Future-Proof Your Career with AI Newsletter Strategy

View Email

Why your firm is struggling with AI adoption

khemaridh@substack.com4/26/2026

View Email

I tried OpenAI's new "Super App"

khemaridh@substack.com4/23/2026

View Email

Claude Cowork gets some competition

khemaridh@substack.com4/19/2026

View this post on the web at https://khemaridh.substack.com/p/what-milkshakes-can-teach-us-about I think about this comic strip all the time. Let’s be honest. Using AI to summarize and create emails is one of the most popular use cases for this powerful technology. And with the rise of Claude CoWork, [ https://substack.com/redirect/40f62545-7dac-41a6-8519-ce73e928b47b?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] it’s become even easier to create elaborate presentations, briefing documents and LinkedIn posts. But when you zoom out and take stock of all these deliverables (not to mention token utilization [ https://open.substack.com/pub/khemaridh/p/ai-just-got-way-less-fun?r=bf55&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true ]), what is really happening? And are we actually moving the needle? Claude Cowork is the most powerful AI tool for knowledge work Imagine sitting down Monday morning and your meetings are already prepped, your inbox is triaged, and last week’s notes are organized — all before you opened your laptop. That’s Claude Cowork running on a schedule you set once. This self-paced course teaches you to build that system. Finish it in a weekend. The answer can be found in milkshakes I know this sounds silly, but bear with me. Here’s a 4 minute video [ https://substack.com/redirect/c5bdcb55-006a-406f-a3d4-32c723ef1fac?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] from the late marketing professor Clayton Christensen called Understanding the Job: In this video, he tells the story about milkshake sales. The majority of the milkshakes were being purchased before 8am, which is very counter-intuitive for a product that is a “dessert.” So Christensen set out to answer the question: What job is a milkshake hired to do? There’s an old-school framework in marketing called Jobs to be Done [ https://substack.com/redirect/9170744d-1867-4d49-87b5-c2d5ff1523d3?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] which states that consumers buy products to fulfill a certain job. So the “job” of Lululemon shorts is to help you get fit. And the “job” of a MacBook Pro is to help you generate income. So back to the milkshake. It turns out that the majority of milkshake buyers were morning commuters. They didn’t want something sweet after a Big Mac. Heck, they might not even have been trying to satisfy a sugar craving. Instead, they had “a long boring drive” and needed something to keep them occupied. They weren’t looking for an outright meal, but needed something to hold them over until a mid-morning breakfast. And here’s how a milkshake stacked up relative to the alternatives: Bananas were eaten too fast Donuts were too messy Bagels were hard to eat while driving Snickers bars felt too indulgent The reason this short video always blows my mind is that it shows that it’s not always clear why we do a certain activity. Which has a lot of implications in an AI world. It’s vibes all the way down I’ve worked with many companies filled with extremely hard-working professionals. They are talented and their organizations are highly profitable. But when you ask them to specify what their actual work consists of — they often find it hard to define. In Daniel Miessler’s post the most important ideas in AI right now [ https://substack.com/redirect/c5b608a9-b9c7-487b-aa8f-720022f0df3a?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] he doesn’t hold back (emphasis mine): Most organizations run on vibes and spreadsheets. AI makes all of that visible. The actual work, the actual costs, the actual quality—all of it becomes measurable in ways that were never practical before. Miessler also argues that there’s an “articulation” gap between what experts know and what’s written down: Most expertise lives in people’s heads. Cliff, the 62-year-old who knows how everything works but never documented any of it. When Cliff retires, that knowledge dies with him. And in an ideal world, every leader would have a map of both the job to be done and how it gets executed (by both humans and agents). From vibes to jobs I challenge everyone to really think deeply about their “job” and what value they are ultimately delivering to their stakeholders — whether it’s their clients, shareholders or the public good. AI is already eliminating a massive amount of tedious work — the emails and PowerPoints are already writing themselves. I know that in my business, I’ve been able to create massive amounts of decks, newsletters and training materials. If my “job” is merely to help people learn AI then I am passing with flying colors. But that’s like saying a milkshake is dessert. Upon deeper reflection, I believe that my job is to help people achieve professional excellence. And AI is just a vehicle to help them with that job. Download our free guide to Claude Cowork Unsubscribe https://substack.com/redirect/2/eyJlIjoiaHR0cHM6Ly9raGVtYXJpZGguc3Vic3RhY2suY29tL2FjdGlvbi9kaXNhYmxlX2VtYWlsP3Rva2VuPWV5SjFjMlZ5WDJsa0lqbzBNekExTVRReE9UZ3NJbkJ2YzNSZmFXUWlPakU1TkRBM09EYzVNeXdpYVdGMElqb3hOemMyTXpRMU1ETXpMQ0psZUhBaU9qRTRNRGM0T0RFd016TXNJbWx6Y3lJNkluQjFZaTB6TXpZek5USTJJaXdpYzNWaUlqb2laR2x6WVdKc1pWOWxiV0ZwYkNKOS43cEhRZ1o0QU92azRRX2NESU5QdGp5MEUyQWZwY2I2Y1VEeHhDQ3JZX1kwIiwicCI6MTk0MDc4NzkzLCJzIjozMzYzNTI2LCJmIjp0cnVlLCJ1Ijo0MzA1MTQxOTgsImlhdCI6MTc3NjM0NTAzMywiZXhwIjoyMDkxOTIxMDMzLCJpc3MiOiJwdWItMCIsInN1YiI6ImxpbmstcmVkaXJlY3QifQ.zdDL_b8A1n7FTidgtq-cig1ootvRDTl_Srb6KeToKfw?

View Email

What milkshakes can teach us about AI

khemaridh@substack.com4/16/2026

View Email

How to get your company AI-pilled

khemaridh@substack.com4/12/2026

View Email

AI just got way less fun

khemaridh@substack.com4/9/2026

View Email

The Ultimate AI Catch-Up Guide

khemaridh@substack.com4/5/2026

View Email

Claude now multi-tasks with Excel and PowerPoint

khemaridh@substack.com4/2/2026

View Email

A complete list of Claude's new features

khemaridh@substack.com3/29/2026

View this post on the web at https://khemaridh.substack.com/p/claude-cowork-how-to-use-the-new 2025 was all about prompts. [ https://substack.com/redirect/699e12a4-89fb-4f67-a2a1-b6344d654e78?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] This year is all about context. [ https://substack.com/redirect/3a19b746-2202-451d-a82c-7e99e884d148?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] Yes, the models are getting way more powerful at long-running tasks. But more importantly, they now can process much more context. Cowork just added a feature to make it much easier to manage all of this additional context. An introduction to Cowork Projects Throughout 2025, I was on the record saying that Claude Projects outperformed ChatGPT’s version. It seemed like the former used a more intelligent RAG approach to understanding and synthesizing your data. Then Claude Cowork came along [ https://substack.com/redirect/c515e146-4ebc-42d8-9510-95978b9d9252?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] and let users run sessions from their local machines. This immediately fixed the “last mile” problem — but created a new one. How was context managed when it sat on countless files and folders? This past week, the Cowork team delivered a solution. Hit your goals faster using Claude Code (like Meek Mill) Meek Mill discovered Claude Code and he’s been automating like crazy. While he received a helping hand from some “tech youngbull,” he still had some questions. (He also probably struggled with the IDE, Terminal, Skills and API endpoints.) Nonetheless, he found use cases across his family office and business processes. Claude Code users (like Meek) are watching their skills go “parabolic.” It lets you build tools that keep working when you’re not: meeting analyzers, prospect research pipelines, dashboards that surface what matters before you ask. No coding required — just the reps that separate builders from prompters. Creating your first project From Claude’s official feature announcement: [ https://substack.com/redirect/c786dd11-48bf-4d54-b132-93f39cd8eb59?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] Projects keep your tasks and context in one place, focused on one area of work. Files and instructions stay on your computer. To get started, click on the new Projects tab in the sidebar. You’ll be presented with 3 options: If you’ve spent a long time curating a project in Claude “chat,” you can easily import it into your new Cowork project. Additionally, you can bring multiple projects into your new project. Alternatively, you can Start a project from Scratch. You’ll have the option to give it: Create Custom Instructions Add files and folders as your context Specify where your outputs should be saved This is an important distinction — the folder that holds your context can be different from the folder where your outputs are saved. This will be very impactful for teams looking to share common folders for context (but creating files in a different location). Here you can see how the project pulls in my master context files. (Cowork also creates background memory, [ https://substack.com/redirect/05f2ac0d-95d8-4b25-873e-3d79f0a8e905?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] periodically refreshing the context from chats and files when it sees fit.) I ran a lazy prompt to see if it was sourcing its context from the appropriate place. Create a powerpoint presentation of the current curriculum. Add visuals when necessary. Use the style guide Here’s the PowerPoint result. Next up, I wanted to create a landing page for my upcoming course on Claude Cowork. (It’s going to be dope.) Create a sales page for a course called Unfair Advantage using Claude Cowork. The materials will be similar to the way I teach Claude Cowork during training sessions. Use this outline below. In the right panel, you could see Cowork’s plan and which files it was choosing to pull into context. There was another context panel at the bottom right, but I couldn’t figure out what exactly it did. Final thoughts on Cowork Projects If I’m honest, these behave exactly how I would expect them to behave: You can create custom instructions You can easily add and remove context There’s a natural home for scheduled tasks [ https://substack.com/redirect/6888b12f-5afe-4519-bce4-16918d7c1446?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] As for future improvements — I hope all the folder selection options get consolidated and that you can easily see when you’re running into your context limits. And finally, I’d want to better understand how data from external connectors works with this context. Unsubscribe https://substack.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.x_XOG2e2q4y10iLubiOhF9zExwX2Ru_2AN6BXaEDg8M?

View Email

Claude Cowork: How to use the new Projects feature

khemaridh@substack.com3/26/2026

View Email

Claude is coming for your messaging apps

khemaridh@substack.com3/22/2026

View Email

The Complete Guide to Claude Skills

khemaridh@substack.com3/19/2026

View Email

The Rise of the AI Chief of Staff

khemaridh@substack.com3/15/2026

View this post on the web at https://khemaridh.substack.com/p/claude-can-now-run-scheduled-tasks Chat is dead! Chat is dead! For the better part of 2025, I predicted that chat wouldn’t be how we ultimately use AI. Claude Code [ https://substack.com/redirect/ad2b8d91-30bc-4f96-afd6-366d5a5b0fe0?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ], Cowork [ https://substack.com/redirect/017a6624-e746-466c-ab4c-94bf36bd65bb?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] and now Microsoft Cowork [ https://substack.com/redirect/52bd8c37-7a33-4b94-9536-c7a50570527d?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] proved that I was right. [ https://substack.com/redirect/4a983453-d1dc-46be-b6f1-8f5bbb523a96?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] But one problem still remained: automation. Coders figured out how to solve this challenge with an archaic workflow called CRON jobs. But the normies — myself included — needed something simpler. A way to automate that you could click and organize. And, of course, Claude came through and delivered. Introducing Scheduled Tasks for Claude Cowork This powerful feature lets you run actions including creating and updating files on a schedule. Like anything in Cowork, it can access files/folders as well as any skills [ https://substack.com/redirect/6a221470-10fb-4a74-91b1-e07fae8ff811?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] and tools (like the Chrome browser extension). [ https://substack.com/redirect/8e80b490-747c-42f1-bb19-11049edfe2b2?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] To schedule a task you have to be using the desktop app and be in the Cowork tab. Once you click Scheduled you’ll be taken to the following screen where you’ll select New Task. Next, you’ll get to build out your task: It’s pretty straightforward but some additional bits: Since you only get one shot at this prompt, it better be extremely detailed. Always click the more options button. Since Cowork runs locally on your machine, you need to give it a folder, especially if it’s going to create or modify files. If the task requires some heavy lifting, such as Excel or PowerPoint or browsing the web, I strongly recommend using Opus 4.6. This is where you set the frequency. Remember that your computer has to be on and awake, or else it won’t run. Once you’ve saved the task you’ll see it on your “dashboard.” When you click into it you’ll get to modify it. Here are a few pointers: You can always edit the task (including the prompt) You can run a trial to see how it works (which I highly recommend) These are tools that you’ve given the task “persistent access” to History of runs Now let’s go through 2 examples. Build our own army of agents Everyone’s talking about AI agents. And yes, scheduled tasks are a great first start. But they’re still not that powerful. Claude Code lets non-technical professionals build agents that work autonomously — analyzing transcripts after every Zoom call, surfacing your highest-leverage emails, monitoring deal announcements while you sleep. No coding required. Just clear thinking and our step-by-step course. Unfair Advantage costs $249 for lifetime access and a 14-day money back guarantee. Example 1: Meeting Prep Meeting prep is finally automatable thanks to scheduled tasks and connectors. The workflow is really simple. Every night, Claude looks at tomorrow’s calendar to look up meetings. It then prepares me with the following workflow: Grabs a bio on the attendees (LinkedIn, company website and personal blog) Looks at prior email interactions using the Gmail Connector Looks at prior calls using the Granola Connector [ https://substack.com/redirect/cdecfc6a-9850-4daf-8d25-7662fc0e992e?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] Sends each summary to a Slack channel Here’s what the prompt looks like: Go through my calendar for the next day. Look at all the meetings. Ignore the ones that don't have any invites. Then, for each meeting, send me a separate Slack message that covers the following: - Name - Quick background on them (via LinkedIn and web search) - If they have a blog or social presence, two links to the last things they've posted. - Look in Granola to see if we've had any conversations in the past month and give a two-sentence summary. - Look in my email to see if there's anything relevant from the last month to provide context Since there will be many meetings, separate each message on Slack with "-----" So that there is visual separation Here’s the output in Slack: Example 2: Automated Market Research For the next example, I wanted to create a very customized research agent. I wanted this agent to search the web each day to look for articles and research papers that could help me further develop my training programs. I used the same exact process to set it up. Here’s the prompt that I used: Conduct a series of web searches to look for articles that can help knowledge workers get better at AI. This includes : - use cases - examples - frameworks - organizational design/hiring - mindset shifts - upskilling The avatar reading these articles are knowledge workers who work in financial services, consulting, law management, marketing who know that AI is important but are looking to get deeper. They are smart and driven, but not software engineers. We want to prioritize articles from reputable mainstream sources and prominent bloggers: - FT, WSJ, NYT, Economist, Bloomberg - Harvard Business Review, VC websites, Management Consultants (McKinsey, BCG) - Prominent Blogs: Every.to, Ethan Mollick, CRA Admired Leadership, Conor Grennan, and Allie K. Miller Create a new Excel files with: - Article Name - Source - Author - Link - Summary - Category (Use case, framework, etc) - Ranking (1-5, 5=best) Grab the top 10 articles and make sure the links aren't paywalled And here’s the result — it’s damn good. Your turn So how should you go about using scheduled tasks? Here’s a simple process to set up your first scheduled tasks: Identify a repeatable task Think about a specific desired output (update a list, send a specific message, download a file) Create a detailed prompt that captures all the information in one-shot Identify the connectors that either add context (Granola, Google Drive) or that facilitate delivery (Outlook, Slack) Test it with “run now” Go and watch A Knight of the Seven Kingdoms with all your newfound free time Keep building more and more agents. It’s THAT easy Everyone’s talking about AI agents. And yes, scheduled tasks are a great first start. But they’re still not that powerful. Claude Code lets non-technical professionals build agents that work autonomously — analyzing transcripts after every Zoom call, surfacing your highest-leverage emails, monitoring deal announcements while you sleep. No coding required. Just clear thinking and our step-by-step course. Unfair Advantage costs $249 for lifetime access and a 14-day money back guarantee. Unsubscribe https://substack.com/redirect/2/eyJlIjoiaHR0cHM6Ly9raGVtYXJpZGguc3Vic3RhY2suY29tL2FjdGlvbi9kaXNhYmxlX2VtYWlsP3Rva2VuPWV5SjFjMlZ5WDJsa0lqbzBNekExTVRReE9UZ3NJbkJ2YzNSZmFXUWlPakU1TURNek56ZzVOaXdpYVdGMElqb3hOemN6TXpJd09ESTVMQ0psZUhBaU9qRTRNRFE0TlRZNE1qa3NJbWx6Y3lJNkluQjFZaTB6TXpZek5USTJJaXdpYzNWaUlqb2laR2x6WVdKc1pWOWxiV0ZwYkNKOS5TcWZubkNEX2lQejVZdUtKY3RqTDBzZ1ZscjlRZlltbXF0cktjZjBpeXFvIiwicCI6MTkwMzM3ODk2LCJzIjozMzYzNTI2LCJmIjp0cnVlLCJ1Ijo0MzA1MTQxOTgsImlhdCI6MTc3MzMyMDgyOSwiZXhwIjoyMDg4ODk2ODI5LCJpc3MiOiJwdWItMCIsInN1YiI6ImxpbmstcmVkaXJlY3QifQ.tbf3N7PffY0Uso7PgdJcmKg6oB8kUBpx_4fvwGzVDKs?

View Email

Claude can now run scheduled tasks

khemaridh@substack.com3/12/2026

View Email

The "Cursor Moment" for Finance

khemaridh@substack.com3/8/2026

View this post on the web at https://khemaridh.substack.com/p/i-paid-my-daughter-7-to-learn-claude I pride myself on being a thoughtful and principled parent. And I’ve read enough parenting blog posts to deeply understand that you should never use cash as a prize for intrinsic motivation. But here’s the deal. My 11 year old daughter wants to earn more money beyond her weekly chores. I wanted her to naturally come to AI to experiment and tinker — especially since the message she’s constantly getting at school is that “AI is BAD.” But she wasn’t interested, so I upped the ante. I asked Claude if it’s ok to motivate kids with cash payments. Here’s the bull case: Good idea if: it increases curiosity, she starts choosing projects, and you can gradually reduce payment without a meltdown. And the bear case: Bad idea if: she becomes more transactional about learning, refuses anything unpaid, or it undermines your family’s chore culture. Nevertheless, I bit the bullet. I offered her $7 for every hour she spent learning AI. My plan is to give her projects that would ultimately lead to her building her own AI portfolio of websites, games, agents, chatbots and products. With one caveat. I’d never ask her to do this. Instead she’d have to come to me proactively for new projects. Here’s how the first $7 played out. Stop prompting. Start building. Most professionals are still chatting with AI — asking questions, copying answers, starting from scratch every session. That’s soooooo 2025. Claude Code lets you build tools that keep working when you’re chilling: meeting analyzers, prospect research pipelines and dashboards that surface what matters before you ask. All it takes is 7 days of focus. Step 1: Download Claude To kick things off, I created her own Claude login on my MacBook (since I want her to eventually use Claude Cowork and Claude Code [ https://substack.com/redirect/dd18c2b5-7e8b-438b-9d1c-b239c3daed8c?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ]). I had her sign up for the $20 plan and download the Claude desktop app. Throughout the process, I observed how she attempted to figure out issues like installing the app and linking her Gmail account. I felt like I was giving her some “mini life-lessons” by showing her how to use WisprFlow [ https://substack.com/redirect/3bea2759-a260-4499-9947-5c1690c6f011?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] and to store login info in 1Password. Step 2: Configure Claude and Select Models Once she was in the app, I had her immediately go into settings to ensure that memory [ https://substack.com/redirect/412c3848-18e3-4ced-8103-e3fabc08feda?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] and search old chats were activated. Admittedly, the importance of these settings wasn’t obvious to her. Can you guess what we did next? Model selection. I made it very clear that there’s a hierarchy of models and that she should always start with Opus 4.6 (“trust me, bro”) and then move over to Sonnet 4.6 when she hit her limits. A brief security pause Next up was “the talk.” Not the birds and the bees, but a quick rundown of AI security: For now, we’re using it primarily to build our projects When you’re working on it, I have to be around (after all, I gotta track the hours) Do not share personal information about yourself and our family without asking Do not use this on your homework without consulting me If I’m honest, my biggest fear with AI for kids is not the job loss or privacy — it’s that it will be so tempting for them to lean on AI for emotional companionship. So that’s probably what I’m vigilantly monitoring. Step 3: Have Claude Interview You Here I used the “blank slate metaphor” to explain that AI knew nothing about her. [ https://substack.com/redirect/c6dcd7d0-f91a-4e17-a92b-514570580cd6?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] So I suggested that we have AI “interview” her about her classes, hobbies and tastes. I explained that this would help create what AI folks call “context.” (BTW, I also recommend this interview method [ https://substack.com/redirect/8df4d01e-6383-4108-a244-6bc99f497d0a?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] in all my corporate trainings.) If you’re curious about her mood to this point, the general vibe was “How much more time until I get my $7?” Step 4: Build a game Her first project was to build a game. She used a simple prompt: Build me a game with jumping rats inspired by Jellycats, Pusheen and kawaii art. Use lots of pink. Claude defaulted to building the following artifact: I then asked her to come up with 3 of her own improvements (to spur her critical thinking). And then I asked her to ask Claude for 3 more (to show her how to use AI as a co-pilot). Step 5: Set up GitHub It took me 44 years to finally understand what GitHub was and how I could use it. And I had a proud dad moment when my daughter created her first GitHub account (which we referred to as “a place to save your projects.”) Admittedly GitHub is a pretty scary website for non-coders, but with some help from Claude she was able to create her first “repo” (aka project). TBH, pushing code to GitHub to be deployed live is pretty advanced and we hit our hour limit and she ran out of steam. (We also burned through all her Opus credits.) I wonder if she comes back for round 2 this weekend… Stop prompting. Start building. Most professionals are still chatting with AI — asking questions, copying answers, starting from scratch every session. That’s soooooo 2025. Claude Code lets you build tools that keep working when you’re chilling: meeting analyzers, prospect research pipelines and dashboards that surface what matters before you ask. All it takes is 7 days of focus. Unsubscribe https://substack.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.YcRyql6mIpmMRjycP6jsEThWQL5anpFEd-4PVOnbrqY?

View Email

I paid my daughter $7 to learn Claude

khemaridh@substack.com3/5/2026

View Email

Another viral doomsday post?

khemaridh@substack.com3/1/2026

View Email

Stop using AI like it's 2025

khemaridh@substack.com2/26/2026

View Email

The $1 Trillion SaaS Reckoning

khemaridh@substack.com2/22/2026

View this post on the web at https://khemaridh.substack.com/p/have-we-reached-powerpoint-agi Friends, something big is happening. [ https://substack.com/redirect/459dce2e-70a7-4484-aa87-b14114177282?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] In the world of PowerPoint. This week, we got two announcements that bring us closer to PowerPoint AGI. Claude launched a native PowerPoint plug-in NotebookLM (by Google) finally allows you to edit and export to PPT Can we finally reclaim the thousands of hours lost each year to building slide decks? Prompting Was the Training Wheels. It’s Time to Take Them Off. I know you spent all of 2025 learning how to be a fantastic prompter. Sure, that’s super important. But if you’re still copy-pasting into a chat window and re-introducing yourself during every chat session, you haven’t created any personal leverage. Claude Code (which inspired Cowork) is a completely different game. It lives permanently inside your file ecosystem and builds tools that keep running far beyond your chat session. A great prompt gets you a good answer once. Claude Code gets you a tool that generates good answers forever — transcript analyzers that profile prospects after every Zoom call, email agents that surface your highest-leverage replies, a second brain that interacts directly with your knowledge. Unfair Advantage takes you from basic prompter to AI builder in 7 days. $249, lifetime access, zero coding required. The Claude PowerPoint Plug-in Claude recently launched a native plug-in that you run directly from the PowerPoint app. According to the product launch page [ https://substack.com/redirect/0dfa6495-2191-490e-ae07-db1329319244?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ], this plug-in can: Build from your brand templates Modify an existing deck Generate a full deck from a prompt Create native charts and diagrams Once you install the plug-in, you’ll see it in the right toolbar as a panel: I started off with a simple request: take the quote; I believe it's from Lenin (there's weeks when decades happen or something like that), and organize these seven images in a way that is coherent and legible. Use rounded corners if possible It took 3-4 iterations to get the order correct, but here was the final output: Next, I needed some design help. Here’s a very common slide that I use to explain context scaffolding: [ https://substack.com/redirect/ee06cd7b-f640-47d3-bdc0-db680ccb287a?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] I wanted to pretty it up and gave the following prompt: take this existing slide and make it look better. Use some kind of gradient color. Preserve the histogram nature of it, and make the text better. look at the color scheme from the other slides It fumbled the first iteration but got the second one on the first attempt: I tried it again on a “timeline slide” showing my career evolution into AI, but it couldn’t get it right. My issues mostly related to the placement of images: Logo too high Logo on text Missing logo Should have spelled LaTour Finally, I went for the big kahuna. One-shotting a presentation from a detailed outline. Given the shift away from chat towards agents (for all use cases), I’ve been revamping my curriculum. I dropped in a 1,000 word outline into the prompt and said: Build this Here’s one slide: And another: It was pretty clean, but tbh I didn’t love the design choices that it made. NotebookLM expands its presentation capabilities NotebookLM also made a quiet upgrade announcement: If you’re unfamiliar with this quiet AI workhorse [ https://substack.com/redirect/f1b6fde3-d997-4342-9db1-229d4aa8dbd8?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ], NotebookLM lets you upload up to 500 sources and synthesize them in a variety of different outputs. [ https://substack.com/redirect/b30e38d4-0467-46b9-bc63-3df476ffbd70?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] I plugged in this fantastic post — A Guide to Which AI to Use in the Agentic Era [ https://substack.com/redirect/4c25d3cf-687b-4723-9e32-9a3e4038eb74?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] — and asked NotebookLM to create a slide deck. Here’s one slide on NotebookLM And another featuring a horse [ https://open.substack.com/pub/khemaridh/p/chatgpts-faster-horse-problem?r=bf55&utm_campaign=post&utm_medium=web&showWelcomeOnShare=false ]: Now here’s where it gets interesting. In the past, once the slides were created, you couldn’t edit them — which really made it unusable for anything that required a degree of professionalism and design consistency. Here’s the result: Not bad, it followed the instructions pretty well and the slide is a significant improvement. Now it’s time for a little let down. While the Export to PPTX feature has been announced, it hasn’t been rolled out to my account yet. The final verdict While I enjoyed having the native PowerPoint plug-in, I thought NotebookLM had a significantly better design aesthetic. The revision feature is nice too, particularly since you can modify specific slides and/or the entire deck. The wildcard remains the “export” function which should arrive any day — I can’t wait. Build your “unfair advantage” with Claude Code Our new course teaches non-technical professionals how to build real tools — transcript analyzers, email agents, custom dashboards — without writing a single line of code. Unsubscribe https://substack.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.q1YuD0Prtk7Y1aLi8IZ3Fq5ifxMkn78ENbjRfwaKD8k?

View Email

Have we reached PowerPoint AGI?

khemaridh@substack.com2/19/2026

View this post on the web at https://khemaridh.substack.com/p/this-ai-blog-post-broke-the-internet AI has been on a bender in 2026. It started with Claude Cowork bringing agentic workflows to Excel and PowerPoint. Then Opus 4.6 and ChatGPT 5.3 Codex continued their giant strides in performance and “intelligence.” In late January, folks built their own personal AI agents on dedicated Mac minis. And then last Wednesday, Matt Shumer broke the Internet. In the odd chance you’ve been on a meditation retreat, his post Something Big is Happening [ https://substack.com/redirect/780ccfbd-3d55-4088-a81d-c6cd2dc9136f?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] went absolutely bonkers. The tweet alone has been viewed over 80 million times. Its blast radius was so expansive that old school CEOs “panic-sent” it to their executive teams as required reading. Right AND left-wing influencers used it to rally future anti-AI legislation. The dying media (Forbes and AOL.com) featured the story prominently. Even my meditation teacher sent it to me. (BTW, the post served as a dope marketing campaign for my Claude Code course “Unfair Advantage” [ https://substack.com/redirect/a0139fa4-a412-4b16-9ca5-efc2cf6e192c?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] which also saw its registrations spike!) The tl;dr of the post is that AI is an exponentially powerful technology that is coming for everything you consider sacred: your job, dignity, financial assets and your kids’ futures. It’s the ultimate AI Rorschach Test. It will violently reinforce your existing world view on AI. If you’re bullish on AI, it’ll make you more bullish. And if you think AI will destroy the world, well that destruction has already begun. Personally, I fall into the very excited camp despite modest concerns. Here are my own takeaways. Everything is software One of Shumer’s key arguments is that AI dominates at coding. He’s right and the data overwhelmingly supports this: Spotify declared on an earnings call that its best developers haven’t written a single line of code since December Both the Claude Code and Codex GPT coding agents were predominantly built by themselves A significant percentage of new code on GitHub is AI-generated Coding is an activity that lends itself particularly well to AI. The accuracy of its outputs is directly verifiable. If I want to create an OpenTable clone, there’s a finite set of outcomes (i.e. can I book this reservation) that I can independently check. And coding operates on a very narrow subset of language. (Heck, even I’ve become a coder over the past two years. The most impactful tools I’ve built are a lightweight CRM focused on developing authentic relationships, a sales calls analyzer to improve my close rate and a curriculum generator to enhance my teaching pedagogy.) Shumer’s bull scenario hinges on the belief that all of mankind’s problems (and desires) can be distilled into software problems. Healthcare, finance, education, poverty eradication, entertainment are all fixable with software. And since the cost of building high-quality software is effectively a $100/month Claude subscription — buckle up! I’ve been implementing AI for financial firms for nearly two years and I say hold your horses: Turning non-software problems into software problems is easier said than done. For starters, data access is a huge problem. While software prides itself on transparency, public data sets (like HuggingFace) and open-source code repositories — other industries are more closed off. For these other domains, this means that AI suffers from a sizable data disadvantage. It’s not trained on the most complete data and it can’t use this data as its context. (Not to mention that in industries like finance, the data itself is the competitive advantage.) Furthermore, outside of coding the answers to many questions are not easily verifiable. Let’s say I wanted to answer the question: Should I invest in Google? Let’s try to turn this into a software problem. We could: Load in all of its historical financial statements. Compare the valuation to its peer group. Assess its existing customer base and pricing power. Decompose its factor exposures. Evaluate the composition of the board of directors. To turn this investment question into a software problem, you’d have to identify all the variables that would be required to answer it. And for something like a stock investment there are tens of thousands of factors that influence the outcome. But it’s even more challenging. The question itself is problematic. Are we looking at Google as a 1-day or 100 year investment? Are we looking at the return from an absolute, relative or risk-adjusted returns perspective? This is not how much of the finance industry operates. Between old ways of doing things, legacy tools (ahem, Excel) and a general apprehension to anything “coding-related” you can understand the hesitation (and difficulty) of redesigning an entire process to be more software-oriented. The same could be applied to industries like healthcare, law and consulting. How can you turn your work processes into software problems? I believe that Shumer is right that every single worker should be striving to push the limits on transforming their existing workflows into software problems that can be tackled by AI. Yet I also believe tremendous human judgement, intuition and experience are required to integrate all of that information into an actual decision. Can you speed run domain expertise? Here’s the part of Shumer’s post that put the fear of God into millions of knowledge workers: The honest answer is that nothing that can be done on a computer is safe in the medium term. If your job happens on a screen then AI is coming for significant parts of it. The timeline isn’t “someday.” It’s already started. I think this statement requires some clarification. Jamie Dimon’s job “happens on a screen” yet I promise you AI will not be the next CEO of JP Morgan. But, if your job is formatting tables and standardizing charts in PowerPoint — I’d be careful. So what unique advantage does Jamie Dimon have versus our young grad? Domain expertise. And here is where things get interesting. It’s a huge superpower to be fluent in AI. But it pales in comparison to being AI Fluent and having domain expertise. Part of the reason why my nascent business LaTour AI [ https://substack.com/redirect/de2543b5-b66b-4dc6-9f62-a8425a50668c?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ] has been so successful is because of my 15 years of experience in financial services. I have a strong understanding of the outcomes, nuance, constraints, edge cases, workflows and personalities of the industry. (Not to mention tons of relationships to facilitate biz dev.) And when paired with AI, you’ve got yourself a nasty combo. I believe Shumer is correct that AI Fluency will become table stakes. You can already see that happening today. But the real differentiator will be the domain expert who leverages AI to the max. So how does one acquire domain expertise in an AI world? Here’s my mental model for building domain expertise: books versus reps. “Reps” comes from doing the damn thing, whereas “books” comes from learning about the damn thing. Every industry will have its own books/reps ratio. For example, becoming a nuclear physicist probably requires a heavy dose of reading, research and learning. (And then a ton of experience as well.) On the other hand, becoming a great salesperson probably doesn’t require reading a lot of books about sales. Instead you have to go out and experience firsthand the rejection, coalition-building, empathy, social cues and persuasion techniques. AI is an extreme accelerant to the learning component. You have immediate and free access to the world’s knowledge in a customizable and conversational form. It’s patient and adapts to your learning style. However, acquiring the reps — doing the damn thing — is going to be hard to speed run. It’s these reps that will enable you to see where AI falls short, the relationships you’ll need to build and where the big opportunities lie. Should you be scared? Back to the Rorschach test. If you’ve made it this far, here’s what I know about you. I know that you’re wildly capable of taking your existing body of work and converting as much of it as possible into software problems. Is it a new way of thinking? Absolutely. Is it difficult? Not if you truly understand why you do the work you do. I also know that you are a voracious learner who will utilize AI to improve your craft. The more pride you take in your craft, the more motivated you’ll be to get better at it. And then there’s the reps. These reps compound over time. All you gotta do is show up — and the rest takes care of itself. Here’s one easy way to stay ahead A huge part of Shumer’s argument is that everyone can use code to solve problems. It’s cheap, powerful and accessible to everyone via Claude Code. I built this course because I wanted you to add this skill to your AI toolkit. In under a week you’ll learn how to build transcript analyzers that profile prospects after every Zoom call, email agents that surface your highest-leverage replies, a second brain that interacts directly with your knowledge. Unsubscribe https://substack.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.eQOskanisi1JzcEomUYwiRIbN9v1ehvsEPX6gkKWAo0?

View Email

This AI blog post broke the Internet

khemaridh@substack.com2/15/2026

View Email

Claude Cowork for Windows is here

khemaridh@substack.com2/12/2026

View Email

Will AI tear through Corporate America

khemaridh@substack.com2/8/2026

View this post on the web at https://khemaridh.substack.com/p/how-to-use-clawdbot-with-no-risk “There are decades where nothing happens, and there are weeks where decades happen.” I can’t even keep track anymore. ClawdBot. MoltBook. New Codex app. Nvidia calls off the OpenAI deal. Anthropic Legal. SaaS stocks sell-off. I’m still knee-deep on ClawdBot. While I don’t think the product itself will ever go mainstream — it is a massive inflection point on where things are headed. Last year using o3 and Claude Code for the first time felt like Magic Moments —there was just something about the experience, so unique, so cool, that you could get a little glimpse of the future. Personally, I want to experience that Magic Moment for ClawdBot. I don’t recommend you install it. It’s gnarly. But I still want you to experience it. And here’s how you can do it without putting yourself at risk. It starts with AI Coding Fluency You don’t need to know how to code to make this work. But you need to understand how to navigate a command line, GitHub, and an Agentic IDE (like Claude Code, Cursor or Codex). Thankfully you can literally ask ChatGPT how to do all these things. Or you can sign up to Unfair Advantage — our Claude Code course for smart, non-technical professionals [ https://substack.com/redirect/5a5cc53e-756e-462f-a0b6-0b69fb46935c?j=eyJ1IjoiNzRiZXZxIn0.26TDO4Ygo5l69NnkPzr2Ax0IIjv-K5IWcmNJKcK8PLY ]). Since the project is Open Source you can access it via GitHub. Next, you can copy the code (without running or installing it) to your local machine. It’s just a bunch of text files. The key here is that you’re not running it, it’s that you’re setting it up on your machine. To copy the code, you literally need one command inside a blank Claude Code window. If you’re new here, the easiest way is via the Claude Desktop app. download this repo https://github.com/openclaw/openclaw This will trigger a 3-5 minute download of all the files. Here’s what it looks like in the finder: Deconstruct the project with the help of AI You can now fully interact with this project through simple chat via Claude Code. Here’s my first question: ❯ ELI5, how does this project work? Here’s the response (truncated): What OpenClaw Is Imagine you have a really smart robot friend who can answer questions, help you with tasks, and remember conversations. But here’s the problem: this robot lives in a special building (the AI company’s servers), and you can only talk to it through specific doors (their apps). OpenClaw is like a telephone operator that lets you talk to your robot friend through ANY messaging app you already use - WhatsApp, Telegram, Discord, or even text messages! The Simple Story The Main Characters: 1. You - sending messages from your phone 2. The Messenger (WhatsApp, Telegram, etc.) - where you send your message 3. OpenClaw (The Gateway) - the telephone operator/translator 4. The Smart Robot (Claude, ChatGPT) - the AI that thinks and answers 5. Your Computer - where OpenClaw lives [Truncated] Remember — OpenClaw is not running. The LLM (Claude Code, in this case) is reviewing the code and answering. The questions we can ask are endless: ❯ Can you explain in less than three paragraphs to someone who understands LLMs well but is not a coder what makes this different than just using Claude Code on your machine? Here’s the response: OpenClaw vs Claude Code: Different Tools, Different Jobs Claude Code is an interactive coding assistant that runs in your terminal - you invoke it when you need coding help, it completes a task, then exits. OpenClaw is an always-on gateway server that connects messaging platforms (WhatsApp Telegram, Discord, etc.) to LLMs, acting as a persistent personal assistant. Think of Claude Code as a specialized IDE tool, while OpenClaw is more like running your own hosted chatbot service that routes messages from any channel to any LLM provider. The core difference is architectural: Claude Code manages terminal sessions and file operations for development workflows, while OpenClaw manages persistent conversational sessions across multiple messaging channels with features like pairing/authentication, group chat policies, media handling, and cross-platform message routing. OpenClaw lets you text your AI assistant from your phone via WhatsApp using the same conversational thread that remembers context across days, whereas Claude Code gives you a powerful coding agent that lives in your terminal for the duration of your development session. In short: Claude Code = coding assistant in your terminal, OpenClaw = personal AI infrastructure that makes LLMs accessible through the messaging apps you already use, running 24/7 on your hardware with full control over routing, permissions, and data storage. Next, I wanted to “leg into” the project with the appropriate security guardrails: ❯ On a 1-10 regarding security, I’m a 2 (risk averse). In short bullets, explain to me how I can “leg in” to this and make it more secure Phase 1: Isolated Testing Run OpenClaw in a Docker container or VM first (not your main machine) Use a dedicated, limited-scope API key (not your main Anthropic/OpenAI account) Start with just ONE channel (Telegram recommended - easiest to isolate) Set dmPolicy: “pairing” so only explicitly approved contacts can message Don’t enable group chats yet Phase 2: Lock Down Access Store bot tokens in separate files with chmod 600 (not in config or environment variables) Use allowFrom with explicit user IDs only (no wildcards, no usernames) Set groupPolicy: “disabled” to block all group messages Enable only the tools/actions you need: channels.telegram.actions.reactions: false, etc. Review logs daily initially: openclaw logs --follow Phase 3: Network Hardening [Truncated] Since ClawdBot has an entire ecosystem of plug-ins, skills, and customizations — I wanted to understand where I could extend it: ❯ I know that there's a rich ecosystem of add-ons and customizations. Can you also look at the documentation in their GitHub repo and make three brief recommendations about safe extensions? They could really help me better understand what's so special about this Each example merits its own section, starting with Memory Core Plugin: Memory-Core Plugin (Safest - Built-in, No External Dependencies) What it demonstrates: OpenClaw’s contextual memory across conversations - the AI remembers what you told it weeks ago. Security profile: ✅ Ships with OpenClaw (already vetted) ✅ Local-only (no external API calls) ✅ Read-only search through your workspace files ✅ No network exposure, no credentials needed ⚠️ Stores indexed data in ~/.openclaw/memory/ (keep permissions tight) Why it’s special: Unlike Claude.ai where each conversation is isolated, this lets your assistant remember “I prefer Python 3.11” or “my dentist appointment is Feb 15th” across all channels and conversations. It’s like giving the AI a notebook. Next up was something on diagnostics so I skipped it 😜. The next tip was effectively Longer Term memory. After all, LLMs are the worst co-workers since they don’t learn from their mistakes. This integration uses RAG techniques to access your old conversations: Memory-LanceDB Plugin (Moderate Risk - Requires OpenAI API) What it demonstrates: Long-term semantic memory - the AI can recall “that conversation about security in October” without you specifying it. Security profile: ⚠️ Requires OpenAI API key (sends embeddings to OpenAI) ⚠️ Stores vector database locally in ~/.openclaw/memory/lancedb/ ✅ Auto-capture/auto-recall can be disabled (start with both off) ℹ️ Creates embeddings of your conversations (consider privacy implications) 🔒 Mitigation: Use a dedicated OpenAI key with spending limits ($5/month cap) Why it’s special: This is what separates OpenClaw from simple chatbots. It builds a searchable knowledge base of your conversations. Ask “What did I tell you about my travel plans?” and it semantically searches months of history instantly. For my last query, I tried to peek into the future: ❯ If you had to predict the future and the big foundation model companies implement this into their offering, what would it look like and where would they struggle? Here’s what they’d build: Anthropic/OpenAI/Google Could Launch in 6-12 Months: “Claude Connect” or “ChatGPT Channels” - A hosted service where: You authenticate once with OAuth Connect your messaging accounts (WhatsApp, Telegram, Discord) Their servers handle routing between your messages → their AI Unified conversation history across platforms Persistent memory (they already have Projects/Memory features) Beautiful web dashboard for configuration [Truncated] And here’s where the foundation labs would struggle in building an OpenClaw alternative: 1. The Trust Paradox OpenClaw runs on your machine keeping data local, but foundation companies would route all your messages through their servers where they can see everything. Risk-averse users and enterprises won’t trust sending personal WhatsApp/Signal conversations through Anthropic’s infrastructure, especially when compliance requires data sovereignty. 2. The Business Model Conflict OpenClaw is provider-agnostic (switch between Claude, GPT, local models freely), but foundation companies need vendor lock-in to maintain revenue. If they support competing models they become a commodity router; if they don’t, users choose more flexible alternatives. 3. The Platform Access Problem WhatsApp Business API costs money per message and Meta would block mass personal routing, while iMessage has no official API (Apple would sue for reverse-engineering). OpenClaw individuals can use personal-use APIs and reverse-engineered protocols that don’t scale commercially but work fine at small scale. 4. The Compliance Nightmare Routing millions of users’ messages makes them legally responsible for data residency, content moderation, age verification, wiretapping laws, and breach liability. They’d need to scan and log everything for compliance, contradicting privacy promises and creating massive insurance costs. [Truncated: Customization Gap, Multi-Tenancy Technical Challenge] Now it’s your turn Fire up your GitHub and kick off your own ClawdBot “simulation.” What burning questions will it answer? Drop your responses in the chat. If you’re looking to level-up your career with Claude Code, look no further than our new course Unfair Advantage: Claude Code Mastery (for Non-technical smart people). Not only will you whip up your own “ClawdBot Simulator” you’ll build custom KPI dashboards to outperform your goals, transcript analyzers to generate more sales and intelligent email agents to identify the highest-leverage opportunities. Unsubscribe https://substack.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.SQMuiA8LQl-7uYTy3Ww1AlppBpBNtzjn5g2OIPopwKo?

View Email

How to use ClawdBot (with NO risk)

khemaridh@substack.com2/5/2026

View Email

Should we be scared now?

khemaridh@substack.com2/1/2026

View Email

Will Claude Eat Excel?

khemaridh@substack.com1/29/2026

View Email

The next hot thing in AI (is a Mac Mini)

khemaridh@substack.com1/25/2026

View Email

6 Tips to Unlock NotebookLM's superpowers

khemaridh@substack.com1/22/2026

View Email

Move over ChatGPT

khemaridh@substack.com1/18/2026

View Email

Will Claude Cowork change work forever?

khemaridh@substack.com1/15/2026

View Email

AI: The double-edged sword

khemaridh@substack.com1/11/2026

View Email

2025 AI Retrospective: The Tools, the Workflows, the Reality

khemaridh@substack.com1/8/2026

View Email

Just don't call me a "vibe coder"

khemaridh@substack.com1/4/2026

View Email

Welcome to Future-Proof Your Career with AI

khemaridh@substack.com1/3/2026

Explore all emails from Future-Proof Your Career with AI

Why your firm is struggling with AI adoption

I tried OpenAI's new "Super App"

Claude Cowork gets some competition

What milkshakes can teach us about AI

How to get your company AI-pilled

AI just got way less fun

The Ultimate AI Catch-Up Guide

Claude now multi-tasks with Excel and PowerPoint

A complete list of Claude's new features

Claude Cowork: How to use the new Projects feature

Claude is coming for your messaging apps

The Complete Guide to Claude Skills

The Rise of the AI Chief of Staff

Claude can now run scheduled tasks

The "Cursor Moment" for Finance

I paid my daughter $7 to learn Claude

Another viral doomsday post?

Stop using AI like it's 2025

The $1 Trillion SaaS Reckoning

Have we reached PowerPoint AGI?

This AI blog post broke the Internet

Claude Cowork for Windows is here

Will AI tear through Corporate America

How to use ClawdBot (with NO risk)

Should we be scared now?

Will Claude Eat Excel?

The next hot thing in AI (is a Mac Mini)

6 Tips to Unlock NotebookLM's superpowers

Move over ChatGPT

Will Claude Cowork change work forever?

AI: The double-edged sword

2025 AI Retrospective: The Tools, the Workflows, the Reality

Just don't call me a "vibe coder"

Welcome to Future-Proof Your Career with AI