AI in Action with Tal Swicegood

Built on Rented Land

Tal Swicegood — Sun, 28 Jun 2026 12:47:29 -0500

This week a major AI lab put out an impressive new model and pulled it back within forty-eight hours. That, plus a vendor trying to charge a company thirty grand a year to access its own data, plus the oldest gut-check in business (what happens if you get hit by a bus?), all pointed at the same thing: ownership. The barrier to building collapsed, you can stand almost anything up in an afternoon now. But the gold rush has everybody building fast on rented land: rented models that can be pulled, rented platforms that change the rules, rented access to your own data, whole operations sitting on one person's personal account. It all feels like ownership until the lease is up. In this one I confess to doing the exact thing I warn clients about, make the case for the slower, unglamorous move of building where the client actually owns it, and close on the difference between a house built on sand and a house built on rock, and what I actually want to hand my kids. AI in Action with Tal Swicegood is an honest take on what AI is really doing in real businesses. Find what I'm building at lvluplocal.com.

Write It Down Once

Tal Swicegood — Sun, 14 Jun 2026 19:36:00 -0500

Everyone's teaching AI skills this month. Tal demos four he built in one morning, including a margin-leak finder that recovered $400K/yr from a fictional fleet company's billing data. Then he gives you the part the tutorials skip: a skill is a standard operating procedure, the hundred-year-old binder every franchise runs on. What's new is who's reading it. Write down how you do things once, fix the document every time it misses, and your clearest day becomes the floor, not the ceiling. Homework: write one skill this week, the thing you've explained three times this month. Tools and methods Tal trusts: lvluplocal.com

A Business That Remembers

Tal Swicegood — Sun, 07 Jun 2026 11:44:54 -0500

This week Tal sat in on a run of discovery calls with companies in wildly different industries — a demolition contractor, a healthcare group, a warehouse-software company — and saw the exact same problem three times in a row. Not that they lacked AI. That their company couldn't think: their information was scattered across a dozen apps that had never once spoken to each other, with AI bolted onto each silo separately. This episode is about the unglamorous fix almost nobody will do, and why that's exactly where the advantage is. In this one: - Why most companies aren't missing AI — they're renting a dozen disconnected brains - Bolting AI onto a silo just gives you a smarter silo - Build the foundation, not another shiny tool (nobody claps for plumbing) - Organizational memory: the knowledge that walks out the door when people leave - A turn toward memory, faith, and what we choose to keep and pass down Find what Tal's building and the tools he trusts at lvluplocal.com.

Creating API Keys for Anything

Tal Swicegood — Tue, 02 Jun 2026 08:32:29 -0500

This is a practical AI-operator episode about API access when the official path is slow, blocked, or just plain weird. Tal walks through the difference between an official API key, a browser network capture/HAR workflow, and full browser automation — including why the first is preferred, why the second can save a project, and why the third is brittle enough to treat carefully. - Why every web app has an API, even if the vendor does not expose it cleanly - How browser network captures and HAR files can give an agent enough context to build a workaround - Why official API access is still more durable when you can get it - Browser automation as the last resort: powerful, fragile, and riskier Find the tools and methods Tal trusts at lvluplocal.com.

The Machine Has No Taste

Tal Swicegood — Fri, 29 May 2026 16:19:00 -0500

The cost of making things — posts, blogs, images, video — has fallen to basically zero. Tal argues that's a trap, not a finish line: when anyone can flood every channel for free, the only thing standing between you and forgettable noise is taste. Built around a live agent demo from this week, this episode makes the case that judgment — knowing what's good, and having the spine to say what not to make — is the one thing AI can't hand you, and the most valuable thing you own. - Why a following is not a business, and volume was never the point - Taste as "the no": mostly knowing what not to make - The hype to walk away from — the content firehose that skips the judgment - Where taste actually comes from, and what AI should give you back Find what Tal's building and the tools he trusts at lvluplocal.com.

Three Commands and an Opinion

Tal Swicegood — Sun, 24 May 2026 09:34:27 -0500

This week Tal spent ninety minutes on a call showing business operators that the terminal — the scary black-and-white window people have been afraid of for ten years — is basically three commands. But the bigger story isn't the terminal. It's what happens once the technical barrier collapses: the people who pull away aren't the smartest, they're the clearest. AI as a mirror, why "boring and reliable" is the winning posture, and the real reason any of this matters — getting your evenings back, on purpose. In this episode: - Three commands and an entire decade of fear, gone - The marketing-agency frame that's already twelve months out of date - The honest messy parts: tools break, even close colleagues need things packaged for them - AI as a mirror — it rewards clarity, exposes fuzziness - Why the boring reliable thing wins, in lobbying and in AI - Compressing the work so it pays out at the campsite, not on Saturday at the laptop

Everything Just Changed

Tal Swicegood — Wed, 20 May 2026 08:00:00 -0500

Tal spent part of his career building websites for a living. This week he watched that work compress into a single hour — and what struck him was not loss, it was how many people will see it and do nothing. An honest take on the real cost of waiting, why AI rewards clear thinking over technical skill, and the part of all this that has nothing to do with business at all. In this episode: - Why 'my competitors are not tech-savvy' is a story people tell themselves - The hidden, compounding cost of 'I will get to it someday' - AI as a mirror — it rewards clarity and exposes fuzzy thinking - Substance over hype, and getting your evenings back