Really useful piece. What stands out is not just Claude Code itself, but the bigger shift behind it. Coding is slowly becoming more accessible to people who can think clearly, give direction, and test well, even if they do not write syntax.
Exactly. Once the model layer becomes easier for everyone to access, the real difference shifts to product judgment. Not just what the tool can do, but what problem it solves, how smoothly it fits into work, and whether people actually keep using it.
Greaaaat article. I've been using Claude Code on a Raspberry Pi for a few months. This article does a much, much better job than I ever could in describing setup, benefits, tweaks, annoyances. Love your stuff!
Good piece — Ruben writes well for a non-technical audience and has clearly put thought into accessibility. A few honest takes:
What’s genuinely useful here:
The CLAUDE.md memory trick is solid and underused by beginners. The “screenshot the bug” workflow is practical. The “describe the outcome, not the steps” prompting advice is correct and worth repeating. These are real habits that save time.
Where it gets a bit sloppy:
He conflates Claude Code (the terminal-based agentic coding tool) with the Claude desktop app’s “Code” tab, which are actually different products. The VS Code + Claude extension workflow he’s describing is Windsurf/Cursor territory more than classic Claude Code. If a reader goes Googling “Claude Code” expecting a VS Code plugin experience, they’ll be confused.
The “100x faster” framing is classic content-creator hyperbole. Skip permissions + auto-accept is genuinely useful, but it’s also where things go sideways for non-technical users who can’t debug a spiral loop or catch a messy codebase. He acknowledges this in the “falls short” section at least — which is the most honest part of the piece.
The honest meta-observation:
This is a newsletter for people who want to feel like they’re building without really building. Which is fine!
There is some bad advice in here, coming from a seasoned engineer. Don’t put all your instructions in a Claude.md or instructions.md file; it will eat up the context window even if not relevant for the task. Use SKILL.md files instead.
You don’t have to be an expert dev to share your experience. But it is a good idea to research best practices before unintentionally giving bad advice on the matter as if you were the SME.
The "English is the new code" reframe is doing a lot of work here, in a good way. Most Claude Code guides start with terminal setup and lose people immediately.
The GitHub-first approach makes sense because it gives non-developers a mental model they can actually hold: this is like Google Drive for code. One thing I'd add from experience: the folder you point Claude Code at matters more than most guides suggest. If you start it inside a folder with too much unrelated context, the early sessions get confused. Starting in a clean, purpose-specific directory and letting it build structure from scratch has worked better for me.
The auto-accept edits toggle is also a bigger deal than it sounds. Worth a dedicated note.
Great article for people that are new to Claude code. I recommend that before start coding use plan mode with AskUserQuestions tool it will save you a lot time and getting a much better outcome. Lastly use this handy command /init it will create the Claude.md for you. To really maximize your productivity after using it for while use /insight it will let you know how you are doing and how to get Claude code on the right track.
Hi Ruben! I just subscribed but unfortunately I didn't receive the welcome email with access to the Notion doc . I've checked my spam folder and it's not there either. Could you help me out? Thanks for sharing this !! really looking forward to the anti-AI writing style file!
Ruben, is Claude Code better at coding that, say, Cowork? I've been using Cowork, only because I haven't really used Code at all, but I was wondering if there's a difference. Thanks!
Thanks for sharing, love the explanation of Claude Code.
glad you liked it :) do you code?
Really useful piece. What stands out is not just Claude Code itself, but the bigger shift behind it. Coding is slowly becoming more accessible to people who can think clearly, give direction, and test well, even if they do not write syntax.
what's left is pure product thinking.
Exactly. Once the model layer becomes easier for everyone to access, the real difference shifts to product judgment. Not just what the tool can do, but what problem it solves, how smoothly it fits into work, and whether people actually keep using it.
Hey Ruben. Can you share the my voice , my rules with me? Or a guide to set them up would be great!
sure - check my dm.
Thanks for sharing this! super detailed, it honestly made me want to open my mac and sign in right away haha
read every single word. really glad i came across this. also… this made me realize how fast claude is evolving :)
go play with it now :) its honestly super fun.
Greaaaat article. I've been using Claude Code on a Raspberry Pi for a few months. This article does a much, much better job than I ever could in describing setup, benefits, tweaks, annoyances. Love your stuff!
the permissions thing is genuinely annoying :) glad you liked it.
I shared with Claude (it’s become habit)
Good piece — Ruben writes well for a non-technical audience and has clearly put thought into accessibility. A few honest takes:
What’s genuinely useful here:
The CLAUDE.md memory trick is solid and underused by beginners. The “screenshot the bug” workflow is practical. The “describe the outcome, not the steps” prompting advice is correct and worth repeating. These are real habits that save time.
Where it gets a bit sloppy:
He conflates Claude Code (the terminal-based agentic coding tool) with the Claude desktop app’s “Code” tab, which are actually different products. The VS Code + Claude extension workflow he’s describing is Windsurf/Cursor territory more than classic Claude Code. If a reader goes Googling “Claude Code” expecting a VS Code plugin experience, they’ll be confused.
The “100x faster” framing is classic content-creator hyperbole. Skip permissions + auto-accept is genuinely useful, but it’s also where things go sideways for non-technical users who can’t debug a spiral loop or catch a messy codebase. He acknowledges this in the “falls short” section at least — which is the most honest part of the piece.
The honest meta-observation:
This is a newsletter for people who want to feel like they’re building without really building. Which is fine!
i explained those in the blog by the way :)
I have found your writing to be inspiring and incredibly useful. Thank you.
really glad to know.
Exactly!!!
There is some bad advice in here, coming from a seasoned engineer. Don’t put all your instructions in a Claude.md or instructions.md file; it will eat up the context window even if not relevant for the task. Use SKILL.md files instead.
Look it up.
I actually saw this yesterday: https://x.com/trq212/status/2033949937936085378.
Reminder: me and my entire community we do not want to code for a living.
I believe you are a dev yourself - so a different audience.
You don’t have to be an expert dev to share your experience. But it is a good idea to research best practices before unintentionally giving bad advice on the matter as if you were the SME.
Ruben it was really helpful, I now created my first website using Claude Code with zero coding knowledge. Thank you!!
love to hear it :) if you need anything, i'd love to assist you
Amazing read
glad you liked it :)
The "English is the new code" reframe is doing a lot of work here, in a good way. Most Claude Code guides start with terminal setup and lose people immediately.
The GitHub-first approach makes sense because it gives non-developers a mental model they can actually hold: this is like Google Drive for code. One thing I'd add from experience: the folder you point Claude Code at matters more than most guides suggest. If you start it inside a folder with too much unrelated context, the early sessions get confused. Starting in a clean, purpose-specific directory and letting it build structure from scratch has worked better for me.
The auto-accept edits toggle is also a bigger deal than it sounds. Worth a dedicated note.
a messy folder is a confused claude. your fault and not claude's :)
Yeah, true that! Learning by doing!
Great article for people that are new to Claude code. I recommend that before start coding use plan mode with AskUserQuestions tool it will save you a lot time and getting a much better outcome. Lastly use this handy command /init it will create the Claude.md for you. To really maximize your productivity after using it for while use /insight it will let you know how you are doing and how to get Claude code on the right track.
solid add. thanks for this :)
Just returning the favor. Your newsletter have been extremely valuable to me.
Possibly one one of the most valuable pieces of content I've come across this year. Thanks a ton for this!
thats really nice to know - what did you like about it? so i can keep doing it :)
You’re right I won’t be coding but this is so useful
we’re knowledge workers :) but fun to try once in a while.
Hi Ruben! I just subscribed but unfortunately I didn't receive the welcome email with access to the Notion doc . I've checked my spam folder and it's not there either. Could you help me out? Thanks for sharing this !! really looking forward to the anti-AI writing style file!
hi - it take a few mins for the welcome email to arrive :) dm me if there’s still nothing.
Ruben, is Claude Code better at coding that, say, Cowork? I've been using Cowork, only because I haven't really used Code at all, but I was wondering if there's a difference. Thanks!
cowork is not for coding - the infographic i attached will help you differentiate the two :)
The VS hack A+ - thanks!
you’re welcome. tried it yet?