Hey Ruben, just wanted to say thanks π your content is genuinely helpful. No fluff, no filler, just stuff you can actually use. Love that.
BTW, Claude is the only one I'm still paying for this month π Tried GPT, Perplexity - didn't stick. Claude just works for me...
Now, I might've missed this somewhere in your older posts, but I'm really curious what you think about the whole privacy side of things with Claude. Like, how careful do we actually need to be? What's fine, what's not? And if you're comfortable sharing how do you set things up on your end?
Especially Memory & preferences how do you configure that? A screenshot would be amazing if possible...
And also the rest of the settings under Capabilities and Privacy, things like Location metadata, Help improve Claude all of it.
The 6-feature framing is useful but I'd push back on the knowledge work claim. Depends heavily on what you mean by it.
I use Claude for coding and agent orchestration - genuinely better than GPT there. But for research synthesis with large documents, Gemini 3 Pro's context window is hard to beat at its price point.
The real insight here: treating it as Cowork rather than chatbot. That mental model shift matters more than any benchmark. Once I started thinking of it as a collaborative environment, my use patterns changed completely. Tool selection became secondary to how I was framing the work.
I need help, Ruben. I am exhausted, overwhelmed, anxious and feel completely drained looking at reels after reels on how to use AI to automate job search, tweak resume, ATS, draft emails for recruiters. I was laid off from my FT teaching position after eight years at Public College. Being an educator, I am hardwired to learn and learn quickly. However, the sheer volume of information is driving neurons to go haywire. I want to learn AI, not just to find a job but may be to not have to look for a job anymore. Please tell me where to start. π
Teachers are the best AI users I've seen. Because you already know how to break things down, give clear instructions, and iterate when something doesn't land.
Incredibly helpful - motivates me to expand my skills with Claude to get more from the tool. Question: can I get Claude to take meeting notes via a Connector, Plugin, or Artifact?
After reading your newsletter I decided to activate the yearly Pro plan of Claude this morning.
I tried to launch your "You are a Taste Interviewer" prompt in the Cowork to "find the real me in a MD file" and well... it's been working for nearly 9 minutes and counting:
Working through a complex response... Β· 9m 9s
Is it normal? I'm used to super flash response by ChatGPT...
Hey Ruben, thanks for replying to my comment. Yes I did it, I recall a newsletter of yours where youβd suggest always to keep it on and with the latest model option selected.
If I switch to the normal chat bot it seems it can handle the conversation anyway but Iβm not sure I will get the file MD back properly. :/
Claudeβs Artifacts feature was a game changer for prototyping, but the real moat is the low hallucination rate in technical tasks. For anyone building AI products, Claude is becoming the default 'brain.' Anyone still finding reasons to stick with OpenAI for RAG?
Hey Ruben, thanks for the response. I'm enjoying Claude so far more than ChatGPT. Being in sales, I am a text file strategy is a massive improvement over ChatGPT. I feel like I'm one step above all of my colleagues now.
Wondering if you think the $100 version of Claude is worth it and how the PowerPoint add-in compares to Gamma.
Thanks for this very detailed analysis Ruben. I've been using Chatgpt, Gemini and Claude for a while now and each is good in their own way. Where I noticed Claude does better is on the presentation creation, the ppt output is brilliant, the fact that it uses html language to design makes a huge difference to the output. I've also used it to create structured excel files with formula and again it worked great. You opened up a new world of possibilities though and I look forward to implementing them, especially yhe Excel plugin and the coworker.
What is the best tool in Claude for translation work? But not just 'translate A into B'. I mean real translation work, where you interact with Claude to refine your/its translation, and then make it paste it in your translation tool. It struggled to recreate a document that could be opened (yes, it was not a simple document, it contained XML strings).
hi Ruben, this is very useful, thank you. About your point on Grok - I would add that the model of choice may still depend on the topic you work on. My concern is that Grok's advantage on accessing X introduces demographic bias (I found that nearly two-thirds (63.7%) of X users are male, and the dominant age group is 25-34. So Grok's training data skews male, younger, and tech-oriented. Plus the platform is quite politicised.). Do you think this would have impact when using model say for research on female wellness focused topics?
Hi Ruben, I switched to Claude for a lot of my knowledge work at the end of last year. I think the quality in a lot of areas is superior; however, the usage limits in Pro are becoming almost unmanageable. Do you have any tips and tricks beyond the obvious to help manage this as it appears to be a common issue?
Not prompting from scratch. Write markdown files with your context, style, examples, and rules. Drop them in a Cowork folder. Cuts the back-and-forth in half.
Not every task needs Opus. Itβs the model that burns usage faster.
Hey Ruben, just wanted to say thanks π your content is genuinely helpful. No fluff, no filler, just stuff you can actually use. Love that.
BTW, Claude is the only one I'm still paying for this month π Tried GPT, Perplexity - didn't stick. Claude just works for me...
Now, I might've missed this somewhere in your older posts, but I'm really curious what you think about the whole privacy side of things with Claude. Like, how careful do we actually need to be? What's fine, what's not? And if you're comfortable sharing how do you set things up on your end?
Especially Memory & preferences how do you configure that? A screenshot would be amazing if possible...
And also the rest of the settings under Capabilities and Privacy, things like Location metadata, Help improve Claude all of it.
π
Youβre welcome!! I use Grok for search now and Claude for everything else.
The one setting that actually matters: help improve Claude.
If it's ON, your conversations can be used by Anthropic to train future models. And they can keep that data for up to five years.
If it's OFF, they don't use your chats for training.
Right, Claude is handling pretty much everything for meπ I might give Grok and Gemini a try soon. Anyway, I got your point about privacy...
Thanks! π
The 6-feature framing is useful but I'd push back on the knowledge work claim. Depends heavily on what you mean by it.
I use Claude for coding and agent orchestration - genuinely better than GPT there. But for research synthesis with large documents, Gemini 3 Pro's context window is hard to beat at its price point.
The real insight here: treating it as Cowork rather than chatbot. That mental model shift matters more than any benchmark. Once I started thinking of it as a collaborative environment, my use patterns changed completely. Tool selection became secondary to how I was framing the work.
When I say knowledge work, I mean writing, thinking, analyzing, building with your files.
Claude is not the best at everything. I said that in the piece.
Grok? Are you paid to use or try it? I find it feckless.
I pay for it, same as Claude, same as every tool I recommend here.
I need help, Ruben. I am exhausted, overwhelmed, anxious and feel completely drained looking at reels after reels on how to use AI to automate job search, tweak resume, ATS, draft emails for recruiters. I was laid off from my FT teaching position after eight years at Public College. Being an educator, I am hardwired to learn and learn quickly. However, the sheer volume of information is driving neurons to go haywire. I want to learn AI, not just to find a job but may be to not have to look for a job anymore. Please tell me where to start. π
Teachers are the best AI users I've seen. Because you already know how to break things down, give clear instructions, and iterate when something doesn't land.
That is literally what makes someone good at AI.
Ok, Iβll try Claude this weekend, you convinced me. Image generation sucks, but I've got Gemini for that. π©·π¦©
Nothing touches it right now. Hopefully you give Cowork a real try too.
And tell me how it goes :)
I will!π©·π¦©
Just got Claude Pro for my small team today. Tomorrow weβll do whatβs in this article. The next day, weβll be in the future :)
This is the energy. Go get it :)
See you and your team in the future!!
Thank you for this detailed step-by-step guide. Much appreciated.
Thanks for reading. Now try it today :)
Incredibly helpful - motivates me to expand my skills with Claude to get more from the tool. Question: can I get Claude to take meeting notes via a Connector, Plugin, or Artifact?
Not natively, no. Claude can't join a Zoom or Teams call and listen live.
Though you can connect Granola (what I use for meeting notes btw) to Claude :)
I wrote a piece about it here: https://ruben.substack.com/p/you-forgot-70-of-yesterdays-meeting
Hi Ruben / All,
After reading your newsletter I decided to activate the yearly Pro plan of Claude this morning.
I tried to launch your "You are a Taste Interviewer" prompt in the Cowork to "find the real me in a MD file" and well... it's been working for nearly 9 minutes and counting:
Working through a complex response... Β· 9m 9s
Is it normal? I'm used to super flash response by ChatGPT...
Can you please help?
Thanks,
Marco
Hi, Marco - did you turn Extended Thinking on?
Hey Ruben, thanks for replying to my comment. Yes I did it, I recall a newsletter of yours where youβd suggest always to keep it on and with the latest model option selected.
If I switch to the normal chat bot it seems it can handle the conversation anyway but Iβm not sure I will get the file MD back properly. :/
Claudeβs Artifacts feature was a game changer for prototyping, but the real moat is the low hallucination rate in technical tasks. For anyone building AI products, Claude is becoming the default 'brain.' Anyone still finding reasons to stick with OpenAI for RAG?
I don't build AI products so I won't pretend to have an opinion there :)
This is quality. Giving Claude a chance now.
Super cool - how was it? :)
Hey Ruben, thanks for the response. I'm enjoying Claude so far more than ChatGPT. Being in sales, I am a text file strategy is a massive improvement over ChatGPT. I feel like I'm one step above all of my colleagues now.
Wondering if you think the $100 version of Claude is worth it and how the PowerPoint add-in compares to Gamma.
Thanks for this very detailed analysis Ruben. I've been using Chatgpt, Gemini and Claude for a while now and each is good in their own way. Where I noticed Claude does better is on the presentation creation, the ppt output is brilliant, the fact that it uses html language to design makes a huge difference to the output. I've also used it to create structured excel files with formula and again it worked great. You opened up a new world of possibilities though and I look forward to implementing them, especially yhe Excel plugin and the coworker.
Yes, the Excel plugin is a different beast entirely.
How about Cowork? You tried it yet?
What is the best tool in Claude for translation work? But not just 'translate A into B'. I mean real translation work, where you interact with Claude to refine your/its translation, and then make it paste it in your translation tool. It struggled to recreate a document that could be opened (yes, it was not a simple document, it contained XML strings).
Cowork. Without a doubt.
hi Ruben, this is very useful, thank you. About your point on Grok - I would add that the model of choice may still depend on the topic you work on. My concern is that Grok's advantage on accessing X introduces demographic bias (I found that nearly two-thirds (63.7%) of X users are male, and the dominant age group is 25-34. So Grok's training data skews male, younger, and tech-oriented. Plus the platform is quite politicised.). Do you think this would have impact when using model say for research on female wellness focused topics?
When I say Grok is the best for search, I mean for what I use it for: AI news, tech, what's trending right now, who said what.
If itβs research-heavy work, you might want to try Perplexity.
Hi Ruben, I switched to Claude for a lot of my knowledge work at the end of last year. I think the quality in a lot of areas is superior; however, the usage limits in Pro are becoming almost unmanageable. Do you have any tips and tricks beyond the obvious to help manage this as it appears to be a common issue?
Not prompting from scratch. Write markdown files with your context, style, examples, and rules. Drop them in a Cowork folder. Cuts the back-and-forth in half.
Not every task needs Opus. Itβs the model that burns usage faster.
ΠΠ°, ΡΠ΅Π³ΠΎΠ΄Π½Ρ ΠΏΠΎ ΠΌΠ½ΠΎΠ³ΠΈΠΌ Π·Π°Π΄Π°ΡΠ°ΠΌ ΠΎΡΠΊΡΡΠ» Π΄Π»Ρ ΡΠ΅Π±Ρ ΠΠ»ΠΎΠ΄, Π½ΠΎ ΡΠ°ΠΊΠΆΠ΅ ΡΠ°Π±ΠΎΡΠ°Ρ ΠΈ Ρ Π΄ΡΡΠ³ΠΈΠΌΠΈ ΠΏΠ»Π°ΡΡΠΎΡΠΌΠ°ΠΌΠΈ ΠΠ, Π² ΡΠΎΠΌ ΡΠΈΡΠ»Π΅ ΠΈ Π΄Π»Ρ Π²Π·Π°ΠΈΠΌΠΎΠΏΡΠΎΠ²Π΅ΡΠΎΠΊ
What AI tools? :)