Economic Architecture

Layer 3. If it doesn't scale economically it gets sunset regardless of technical quality. Token economics, protected costs, and denial of wallet.

Reasoning Is About to Get Better and More Expensive

Aug 8, 2026

•

4 min read

Reasoning Is About to Get Better and More Expensive

Twelve to thirteen ongoing agentic workflows across three or four agencies, and roughly $500 a month. Almost none of that is local models. It is six habits, and the first one is a configuration change.

Laws & Principles

Can You Make More Money With the Same Money?

Aug 8, 2026

•

3 min read

Can You Make More Money With the Same Money?

Small companies track the wrong things when they adopt AI. There is one number that compounds, and going from $100,000 per employee to $300,000 changes what the business is.

Economic Architecture

Forty Hours to Build What Their Vendor Never Would

Aug 8, 2026

•

4 min read

Forty Hours to Build What Their Vendor Never Would

A logistics ops team fought the build for months, out of fear. Then a feature they had never thought to ask for shipped in a week, and the manager understood what five years of stability had actually cost.

Economic Architecture

They Hired Me to Build It. I Asked What If We Don't.

Aug 8, 2026

•

3 min read

They Hired Me to Build It. I Asked What If We Don't.

Half a million dollars of budget, aimed at a category where the incumbents had raised hundreds of millions. Nobody had checked whether the thing already existed.

Economic Architecture

They Wanted to Replace Their Reps With AI. I Told Them No.

Aug 8, 2026

•

4 min read

They Wanted to Replace Their Reps With AI. I Told Them No.

One question sorts every customer interaction into the ones AI belongs in and the ones where it will cost you. The same budget, pointed at a different surface, made their customer satisfaction go up.

Economic Architecture

Your Agents Are Awake 95% of the Time for No Reason

Aug 8, 2026

•

6 min read

Your Agents Are Awake 95% of the Time for No Reason

We spent months writing reconnect logic and retry loops to keep agents alive. We were solving the wrong problem, and the right answer is queue infrastructure from the 1980s.

Laws & Principles

Aug 8, 2026

•

5 min read

The Luckiest Idiot in Business History

Timothy Dexter shipped coal to Newcastle and made money. Everyone decided he was lucky. I think we call it luck because we cannot see where the information came from, and that has a lot to do with who builds the next wave of AI companies.

Economic Architecture

Reasoning Is About to Get Better and More Expensive

Can You Make More Money With the Same Money?

Forty Hours to Build What Their Vendor Never Would

They Hired Me to Build It. I Asked What If We Don't.

They Wanted to Replace Their Reps With AI. I Told Them No.

Your Agents Are Awake 95% of the Time for No Reason

The Luckiest Idiot in Business History

Chris Knows Production AI