|
Next week we're going to graduate from AI slop creator to real builder. I am going to show you how easy it is. We're going to build a To Do list tracker that really works *for you.* Why? Two reasons: One - Because I've downloaded, abandoned, and felt quietly guilty about more task apps than I can count. Todoist, Things, Notion, a legal pad, the Notes app, a whiteboard I can't see from my desk. None of them were wrong. They just weren't mine; each one was someone else's idea of how I should organize my brain. Two - Because I want to show you how easy it is to create something truly meaningful and useful that doesn't just live in a Claude app. We're going to build something that looks akin to this. You can redesign it how you like, relabel categories, change colors, but it'll operate like a to do list: add things, take things off the list, etc. The leap we're taking next week is to something you can actually interact with where you want to: your phone when you're commuting, your laptop when you're traveling and your desktop at the office. And it's easier than you think. The entire engine behind a real, live web tool is just three pieces:
A page, a place to keep data, and a login if you need one. That's the whole schematic. For my task list, that meant a page sorted into the buckets I actually live in, a star for what's urgent, and a database quietly remembering all of it. So the same list shows up whether I open it on my laptop at 6am or my phone in the school pickup line. No new subscription. No learning someone else's system. It just fits, because I told it to. Be aware though. This is not the all-singing-all-dancing-app that takes payments, connects to your CRM and to Bloomberg. The process is this simple right up until the tool has to reach into your other systems like pulling live numbers from your data, syncing your calendar, firing off a Slack alert. That's when you graduate to connectors. (We can do that another week if you're interested). Until then, three tools cover an astonishing amount of useful. The takeaway: the distance between "AI wrote me something" and "AI built me something I use every day" is mostly a willingness to point the same machine at a sturdier target. Next week, the build itself. I'll walk you through the exact sequence (Claude artifact to live website) using this task list. Five steps, no code, about an afternoon. For now, one question: if you stopped trying to cram your work into someone else's app, what would your list actually look like? Alex P.S. next week we go live. Bring your worst, most scattered to-do list. |
As an AI Coach, Advisor, and Agent Builder, I help organizations and business leaders harness the power of artificial intelligence to boost productivity and streamline operations. I enable organizations to navigate the transformative landscape of AI, educating teams, identifying operational and strategic opportunities with AI and creating a framework for safe and transparent use of data in the organization.
You've heard the complaints about AI slop. The generic LinkedIn posts. The Twitter threads that all sound the same. The flood of content that exists because it's now almost free to make. Everyone's pointing at the public version of this problem, the stuff strangers scroll past on their feeds. Nobody's talking about the slop we make for ourselves. Here's what I mean. The same thing that makes public AI slop so easy to produce (low effort, instant output, a little hit of delight every time) is...
Most of us ask AI to do the one thing it's worst at. We ask it to decide. "Which vendor should I pick?" "Is this a good hire?" "Should we raise prices?" And it answers instantly, confidently, in a clean paragraph. The problem is that the confident paragraph is often the shallow one. Here's how to fix that, and it takes about thirty extra seconds. First, the proof it matters. Researchers gave a top AI model a farmer's question: plant apples or grapefruit next year? The model saw that...
Yesterday a portfolio manager I work with sent me a link. "Free trial," she wrote. "Tell me what you think. Is this actually useful, or am I paying for ChatGPT in a trench coat?" She'd signed up for a new investment research platform. Pick a public company and you get a bull case, bear case, list of risks, questions for management, a multi-year financial story, earnings review, and relevant podcasts. All sourced from the standard stuff: EDGAR, earnings transcripts, proxies, podcasts. Her...