In Part I of the series, we talked about what vibe coding is and how to figure out what you’d build (and if you should build something. Today in Part II, we’re talking about how tools, prices, and signup flows change fast and to treat the specific how-tos as current-as-of-writing and the reasoning as durable. I run a Linux server and have forgotten I ever didn’t know how. My friend Andrew Winston built and shipped Context Coach as a genuine non-engineer, recently enough to remember every place he got stuck. So we wrote this part together — my structure, his fresh scars, and his real setup list at the end as the worked example. It’s more useful than either of…
Category
AI
Vibe Coding for People Who Can’t Code: A five-part series. Part I — What it is, why you’d bother, and what you’d build
I last wrote code in 1980 on a TRS-80 or a Commodore 64, I forget which, but alas it doesn’t matter! Over the last two months I built three pieces of software. One of them has over 40,000 lines of code that I’ve never seen. The point of this series isn’t for you to build these. They’re mine; they fit my life; yours will be different. They’re here as worked examples — what each cost, what it taught, and what I got wrong, which turns out to be the useful part. This is the longest series of posts I’ve ever written. It’s designed for the “Vibe Code Curious” — especially people in business and leadership roles — and each part…
Garbage In, Garbage Out
There’s a fundamental truth about AI that most people don’t think about enough: the transformer architecture — the engine underneath ChatGPT, Claude, Gemini, all of them — is predictive by nature. It analyzes the most likely next word and generates it. That’s extraordinary and powerful, but it also means AI isn’t thinking. It’s pattern-matching at superhuman speed. And here’s the other thing: AI models are typically trained at a point in time. They’re not updated in real time as the world changes around us. Not yet, anyway (although some are designed and some are getting better at incorporating real-time search results). What does that mean for people using AI to help them write things? Or for people building agents to…
Curated Reading on AI, Part II
In Part I, I curated a lot of big picture articles about AI and society. Today’s post will be more practical and tactical about the business of AI. First from Thomas Tunguz at Theory Ventures – The AI Problem Matrix, which does a great job of laying out a framework for where and how humans (and also AI/Software) will be able to create value in the new world and where it will be capped. Next, two interesting articles about where pricing is headed or not headed in the world of AI where everyone is waxing philosophic about “outcome based pricing,” but no one has quite figured out what that means yet for the vast majority of use cases. We certainly…
Where The Pundits Are Getting It Wrong – We Still Need Talented Software Engineers
There’s a narrative gaining steam in the AI discourse that goes something like this: coding assistants are getting so good that we won’t need software engineers anymore. Some version of “AI writes code now, so why would you hire humans to do it?” This take is wrong. Not slightly wrong — fundamentally wrong. And it’s wrong because it confuses three very different things. Writing Code, Building Products, and Building Companies Coding assistants write code. That’s a real and valuable capability. They can generate functions, debug errors, scaffold entire applications, and produce boilerplate at superhuman speed. No argument. But writing code is not the same as building a software product. And building a software product is not the same as building…
Markup AI launch – TODAY!
After months of the fastest and most thorough software development cycle I’ve seen in my career, I am proud to announce the launch of our Content Guardian Agents platform Markup AI today. Here’s the defining quote from one of our early clients, the head of content at a B2C marketer: “90% of AI content is mind-blowingly great, and 10% completely wrong — and you spend hours trying to fix the little part that annoys you.” If that resonates with you, try us out. We’re offering a free trial for at least 30 days to anyone and everyone – here is the link to sign up. Our agents provide a unified framework to give you confidence before you publish that the…
Chatting with my DNA – a fascinating personal use case and a deep rabbit hole
This one has nothing to do with running a company. But it’s one of the most fascinating things I’ve done with AI, and I fell down such a deep rabbit hole that I have to share it. My friend Chad Dickerson — former CEO of Etsy, now an executive coach — mentioned that he’d uploaded his raw DNA file to an AI and started asking it questions. My reaction was something like: wait, you can do that? You can. Here’s how. If you’ve done 23andMe (or Ancestry.com — the process is similar), you can download your raw DNA data file. It’s just a text file full of SNPs — single nucleotide polymorphisms, the genetic markers that make you you. Upload…
Don’t Start a Forest Fire to Roast a Marshmallow (literally or figuratively with AI)
My friend Andrew Winston has spent the second leg of his career the last two decades working on corporate sustainability, advising some of the largest companies in the world on how good business practices drive good business outcomes, and writing some amazing books. I posted about his first three here and here and here many years ago and oddly didn’t post about his most prominent book with Unilever CEO Paul Polman more recently. Andrew was recently named the #1 Management Thinker in the World by Thinkers50, which I didn’t even know was a thing, but now I get to tease him that he’s Public Intellectual #1. Andrew had a great idea recently for a small but powerful browser extension that…
AI Isn’t Hard. You Just Need a Cheat Sheet.
Running Markup AI — a content governance platform built on top of large language models — means I spend a lot of time talking to executives about AI, as well as friends and family who aren’t involved in the tech sector for a living. And I’ve watched the same scene play out over and over: a smart leader sits through a vendor demo, someone drops “context window” or “RAG pipeline,” and they nod along confidently while having absolutely no idea what was just said. I’ve been that person. You probably have too. Here’s the thing — the concepts aren’t complicated. The inventors just gave simple ideas intimidating names. Here’s your cheat sheet. Large Language Model (LLM) or Foundational Model or…
Fantasy Board: My Second Agent
I wrote my second agent — my Fantasy Board of Directors — inspired by Mike Collins, CEO of Alumni Ventures (I’m on Mike’s board). Mike had been experimenting with building AI personas of famous business leaders as thinking partners, and the concept stuck with me immediately. What if I could build a full board of advisors — people I’d never be able to recruit in real life — and use them to pressure-test my thinking? The idea got some great coverage in Fortune and Business Insider, so clearly it resonated. But what I didn’t share in those pieces was the detailed how — the construction instructions, the prompting approach, and the management discipline required to make it actually useful. Every…
Claude and Henry Kissinger, aka, Is This Your Best Work?
I was recently reminded of the great story about Henry Kissinger and work product quality. I can’t figure out if it’s true or apocryphal, but it doesn’t really matter. Here’s the version I found online, commonly attributed to Winston Lord, who served as Kissinger’s Special Assistant and later as Ambassador to China. Lord works for days on a report and submits it to Kissinger. Kissinger returns it with one question: “Is this the best you can do?” Lord takes it back, reworks it, resubmits. Kissinger returns it again. Same question. “Is this the best you can do?” This goes on — six, eight, maybe ten rounds. Finally, Lord brings back a draft and declares: “Damn it, yes, it’s the best…