Your online store, your spreadsheet, your email, your calendar. n8n can make them share information in real time.

• Replace repetitive copy-paste work. If you ever find yourself moving the same information from one place to another, over and over, n8n can take that task off your plate permanently.

You do not need to write code. You do not need to understand how APIs work. You just need to be able to describe what you want in plain language, and then find the right nodes to make it happen.

👩🏻‍💻 If you want to get your hands dirty and go deep into coding, check out my 5-part No-BS Vibe Coding Series and create your own AI Agent with Python.

If you want to try this workflow automation today:

1. Go to n8n.io

2. Sign up for the free trial Cloud plan (You can upgrade later if you want)

3. No install, no terminal, no credit card

That’s it. You’re ready to build.

Subscribe now

Step 1: Connect Your AI News Sources via RSS Feeds

Everything starts with information. We need to tell n8n where to find AI news.

RSS is a quiet feature most websites already have. It’s a live feed of their latest articles that you can subscribe to. Most people don’t know it exists because it was designed for machines to read, not for humans.

💡 Quick note: When you paste an RSS link in your browser, you’ll probably get a weird popup or a broken-looking page full of code. That’s normal. RSS is machine-readable, not human-readable. n8n will be able to handle that.

Here are the 3 sources I started with. Add one RSS Read node per source:

• TechCrunch AI: https://techcrunch.com/category/artificial-intelligence/feed/

• Wired AI: https://www.wired.com/feed/tag/ai/latest/rss

• The Guardian AI: https://www.theguardian.com/technology/artificialintelligenceai/rss

Connect all 3 RSS nodes to your “Execute Workflow” trigger. We’ll handle the real scheduling later in Step 7.

Three sources gives you a solid spread across US and European coverage. You can add more later; the pattern is the same every time.

Step 2: Filter the Feed - Keep Only the Best 5 Per Source

RSS feeds can return 50+ articles at once. That’s way too much noise.

Add a Limit node after each RSS node and set it to 5 items. This gives you up to 15 articles total; a manageable number for the AI to work with.

You can change this number however you like. I found 5 per source to be the sweet spot; enough variety without overwhelming the AI or your inbox.

Step 3: Merge All Sources Into One List

Right now you have 3 separate streams of 5 articles each. We need to combine them into one single list.

Add one Merge node. Connect all 3 Limit nodes into it. Set the Mode to Append.

All 15 articles now flow into one list.

💡 The Merge node has numbered inputs (Input 1, Input 2...). You need to manually drag each Limit node’s output into a separate input. If you connect them all to the same input, you’ll lose data.

Step 4: Aggregate - The Step Most Tutorials Skip (And Shouldn't)

This is the step most tutorials skip, and it causes the biggest headache. I learned this the hard way.

Add an Aggregate node after the Merge node. Set it to “All Item Data (Into a Single List)”.

Here’s what’s actually happening: without this node, the AI processes each article individually, one at a time.

💡 If you skip this node (like I did in the beginning), you may end up getting multiple emails instead of one 🫠

The Aggregate node bundles all 15 articles into one batch so the AI sees everything at once. One batch in, one decision out.

Step 5: Let the AI Pick and Summarize the 5 Best Stories

Now the interesting part.

We’re going to ask an AI to read all 15 articles and pick the 5 most interesting ones, then write a clean summary for each.

Add a Basic LLM Chain node. Inside it, add a chat model. I picked Google Gemini, but you can use Anthropic or whatever model you prefer.

Double-click on the Basic LLM Chain node. In the Parameters section, set “Source for Prompt (User Section)” to “Define Below”.

We’re going to set two things: a User Prompt and a System Prompt.

User Prompt:

{{ JSON.stringify($json) }}

Please write this week's digest for Becoming with AI readers.

Format each stories like this:
📌 [Plain English headline]
[2-3 sentences: what happened + why it matters]
🔗 Source: "URL"

System Prompt:

You are the editorial assistant for "Becoming with AI" —
a weekly newsletter that makes AI accessible to non-technical people.
Readers are curious working professionals in Europe and the US.

Rules:
- Always pick exactly 5 stories
- Format each source link as HTML: <a href="URL">Publication</a>
- ONLY summarize articles explicitly provided. NEVER invent stories.

💡 I have built this system for Becoming with AI newsletter audience for demo purpose, you can tweak the prompts for your use case.

Step 6: Set Up Gmail to Send Your Digest Automatically

This part took me the longest. Not because it’s hard, but because email authentication has a few quirks depending on your setup.

If you’re on n8n Cloud, try the Gmail node first. It might just work with a direct OAuth connection. I am using self-hosted n8n and some features don’t work for me.

If it doesn’t work (like it didn’t for me), here’s the fix: Use Gmail with an App Password instead.

If you want to try this today:

1. Go to myaccount.google.com and find Security and sign-in

2. Make sure 2-Step Verification is enabled

3. Go to myaccount.google.com/apppasswords

4. Write an app name (I wrote “Mail”)

5. Click “Create” and you’ll get a 16-character password. Copy it.

6. Go back to n8n and double-click on the Send Email node

7. Fill in the credentials:

   • User: your-email@gmail.com

   • Password: the 16-character password from step 5

   • Host: smtp.gmail.com

   • Port: 587

   • SSL/TLS: off

8. Click Save

💡 Port matters: I first tried Port 465 with SSL/TLS on. It threw a timed-out error. Port 587 with SSL/TLS off worked immediately.

Now configure the email itself:

• Credentials: SMTP account

• Operation: Send

• From Email: your-email@gmail.com

• To Email: your-email@gmail.com

• Subject: Your Weekly AI Digest

• Email Format: Text

• Text: {{ $json.text }}

💡 Yes, From and To are the same email. You’re sending this digest to yourself. That’s the whole point.

💡 Optional: You can choose Email Format as HTML if you want a better-looking email. Otherwise, you’ll get plain text and links, which is also fine.

Step 7: Add a Schedule Trigger - Make It Run Every Friday

This is the last piece. We need to replace the manual trigger with a schedule so this thing runs on its own every Friday.

Search for Schedule Trigger and add this node to the very beginning of your workflow (replacing the Execute Workflow trigger). Configure it to run every week on Friday at 8:00 AM.

Click Execute Flow to test it once manually and make sure everything works end to end.

💡 This is the step that tripped me up: The schedule won’t run automatically unless you publish the workflow. Click the Publish button in the top right corner.

The Full n8n Workflow: What It Looks Like End to End

Here’s what you built, end to end:

1. Schedule Trigger fires every Friday at 8 AM

2. 3 RSS Read nodes pull the latest AI articles from TechCrunch, Wired, and The Guardian

3. 3 Limit nodes trim each source to 5 articles

4. 1 Merge node combines all 15 articles into one stream

5. 1 Aggregate node bundles them into a single batch

6. 1 Basic LLM Chain node asks AI to pick the 5 best and summarize them

7. 1 Send Email node delivers the digest to your inbox

Seven steps. No code. Runs itself every week.

Here is the actual result:

💡 You can make it look better by using HTML instead of plain text. I wanted to keep it simple for demo purposes.

Share this post with someone who is learning automation tools and n8n

Share

What Else Can You Build with n8n?

Building this took me one afternoon, but the real value wasn’t the automation. It was the feeling of not drowning in AI news anymore.

And the digest was just the beginning.

Once you understand the pattern; trigger → fetch → process → send, you start seeing automation opportunities everywhere. Here are a few real ideas, no technical background required:

A job alert that actually gets it. Most job boards are noisy. With n8n, you can connect to a job board’s RSS feed, run the results through an AI that filters by your actual criteria (not just keywords), and get only the roles that genuinely match, delivered to your inbox every morning.

A meeting prep assistant. Every Sunday night, n8n checks your Google Calendar for the week ahead, pulls in LinkedIn profiles or notes from your CRM for each person you’re meeting, and sends you a clean briefing doc. You show up prepared every time, automatically.

A content repurposing machine. You publish a newsletter. n8n picks it up, asks an AI to rewrite it as a LinkedIn post, a short tweet thread, and a plain-text email, then drops all three into a Google Doc for your review. One piece of writing, four formats, zero manual work.

A personal spending tracker. When an email receipt lands in your inbox, n8n reads it, pulls out the amount and category, and logs it to a Google Sheet. At the end of the month, it emails you a simple summary. No app subscription. No manual entry.

A “what should I read this week?” curator. You give n8n 5 Substack newsletters you love. Every Tuesday, it scrapes the latest issues, asks an AI to pick the 3 most relevant articles based on your current interests, and sends you a shortlist. Your reading list, curated by AI, delivered before your first coffee.

A client check-in system. When a new client signs a contract (via your form tool), n8n automatically sends a welcome email, creates a folder in Google Drive, adds them to your CRM, and sets a reminder to follow up in 7 days. All in under a second.

The pattern is always the same: pick a trigger, add a few nodes, tell the AI what you want, and send the result somewhere useful. You’re not writing code. You’re describing a process, and n8n does the rest. This is called “workflow automation”, and you can build anything from AI news digest to a personal assistant that works for free and never calls in sick.

💡 If you want to go deeper, the n8n community workflows library has over 9,000 real templates to browse. Search for anything; chances are, someone has already built a version of your idea.

Which part clicked for you? Or which part still feels fuzzy? Drop it below; your question might be the next article!

Leave a comment

PS: If you're new here and wondering why a software engineer is writing about all this - here's why I started Becoming with AI.

TL;DR;

The blank page is a creative energy killer, especially when you’re trying to maintain a specific voice. I built an AI writing workflow using Cowork that turns messy notes into structured first drafts by pulling from two living documents:

• voice.md (how I sound) and

• audience.md (who I’m talking to).

You can learn more about How to Use Claude Cowork to Build Your AI Digital Twin.

Welcome👋🏻

I am a Software Engineer with 10+ years of experience. My goal is to close the gap between the technical and the non-technical, making AI accessible to everyone, regardless of their background.

Subscribe now

Earlier today, I was looking at a single bullet point in my Notes app and a voice memo I recorded while walking in the park. In my head, the idea was great. On the screen, it was a mess.

The problem isn’t the idea. It’s the gap between a “messy thought” and a “polished draft”.

For my newsletter, Becoming with AI, my subscribers aren’t looking for technical jargon. They want clarity and a human connection. But after 10+ years as a software engineer, my brain defaults to tech speak. When I try to fix it, I overcorrect into “generic robot”. Neither is my actual voice.

The Real AI Writing Problem: It's Not Ideas, It's Translation

Let me be specific about what was actually happening. I never struggled with having something to say. The struggle was translating a messy idea into a draft that matched the tone I’d spent months developing.

Every time I sat down, I was doing two jobs at once:

1. Figuring out what to say (the content)

2. Figuring out how to say it (the voice)

Doing both simultaneously is exhausting. It’s like trying to build furniture and paint it at the same time. You end up with a sticky mess.

What I needed was a way to separate those two tasks. Get the “how to say it” part handled well enough that I could focus entirely on “what to say”.

My AI Writing Workflow System: voice.md + audience.md

Here’s what I built.

The core of it is a Claude Cowork workflow that pulls from two files I maintain and update regularly. These aren’t static instruction files you write once and forget about. They’re living documents that evolve as the newsletter grows.

• voice.md: A profile of my rhythm, vocabulary, and structural patterns. It includes real examples of what I actually wrote.

• audience.md: A profile of who I'm writing for. Their experience level, what they care about, what confuses them, the language they use, and what they're actually trying to accomplish when they read my stuff.

When I have an idea, even if it’s just a few scattered bullet points or a messy paragraph of thoughts, I drop it into the Cowork. Then Cowork pulls from both files and produces a structured draft that matches my “human-first” vibe.

That's it. The output isn't a finished article. It's a first draft that sounds like me instead of sounding like a chatbot wearing my hat.

Why Showing AI Real Examples Beats Any Style Guide

Most people try to “describe” their voice to AI:

“Write in a warm, conversational tone”.

The AI nods, then produces a generic post that sounds like every "Thought Leader" on your feed.

I've found that showing AI real examples works far better than any style guide you could write. So instead of instructions, I give it evidence. My voice.md file isn't a list of adjectives about my tone. It's full of actual patterns pulled from actual articles I've written. Specific sentence structures. Real examples of my rhythm. The exact words I reach for and the exact words I avoid.

The difference is night and day. When you tell an AI “be warm but direct”, you get generic warmth. When you show it fifteen examples of what your version of warm-but-direct looks like in practice, you get something that actually sounds like you sat down and wrote it.

Try out this today:

1. Open your 3-5 most recent pieces of writing (articles, emails, whatever you’re proud of).

2. Copy 5-10 sentences from each that really sound like you. The ones where you’d say “yeah, that’s my voice”.

3. Paste them into a new document and look for patterns. Do you use short sentences for emphasis? Do you reach for metaphors? Do you start with stories or with statements?

4. Write those patterns down as observations, not instructions. “I tend to follow a long explanation with a short punchy sentence” is better than “use short sentences sometimes.”

5. Save that document. That’s the beginning of your voice.md.

How to Build Your voice.md File (Step by Step)

Here's a starting point you can steal and adapt:

Sentence Rhythm: [Describe the pattern. Short then long? Long then short? Do you use fragments? Single sentence paragraphs?]

Vocabulary: [Words you actually use. Words you never use. Do you reach for metaphors or stay literal? Do you use jargon or translate everything?]

Structure: [How do you open articles? How do you close them? Do you use lists, subheadings, both?]

Tone: [Not adjectives. Examples. Paste 3-5 sentences that capture your exact tone.]

Things I Never Do: [This is actually the most useful section. Knowing what to avoid is more actionable than knowing what to aim for.]

Real Examples: [Paste 10-15 of your best sentences. The ones that really sound like you. This is the evidence the AI needs.]

The Things I Never Do section is where a lot of the magic happens. For me, that includes things like: “I don’t prefer to use em-dashes for dramatic effect, I never open with rhetorical questions, I never use words like ‘harness’ or ‘landscape’ or ‘delve’”, etc.

Constraints are more useful than aspirations when you're teaching a system to mimic your voice.

How to Build Your audience.md File

Your voice file tells the AI how you sound. Your audience file tells it who you’re talking to. Both matter.

Here is the starting point you can steal:

Who they are: [Job titles, experience level, what they know, what they don’t]

What they’re trying to do: [Not “learn about AI”. Be specific. “Figure out how to use AI at work to increase productivity.”]

What frustrates them: [What have they tried that didn’t work? What makes them feel lost?]

Language they use: [How do they describe their own problems?]

What they don’t need: [Technical depth? Hype? Knowing what to skip is as important as knowing what to include.]

For Becoming with AI, my audience is non-technical but intellectually curious. They don't need to understand how something works under the hood. They need to be able to do something useful in 20 minutes.

That single insight shapes every draft the workflow produces.

The Exact AI Writing Prompt I Use (Copy This)

Put your voice.md and audience.md file into a folder called, let’s say, “AI Cowriter”. Add your notes to notes.md file and put it into the same folder. We will let Claude Cowork do the rest for us.

Here’s the exact prompt structure I use when I drop my messy notes into the workflow:

I'm writing an article for my newsletter 'Becoming with AI'.
Read all files in this folder carefully before you start:
voice.md: how the writing should sound
audience.md: who my audience is
notes.md: my notes on a Substack article

Produce a structured first draft with:

- A TL;DR section at the top
- Clear subheadings for each major section
- Practical prompts, templates, or step-by-step guidance wherever I'm describing a process
- A closing section that connects the practical to the personal

This is a first draft, not a final piece. Prioritize getting the voice and structure right. I'll handle the sharpening.

That last line matters. It sets the expectation correctly; for me and for the AI.

This isn't about generating a finished article. It's about getting past the blank page with something that already feels like mine.

What This AI Workflow Actually Changed (Not What I Expected)

The impact has been huge for my creative energy, but probably not in the way you’d expect.

The “blank page” problem is mostly gone. That’s real. I’m no longer starting from zero, fighting with a blinking cursor for thirty minutes before I have anything usable. Instead, I sit down and I’m immediately in editor mode; sharpening, rearranging, adding the details only I can add. That’s a completely different kind of creative work. It’s energizing instead of draining.

But here’s the part that surprised me.

This is definitely not a “set it and forget it” system.

The quality of the draft depends entirely on how much effort I put into updating those two files. If I write a great article and don’t pull the best patterns from it back into voice.md, the next draft will be slightly less “me”. If my audience evolves and I don’t update audience.md, the framing starts to drift.

And that actually keeps me more connected to my own writing process. Not less. I’m constantly asking myself: “What worked about that piece? Why did that paragraph land? What would my readers actually need here?”

Those are exactly the questions a writer should be asking. The system forces the reflection.

The Human Element

I want to be honest about something. When I first started building this, there was a part of me that felt weird about it. Like I was outsourcing something that should be purely mine.

But here’s what I’ve come to understand: the AI isn’t writing for me. It’s giving me a running start. Every draft still needs my eyes, my judgment, my experience, my willingness to cut the stuff that sounds right but isn’t true. The messy notes are mine. The voice profile is built from my actual writing. The audience profile comes from real conversations with real readers.

The system doesn’t replace the human work. It moves where the human work happens. Instead of spending my energy on the mechanical translation from “messy idea” to “structured draft”, I spend it on the part that actually matters: making the piece honest, useful, and specific.

I’m still the one deciding what to say. The workflow just helps me say it faster in a way that already sounds like me.

And I’m still updating those files. Still refining. Still learning what my voice actually is by paying close enough attention to write it down. That’s the unexpected gift of the whole thing: building the system taught me more about my own writing than years of just doing it.

Which part clicked for you? Or which part still feels fuzzy? Drop it below; your question might be the next article!

Leave a comment

PS: If you're new here and wondering why a software engineer is writing about all this - here's why I started Becoming with AI."

TL;DR;

We all feel “AI fatigue” from time to time.

By March 2026, the average professional is paying for four or more AI subscriptions; most of which are quietly draining your bank account while doing exactly nothing for your workflow. The fix isn’t “better” tools. It’s building a Minimal AI Stack: the absolute fewest tools required to cover your entire lifecycle of your work, organized into three layers.

• Layer 1 - The Brain (Research)

• Layer 2 - The Studio (Creation)

• Layer 3 - The Hands (Action)

Welcome👋🏻

I am a Software Engineer with 10+ years of experience. My goal is to close the gap between the technical and the non-technical, making AI accessible to everyone, regardless of their background.

Subscribe now

If you feel like you are drowning in “productivity”, you aren’t alone.

I’ll be honest with you: I’ve been going through the same digital exhaustion myself lately. Every morning, I wake up to three new “game-changing” newsletters, four “must-have” browser extensions, and a nagging feeling that I’m falling behind. Creating this system, this Minimal Stack, was my way out of the noise. This article isn’t just a guide for you; it’s a necessary reminder for me.

By March 2026, the novelty of AI has worn off, replaced by a persistent, low-grade weight. Your browser probably has thirty tabs open; three different chatbots, a research tool you saw on a reel, two image generators, and a PDF summarizer you’ve used exactly once. You are likely paying for at least four AI subscriptions, most of which are quietly draining your bank account while doing exactly nothing for your actual workflow.

The irony of 2026 is that while AI was promised to save us time, we are spending more time than ever “managing” our tools. We’ve become operators of a digital factory rather than creators of work.

To find our way back, we have to stop collecting tools and start building a System.

Why AI Tool Fatigue Is Costing You Time (and Money)

Before we look at the apps, we have to talk about mindset.

Most people approach AI like a hobby, they “play” with it when a new version drops. To actually get work done, you must treat AI like a hire. If you hired a human assistant and they didn’t show up for work for two weeks, you’d fire them. You should do the same with your AI subscriptions. If a tool hasn’t moved a project toward the finish line in a week or two, it is clutter. It is taking up “mental shelf space”.

To build a minimalist stack, we are going to organize your digital life into three distinct layers:

1. The Brain: Where you find facts and organize your own information.

2. The Studio: Where you draft, design, and build the final product.

3. The Hands: Where you take action or automate the “boring stuff” so you don’t have to click.

Layer 1 - The Brain: How to Research Smarter with Perplexity and NotebookLM

Everything starts with information. But in 2026, the internet is a minefield of AI-generated noise and “slop”. You need a “Brain” that doesn’t just talk, but provides receipts.

The Explorer: Perplexity

Perplexity is the single greatest replacement for the Google Search. We used to search, click a link, realize it was SEO spam, go back, click another link, and repeat.

In 2026, Perplexity’s Deep Research does this for you. You ask a complex question; say, “What are the current tax implications for digital nomads in Portugal as of March 2026?”and the AI acts as an agent. It clicks through dozens of sources, reads the fine print, and compiles a cited report.

The Citations Rule: Why Unverifiable AI Is a Liability

In Perplexity, every claim has a footnote. Clicking that takes you directly to the original source. For a professional, this is non-negotiable. If an AI tells you a statistic but can’t show you the source, it might get you into trouble.

The Librarian: NotebookLM

While Perplexity explores the world, NotebookLM organizes your world. It is a private library where the only books on the shelf are the ones you put there.

The 2026 Use Case: You can now upload YouTube links, PDFs, and even voice memos. The Cinematic Video Overview feature can turn several pages of messy notes into a narrated video or a “Deep Dive” podcast where two AI hosts discuss your ideas. You can listen to your own research on your commute. It is the ultimate tool for “internalizing” information rather than just storing it.

Subscribe now

Layer 2 - The Studio: Draft Branded Work Faster with Claude Cowork and Gemini

Once you have your facts, you need to produce something. This is where most people get overwhelmed by prompting. In a minimal stack, we move away from chatting and toward Coworking.

Claude (Cowork & Skills)

As of early 2026, Claude Cowork is the gold standard for drafting. It isn’t just a chat bot; it’s a dedicated space on your computer where Claude acts as a “Desktop Colleague”.

Teaching Claude a Skill: Your AI Digital Twin

The biggest friction in AI is repeating yourself: “Use my brand colors”, “Keep it professional”, “Use my bio”. In 2026, you teach Claude these as a Skill. You upload your brand guidelines or past work once. From then on, you simply say, “Claude, use my ‘Consultant Skill’ to turn this research into a slide deck”. It handles the fonts, the tone, and the layout automatically.

Claude Code: For the non-technical person who has big ideas, Claude Code is the “Technical Teammate”. You don’t need to know how to code; you just describe the tool you want; like a custom calculator for your clients or a personal dashboard, and Claude builds for you.

The Efficiency Play: Gemini (Google Workspace)

If you live in Google Docs and Gmail, Gemini is your shortcut. It lives in your sidebar, summarizing 100 email threads and drafting responses that align with your actual calendar availability, no switching tabs required. It is the best tool for the “Logistical” side of creation.

Layer 3 - The Hands: Automate Repetitive Tasks with Claude and Zapier

The final layer is Automation. This is the “glue” that connects your Brain to your Studio so you stop being a “Copy Paste” person.

Claude in Chrome

Anthropic has a browser extension called Claude in Chrome that turns Claude from a chatbot that answers questions into an assistant that takes action in your browser. Claude works directly in a side panel while you browse, seeing what you see and taking actions when you ask.

Record a workflow

Think of it like showing a new hire exactly how you do something, once. You perform the steps, Claude watches, and from that point on it can repeat the whole thing without you lifting a finger. Click record, do your thing, stop, save it. That’s your shortcut.

This isn’t about automating complex systems. It’s about getting the ten minute tasks, the ones you do the same way every single time, off your plate for good.

Claude Cowork Scheduler

Cowork's scheduler is the closest thing to hiring an assistant who never forgets. You describe the task once; a weekly competitor roundup, a daily email briefing, a recurring report from your Google Drive and Claude runs it on whatever rhythm you set, delivering a finished output every time.

No reminders, no setup friction, no starting from scratch. But here's the caveat: scheduled tasks only run while your computer is awake and the Claude Desktop app is open. If either is off when the task is due, Cowork skips it and runs it once you're back.

The Connector (Zapier & n8n)

Claude is remarkable at thinking. It reasons, writes, summarizes, and executes tasks on your computer. But it doesn’t live inside your other apps. It can’t watch your inbox and react when something arrives. It doesn’t know when a new row lands in your spreadsheet, when a form gets submitted, or when a Slack message needs routing somewhere else. It just waits for you to show up and ask.

That’s the gap Zapier and n8n fill. They don’t think, but they watch, trigger, and connect. A new lead comes in, a file gets uploaded, a calendar event is created; these tools catch that moment and set the chain in motion, with or without you at the keyboard. At that point, you can bring Claude into the middle of the flow to do the reasoning work. But the trigger, the routing, the delivery to the right destination? That’s Zapier and n8n’s job.

Zapier is the easy to use; prebuilt connections, visual setup, no technical background required. n8n gives you more control and runs cheaper at scale, especially if you’re self-hosting. I haven’t used Zapier, I’ve been trying out n8n, but they are fundamentally doing the similar things: if you want automation that runs while you sleep, you need something that watches the world for you. Claude alone doesn’t do that.

Do you want to know more about the automation? Let me know in the comments!

Leave a comment

How to Stop Adding AI Tools and Start Getting Work Done

The most dangerous thing about AI in 2026 isn’t that it’s “smarter” than us; it’s that it’s faster. It can generate noise faster than your brain can process it. If you don’t build a system to filter that noise, your minimal stack will quickly become a maximal mess.

To stay minimalist, you need a “Tool Gatekeeper” System:

The “One-In, One-Out” Rule

Treat your AI stack like a crowded closet. If you want to add a new “cool” tool you saw on social media, you have to delete one you already have. This forces you to ask: “Is this new tool actually better than my current Studio, or am I just bored?”

The Friction Test

Before signing up for any tool, ask:

• Does it provide citations? (If not, it’s for play, not work).

• Can I teach it a “Skill”? (If not, I’ll spend too much time repeating myself).

• Does it have “Hands”? (Can it talk to Zapier or move my mouse? If it’s just a chat bot, it’s adding more copy-pasting to my life).

The “Output First” Routine

Never start your day by “playing” with AI. Start by identifying the Output you need (e.g., “A drafted report”). Then, and only then, pick the tool from your stack that handles that layer. AI should be a response to a problem, not a search for one.

Weekly Maintenance

Every Sunday, look at your browser tabs and your subscriptions. If you haven’t used a tool to finish a project in the last week or two, close the tab and cancel the subscription. The goal is to reach a state of Flow, and you can’t flow when you’re constantly toggling between ten different “assistants”.

Simplicity Is Your AI Superpower: Build Your Stack Today

The promise of AI in 2026 wasn’t to turn us all into “AI engineers”. It was to give us back our time. But you only get that time back if you are willing to say “no” to the noise.

The most productive people I know in 2026 aren’t the ones with the most apps. They are the ones who have mastered three tools. They have a Brain they can trust, a Studio that knows their voice, and Hands that handle the repetitive clicks.

I’m still working on this myself. I still get tempted by the shiny new “Agent” of the week. But every time I feel that fatigue creeping back in, I return to these three layers. This article is my reminder as much as it is yours.

Build your minimal stack today, set up your “Gatekeeper” system, and then, most importantly, use that extra time to go do something that doesn’t involve a screen.

Which part clicked for you? Or which part still feels fuzzy? Drop it below; your question might be the next article!

Leave a comment

PS: If you're new here and wondering why a software engineer is writing about all this - here's why I started Becoming with AI."

TL;DR;

Most people open Claude Chat, paste one document, get one answer, then repeat, manually, for every other file. That’s not a workflow. That’s copy-paste with extra steps.

Claude Cowork fixes this. It’s not a chatbot. It’s an AI coworker that reads your entire folder, writes in your voice, and delivers board-ready documents — while you grab a coffee. ☕ No coding required.

What’s inside this guide:

• Claude Cowork vs. Regular Chat: Why pointing AI at a folder changes everything — and why it’s the professional upgrade non-technical users have been waiting for.

• The Nina Case Study: How one Head of Ops turned 3 pages of messy meeting notes into a polished board presentation in minutes — without touching PowerPoint.

• Build Your AI Digital Twin: The voice.md and working-style.md system that makes Claude sound like you, not a generic assistant.

• The Master Prompt Formula: The exact briefing format that gets Claude Cowork to nail the task on the very first try.

• Pro Tips for Non-Techies: Why plain text files are your secret weapon — and how to set up your Skills folder for maximum speed.

• The Bottom Line: You don’t need to be a developer to automate your job. You just need the right context — and this guide gives it to you.

Already comfortable with Cowork? My vibe coding guide shows you how to go one level further: building real tools with AI.

Welcome👋🏻

I am a Software Engineer with 10+ years of experience. My goal is to close the gap between the technical and the non-technical, making AI accessible to everyone, regardless of their background.

Subscribe now

It's Monday morning, you have 3 pages of messy notes from last week's meetings, a presentation due by Thursday, and a to-do list that didn't shrink over the weekend. You open Gemini or regular Claude.

You paste one document.

You get one answer. Then you repeat, manually, for the next file.

However, this is just a copy paste with extra steps, not a workflow.

If you feel like you're working for your AI instead of the AI working for you, there is a new solution: Claude Cowork.

What Is Claude Cowork? (And How It Differs from Regular Claude Chat)

When Anthropic released Claude Code, the developer tool, they started to see that developers started to use it for everything: including to keep a plant alive, without human intervention.

Because of its potential, non-technical users also wanted to use Claude Code. The problem with that is terminal interface was intimidating for some.

Cowork is the answer to that problem. It takes that high-level “coding power” and puts it into a clean, friendly interface (Claude Desktop app) that anyone can use.

The Game-Changer: How Claude Cowork Reads Your Entire Folder

The biggest difference between regular Chat and Cowork is access.

In a regular chat, Claude can only see what you upload to that specific window. With Cowork, you point it at a folder on your computer. This is the game-changer. Once you give Claude permission to look at a folder, it can:

1. Read every file in that folder at once.

2. Edit those files.

3. Create brand new files (like spreadsheets or outlines) directly onto your hard drive.

4. Delete

Claude Cowork Setup: Plans, Devices, and What You Actually Need

• Cowork is available for Pro ($20/month), Max, Team, and Enterprise plan subscribers using the Claude Desktop app on macOS or Windows.

• Open Claude Desktop, look for the mode selector that includes “Chat” and the Cowork tab, and click “Cowork” to switch to Tasks mode.

• You point it at a folder on your computer. That's the key step. Claude can then read, edit, or create files in that folder.

Pro Tip:

The Claude Desktop app must remain open while it’s working.

Real-World Example: Automating a Board Presentation with Claude Cowork

To see how this works in real life, let’s look at FakeCo Coffee Company.

The Player: Nina, Head of Operations.

The Challenge: Nina just finished a marathon meeting with Product Managers about the Quarterly Roadmap. She has a folder full of messy transcripts and rough notes. She needs to turn these into a polished Board Presentation by April 3rd.

Instead of spending five hours summarizing and typing, Nina uses Cowork.

Step 1: The Setup

Nina puts all her meeting notes and data.csv into a dedicated folder called FakeCo Coffee.

Step 2: The Command

She opens Claude Desktop, switches the mode to Cowork, and points it to that folder. She gives one simple prompt:

Read the meeting notes in this folder. Create a PowerPoint presentation for the board 
meeting on April 3rd. Cover what we achieved last quarter, what went wrong, 
what we're focusing on next quarter, and key risks. 10 slides max. 
Professional but warm tone - this is a coffee company, not a bank.

Step 3: The Execution

Nina watches as Claude “thinks”. She can follow the progress while Claude Cowork does its job.

Step 4: The Result

In minutes, Nina has a structured outline and a summary of the data saved directly to her computer. She didn't copy and paste a single word.

Congratulations to Nina, she made her presentation in a couple minutes instead of spending hours!

However, there is a small catch.

Because Nina gave Claude a broad instruction, the AI had to fill in the blanks. It “guessed” the tone, the structure, and the formatting. While the content is accurate, the presentation might feel a bit generic. It doesn’t yet sound like Nina, and it certainly doesn’t look like FakeCo.

Build Your AI Digital Twin: The voice.md and working-style.md System

This is where we move from “cool AI trick” to “professional-grade workflow”.

By default, Claude Cowork is a bit of a guesser. If you don’t give it specific instructions, it will pick generic colors, standard fonts, and a “helpful assistant” tone that might not sound like you at all.

To get a board-ready result, you need to provide the Guardrails and the DNA.

The Two Ingredients for a Perfect Draft

To turn a generic outline into a masterpiece, Nina adds two types of files to her FakeCo Coffee folder:

1. The Corporate Guardrails (Brand Guidelines)

Most companies have a “Brand Guidelines”. It’s the PDF that tells you which hex codes (colors) to use, which fonts are allowed, and how the company logo should be placed. It ensures that whether a document is created in London or Los Angeles, it always looks like FakeCo.

2. The Digital DNA (Personal Identity Files)

This is the secret sauce that makes the presentation sound like Nina, not a robot. Nina keeps three small text files in her folder to act as a manual for her AI:

• about-me.md: Her role, expertise, and the specific perspective she brings to the team.

• voice.md: Her linguistic style (e.g., “I prefer data over fluff,” “Use short, punchy sentences,” or “Never use the word ‘synergy’”).

• working-style.md: How she structures her thoughts (e.g., “I always start with the biggest challenge first”).

This setup will help you to onboard Claude Cowork so that it can do exactly what you said.

about-me.md

By creating this simple text file, Nina has essentially given Claude a blueprint of who she is.

# About Me

## Who I Am
My name is Nina Hartman. I am the Head of Operations at FakeCo Coffee,
a Dutch coffee shop chain with 34 locations across the Netherlands.
I have been with the company for 6 years.

## What I Do
I run the quarterly planning process and own the relationship with the
leadership board. My job is to turn what the product team knows into
something the board can act on. I sit between the people doing the work
and the people making the big decisions.

## My Audience
The people I write for are busy executives. They do not want to read long
documents. They want to know: what happened, what are we doing about it,
and what do they need to decide. If I give them a wall of text, I have
already failed.

## What Good Work Looks Like for Me
- A document that gets to the point in the first paragraph
- Clear headings so people can scan before they read
- Numbers where possible — not "sales improved" but "sales up 18%"
- Action items that say who does what by when
- An executive summary at the top of anything longer than one page

voice.md

In a standard chat, Claude is a generalist. It tries to please everyone, which often results in that "too-polite AI" tone. By adding a voice.md file to her folder, Nina does something radical: she gives the AI a personality filter.

# My Voice & Communication Style

## The Feeling I Want
Warm but professional. We are a coffee company — we have personality.
But I am writing for a board, so it still needs to feel serious and
trustworthy. Think: a confident manager giving a clear update, not a
consultant writing a report.

## Tone
- Direct. Say the thing. Do not bury it.
- Human. Write like a real person, not a press release.
- Honest. If something went wrong, say so clearly and say what we are
  doing about it. Do not hide bad news behind vague language.
- Confident but not arrogant. We know what we are doing, but we are
  also learning as we grow.

## Language Rules
- Short sentences. If a sentence has more than 20 words, split it.
- No jargon. If I would not say it out loud in a meeting, do not write it.
- No filler phrases. Avoid: "It is important to note that...",
  "As previously mentioned...", "In conclusion..."
- Active voice. "We launched the app" not "The app was launched."
- Numbers over vague claims. "31% fewer drop-offs" not "significantly fewer."

## Words I Like
clear, honest, simple, on track, real, practical, next step, decision

## Words to Avoid
synergy, leverage, holistic, deep dive, circle back, bandwidth,
move the needle, at the end of the day, going forward

## Format Preferences
- Start with the most important thing, not background context
- Use bullet points for lists of 3 or more items
- Bold the key word or number in each bullet, not the whole sentence
- Tables for comparisons and status updates
- One idea per paragraph

Most people spend 30 minutes editing an AI response to make it sound like them. Nina spends 30 seconds updating her voice.md file once, and every document Claude creates from that point forward arrives already sounding like her.

working-style.md

If voice.md gives Claude a personality, working-style.md gives it a workflow.

Look closely at Nina’s rules. She isn’t just asking for a summary; she is setting professional boundaries that prevent the “AI hallucinations” and “over-explaining” that drive most users crazy.

# How I Like to Work With Claude

## Before You Start Any Task
1. Read about-me.md and voice.md first, every time.
2. Ask me 2 to 3 clarifying questions if anything about the task is unclear.
   Do not guess and produce something wrong. It wastes both our time.
3. Show me your plan in plain language before you start writing or creating files.
   I want to approve the approach, not just the output.

## While You Work
- Save your output directly into the "outputs" subfolder in this project folder.
- Name files clearly: use the format YYYY-MM-DD-description
  (example: 2026-03-14-board-presentation.pptx)
- If you are unsure about something mid-task, stop and ask. Do not fill gaps
  with invented content.
- Never delete any of my files. Only create new ones or edit files I
  specifically ask you to edit.

## Output Format Defaults
- Presentations: PowerPoint (.pptx), maximum 12 slides unless I say otherwise
- Documents: Word (.docx) with an executive summary at the top
- Summaries and notes: Markdown (.md) saved in the outputs folder
- Spreadsheets: Excel (.xlsx) with clear column headers and totals

## How I Like to Review
When you finish, give me a short summary (3 to 5 sentences) of what you made,
what decisions you made along the way, and if there is anything you are
unsure about. Do not just say "Done." Tell me what I am looking at.

## What I Do Not Want
- Long explanations of what you are about to do — just do it
- Apologies or disclaimers at the start of every response
- Generic filler content — if you do not have the information, ask me for it
- More than one version of the same thing unless I ask for options

Setting up a working-style.md file is the difference between a “Chatbot” and an Agent. You are training Claude to work the way you work. If you like to see a plan before the writing starts, put it in the file. If you hate Excel but love Markdown, put it in the file.

By combining these three identity files; About Me, Voice, and Working Style, Nina has created a digital twin that doesn't just “help” with the work; it executes the work exactly the way she would.

Do you want to know more about how to create your own Digital Twin? Let me know in the comments!

Leave a comment

Pro Tip:

You only have to write these files once. You can then copy them into every new project folder you create. It’s like bringing your best assistant with you to everyday.

Claude Skills: How to Give Your AI Institutional Memory

If the .md files we discussed earlier are Nina’s “Digital DNA”', Claude Skills are her Professional Toolkit.

A “Skill” is the difference between telling a new employee, “Make a presentation,” and giving them the company brand book, the official slide template, and three examples of board decks the CEO actually liked. It’s the same person, but the output is on a completely different level.

The FakeCo “Brand Skill”

To ensure her work is never generic, Nina adds the FakeCo Brand Skill to her folder. This isn’t just a list of colors; it’s a comprehensive guide that tells Claude exactly how to behave as a representative of the company.

The FakeCo Brand Skill includes:

• Visual Identity: The exact Hex codes (like Espresso Brown and Oat Cream) so every chart and slide background matches the brand.

• The “One-Sentence” Mission: “FakeCo is the coffee company that takes quality seriously without taking itself too seriously”. This gives Claude a “North Star” for the tone of every sentence.

• Structural Rules: Hard constraints like “Always lead with the conclusion” and “Never write a paragraph longer than four sentences in a board document”.

Why “Skills” Change the Game

When you use a Skill in Cowork, you are effectively giving Claude Institutional Memory.

Instead of Nina having to remind the AI to use “Leaf Green” for positive numbers every single time she starts a new chat, she simply points it at the Brand Skill. Claude now “knows” FakeCo. It understands that “Warm White” is for backgrounds and “Charcoal” is for body text.

Do you want to know more about Claude Skills? Let me know!

Leave a comment

Summary: The Nina + FakeCo Formula

Nina has now built a perfect environment for high-level work. By combining her Personal Identity Files with the FakeCo Brand Skill, she ensures her work is:

1. Personal: It sounds like her voice.

2. Professional: It follows her working style.

3. On-Brand: It looks and feels like FakeCo Coffee Company.

Pro-Tip: Choosing the Right File Format

You don’t have to use .md (Markdown) files, Claude can read PDFs and Word docs just fine. However, there is a “secret” advantage to using Markdown for your instructions:

• For Context & Skills (voice.md, about-me.md, etc): Use .md or .txt. These are “plain text,” which means Claude can read them instantly and perfectly without having to “extract” text from a complex layout. Think of it as giving Claude a clean, typed note instead of a photocopied page.

• For Source Material (Meeting notes, PDFs, data): Use whatever you have. If your notes are in a .docx or your data is in a .pdf, just drop them in. Cowork is built to handle the heavy lifting of processing those files for you.

The Master Prompt Formula for Claude Cowork

With her “Context Files” in place and her data ready, Nina is ready for the finish line. She doesn't just ask Claude to “write a deck”. She gives a Master Command that points to everything she has prepared:

Read all files in this folder carefully before you start:

- about-me.md — who I am and who my audience is
- voice.md — how the writing should sound
- working-style.md — how I want you to work
- fakeco-brand-skill.md — how FakeCo documents look and feel
- meeting-notes-fakeco.md — the source content
- fakeco-data.csv — the numbers behind the story

Once you have read everything, ask me 2-3 clarifying questions before you start.

Then create a PowerPoint presentation (.pptx) for the FakeCo board meeting on 
April 3rd, 2026.

The presentation should:

* Be 10 to 12 slides maximum
* Follow the slide order in the brand skill exactly
* Use FakeCo colors, fonts, and formatting from the brand skill
* Tell a clear story: here is what we achieved, here is what went wrong and why, here is 
what we are betting on next quarter, here is what we need from you today
* Include at least 3 charts or visual data callouts from the CSV — focus on revenue trend,
location growth, and staff costs
* Flag any missing information with [CONFIRM WITH NINA] rather than inventing it

Save the finished file to the outputs folder as: 2026-03-10-board-presentation-v1.pptx

When done, give me a 3-sentence summary of what you built and flag anything you were 
unsure about.

The Moment of Truth: Claude Becomes a Consultant

This is the part that usually shocks new users. In standard AI, you hit “Enter” and it starts talking. In Cowork, Claude stops to think.

Because Nina’s working-style.md told it to “Ask 2-3 clarifying questions,” Claude doesn’t just guess. It scans her notes, notices a drop in the revenue, and asks: "Nina, how do you want to frame this revenue drop from previous quarter?"

This is the shift from “Tool” to “Teammate”. By clarifying first, Claude ensures that the final presentation isn't just fast, it’s correct.

The Result: A Board-Ready Deck in Minutes

As Nina watches, Claude doesn’t just generate text, it builds. Looking at the final output, you can see the FakeCo Brand Skill in action. The slides aren’t just some generic backgrounds; they use the “Espresso Brown” headers, the “Oat Cream” accents, and clear, data-driven charts that reflect the CSV data Nina provided.

She didn’t spend her morning struggling with PowerPoint’s “Design Ideas” tool. She spent it as a Director, and Claude acted as her .

How to Brief Claude Cowork Like a Pro (Not Just Prompt It)

If you want these results, you have to move past “talking” to the AI and start “briefing” it. Think of Cowork like a highly talented intern: they are brilliant, but they can’t read your mind.

Use this simple formula for every task:

[What you have] + [What you want] + [How to format it] + [Constraints]

The Contrast:

• ❌ The Bad Prompt: “Make a presentation.”

  • Result: Claude will guess your colors, guess your audience, and guess your data. You’ll spend more time fixing it than if you’d done it yourself.

• ✅ The Good Prompt: “Turn these meeting notes into a 10-slide PowerPoint for a leadership update. Use our brand colors. Include key decisions, next steps, and exactly one slide per department.”

  • Result: You get a professional, structured document that requires minimal tweaking.

From Chatting to Building: What Claude Cowork Actually Changes

The true power of Claude Cowork isn’t that it can write; it’s that it can execute. By moving your work into folders and providing a bit of “Digital DNA” (your voice and style), you stop the endless cycle of copy-pasting.

Tomorrow morning, don’t start with a blank chat window. Start with a folder, a few .md files, and a clear goal.

Let Cowork handle the how so you can focus on the why.

Which part clicked for you? Or which part still feels fuzzy? Drop it below; your question might be the next article!

Leave a comment

PS: If you're new here and wondering why a software engineer is writing about all this - here's why I started Becoming with AI."