Two years into a job I couldn't find my own files. Shortcuts everywhere, untitled documents I'd meant to throw away and never did, and no appetite for fixing any of it by hand. So I asked Gemini to build me a script that would sort it out, with two rules: don't rename anything, and don't delete anything. The folder I was dreading, the one where everything ambiguous would pile up, ended up with about twenty files in it.

A brainstorm about monetizing this blog turned into a realization that I'd never once opened the SEO panel on any of it. So I connected Claude to my Wix site and let it read what was actually there. What followed was fifteen posts fixed, an SEO education I never sat down for, and one moment where I checked the work and found every description had been wiped. The part I keep thinking about isn't the fix. It's that I learned the whole thing while doing it, which is why any of i

Someone asked a question in a company Slack channel that wasn't addressed to me, and it sent me off to Perplexity asking what I could actually do about the environmental cost of using AI constantly. I made a few changes that week and forgot about it. Eleven months later I went back and checked which ones survived, and found that the habit I'd dropped was the wrong one, the habit I kept religiously does nothing at all, and the two changes that genuinely mattered were ones I'd

I've watched the same AI training get built more than once now, in more than one place. The content is usually fine. People walk out able to tell you the difference between a vague prompt and a specific one, and then nothing changes on Tuesday. What people are missing isn't knowledge. Here's what actually moved people, and why one slide did more than a full curriculum.

There was a conversation I needed to have with another program manager, and I kept not having it. He didn't report to me, he was good at the job, and I didn't want to spend the working relationship badly. So I practiced it first, against a Gem built to play him. It pushed back the way he pushes back, told me exactly where I was hedging, and by the time I sat down with the real person, nothing in it was a surprise. Full prompt at the bottom of the post.

Last week's post was about how it felt. This one is about what's actually running underneath it: two scheduled tasks, no code, and the specific guardrails that kept it from falling apart the first two weeks. If you want to build something like this yourself, this is the version with the actual mechanics.

I started a new job about a month ago and braced for the usual rebuild, recreating every script and process I'd relied on before. Instead, I connected a few tools on day one. By week two, someone said a name I didn't recognize, and I already had a profile on them. This is what changed when the context showed up before I did.

There was one person I just wasn't clicking with, and I couldn't say why. So I did something a little embarrassing: I had AI build a communication profile of me, then one of them, then compared the two side by side. What came back wasn't dramatic. It was just true, and I hadn't sat with it before. Includes the exact prompt I use to build a stakeholder profile from meeting transcripts.

I'd made fifteen AI use case videos with no script format, just whatever felt right that day. I transcribed all of them, fed them to NotebookLM, and asked if there was a pattern I couldn't see. There was. Six parts, and I'd been using them the whole time without knowing it.

I built this from an actual presentation to a team that didn't know where to start with AI, then found myself using the same idea to teach my eighty-something relative about cryptocurrency. Four specific habits, nothing about better tools or more time, just moving AI earlier in what you're already doing. Pick one and see what happens.

I used to send my status report after one AI pass and my own read-through. Now five personas argue about it first, the business partner, the executive, the chief of staff, and two more, each built around someone who actually reads the thing. This isn't really about status reports. It's a structure you can point at any output you produce.

AI tools want to answer. That's their default. But one extra line at the end of any prompt forces a pause that changes what comes back — and sometimes surfaces a question you hadn't even thought to ask yourself. Here's what happens in that pause, and why it's often the most useful part of the whole exchange.

Most people use meeting transcripts to capture what was said. That's not the same as understanding who said it — and why. Here's how I started using transcripts as behavioral data, and what changed when I did.

I built a Gem in twenty minutes to handle a framing problem I'd been fighting for months. That part worked. What I didn't expect was what happened when I started giving it stakeholder feedback — and asking it to improve its own instructions.

I sat down to update my resume thinking I knew what I'd accomplished. Months of daily journal entries told me otherwise — not by surfacing things I'd forgotten, but by showing me things I was actively doing that I'd never thought to claim. Turns out the gap between what you do and what you say you do is wider than you think. And it has nothing to do with memory.

I had 387 items of feedback and a process I'd trusted for years. Then AI did the same job — and the uncomfortable part wasn't the time it saved. It was the question I couldn't stop turning over afterward.

My phone was 96% full and I was leaving for vacation in a few days. The reason I couldn't clear it was an external hard drive I'd been avoiding for years — 25 years of photos, buried in backups of backups, scattered across 30-plus folders. I gave myself the weekend and let AI do the heavy lifting. It recovered 2,101 photos I didn't know I had — including the full Morocco trip I thought was only 304 photos. The number that mattered most: zero deletions.

The AI features you're not using are already open on your screen. Slack AI finds what you can't. Zoom AI Companion catches you up when you join a meeting late. Google Drive tells you exactly what changed while you were gone. You don't need new tools - you need to know what your current ones can already do.

I used to check slides the hard way - clicking every object, eyeballing every font, hoping I'd catch what my eyes kept missing. Then I wrote a script to do it for me. My first reaction was: oh shit, that actually worked. What happened after I ran it four more times is the part nobody talks about.

I'm not a developer. I don't know how to write code. I've never taken a programming class. And yet I've built automated tools that saved me hours every week — by doing exactly one thing: describing the problem to an AI and letting it build the solution.