Architecture

1. A product prototype that carries its decisions

   A wedding product proposal became a public walkthrough, an interactive fictional prototype, and a planning handoff that carries the product decisions without exposing the original conversation.

   Oct 10, 20266 min read

2. The Guardrail Removed the Storefront

   A safe AI storefront cannot give the model a blank canvas. It also cannot remove the model and still claim that inference changes the shopping experience.

   Aug 13, 20269 min read

3. The Cut You'll Make Twice

   A written rule is not a control until the system has a place to enforce it and a failure record that proves what happened.

   Aug 6, 20266 min read

4. Please Only Apply If You're an AI Agent

   Firecrawl posted a job only a machine could apply for. Months later, on a different stage, an engineer said the mirror-image thing: don't build me an agent, build my agent a way in. Same shift, two ends of the same transaction — and an economics paper that almost, but doesn't quite, tie them together.

   Jul 14, 20269 min read

5. The Migration That Ate Two Columns

   I rebuilt a database table and it silently deleted two columns I needed. No error. Every test for the thing I was changing passed. Here's what actually caught it.

   Jun 16, 20264 min read

6. The Gate Verifies the Work. It Never Looks at the Plan.

   Thirteen features shipped green. The designs were all wrong. The system made being wrong cheap—but only on one side of the work.

   Jun 16, 20265 min read

7. Where the API Stops

   I once mapped the civil war between human interfaces and machine-native ones at the scale of companies. Then I fought both sides of it in a single afternoon, in a single pipeline — and a human had to close the seam.

   Jun 15, 20269 min read

8. The A/B Test That Built the Lathe

   I pasted a two-paragraph plan into a terminal and walked away for two days. The strategy package that came back was good. Then I asked Claude to do it again from a template, without me in the feedback loop. The template version landed at 70-80% of the quality in 10-15x less time. The gap — and the loop that closed it — has a name from another century.

   May 24, 20269 min read

9. Curation Is Not Composition

   Every creative medium that got cheap hit this moment. Art, music, publishing — all flooded, all eventually rescued by a curation layer that scaled up to match the garbage. Software is in the flood now. Curation isn't going to save it, and I don't think we've noticed the reason yet.

   Apr 17, 202612 min read

10. What If the Fork Is the Problem?

    I just mapped the civil war inside every agent system. Both paths sound reasonable. But what if splitting investment across both means neither gets finished?

    Mar 1, 20268 min read

11. The Civil War Inside Every Agent

    Every agent system is fighting the same battle: learn to navigate human interfaces, or demand native ones. The industry is doing both. The question is who adapts to whom.

    Mar 1, 20267 min read

12. Two Doors for Agents

    GitHub wants agents to explore. Google wants websites to hand them a menu. Two competing philosophies for the same problem—and the one you start with will shape your migration cost when they inevitably converge.

    Feb 18, 20267 min read

13. The AI Analyst

    We're not short on people who can chat with a bot. We're starved for people who can deconstruct a business process into atomic units an AI can actually execute. That gap has a name now.

    Jan 12, 20269 min read

14. The Kitchen I'm Looking For

    I don't need more Salesmen. I need a Sushi Master, a Pitmaster, and a Molecular Gastronomist. AI lets us return to the Guild—craftspeople in their own lanes, augmenting their own mastery.

    Dec 21, 20258 min read

15. The Tragedy of the Timesheet

    What if the billable hour isn't a business model—it's a coping mechanism? A way to avoid confronting that the thing we're selling might not be scarce anymore.

    Dec 16, 20259 min read

16. The Side of Agentic Commerce We're Not Talking About

    I just finished writing a whitepaper on agentic commerce. It's solid work. But something started bothering me. There's a version of this future that looks less like 'shopping gets easier' and more like 'retail becomes a trading floor.'

    Nov 27, 202512 min read

17. The Infinite Concierge: Why Agentic Shopping Is Just Old School Merchandising on New School Rails

    Agentic shopping doesn't change why we buy. It radically changes the cost of discovery and the precision of the pitch. The game is the same. The speed of the players has changed everything.

    Nov 22, 20257 min read

18. AI Isn't a Bubble. It's Infrastructure.

    Hank Green says the AI industry is a bubble. I think we're looking at it wrong—what if AI isn't a product at all, but a foundational technology like electricity?

    Nov 9, 20257 min read

19. The 'Do More With Less' Paradox

    If AI does all the junior work, where do the senior engineers come from? I used to see this as a pipeline problem. Now I'm wondering if we're not even using a ladder anymore.

    Oct 30, 20254 min read

20. When Did I Become the Employee?

    I'm not just paying for the service anymore. I'm doing the work. And somewhere between the self-checkout and the self-install kit, I stopped noticing when 'convenience' became unpaid labor.

    Oct 29, 20255 min read

21. I Don't Trust My AI Agents, So I Build Them Cages

    Agentic software is powerful, but it needs guardrails. Im finding the most important work isn't coding, but architecting the systems that constrain the code.

    Oct 26, 20254 min read

22. From 'Get Shit Done' to 'Just Handle It'

    I used to wear 'GSD' like a badge. But somewhere along the way, I realized my old mantra was creating the exact dependency I was supposed to prevent.

    Oct 24, 20255 min read

23. How AI Is Splitting Consulting Into Architects and Parrots

    The market is flooded with slideware about agentic AI. But the people presenting those decks arent speaking from experience—they're parrots using old tools to describe a new world.

    Oct 16, 20252 min read

24. From Wearing Many Hats to Orchestrating AI Specialists

    The constant role-switching isnt a strength—it's a source of profound inefficiency. AI changes the model.

    Oct 2, 20253 min read

25. Four Questions That Expose Fake GenAI Expertise

    The gap between slick slide decks and the messy reality of building something that actually works is wider than most people realize.

    Oct 1, 20253 min read

26. From Asking AI Questions to Giving It Directives

    The shift from prompting to architecting—and why more powerful models demand a different kind of input.

    Sep 30, 20252 min read

27. Building for AI Agents Changes Everything About Your Technical Skills

    The shift isnt about learning to use AI—it's about learning to build for AI. That distinction changes everything.

    Sep 21, 20253 min read

28. What Actually Worked When I Let Multiple AI Agents Rebuild My App

    Clean specs, small tasks, a unified preamble, and ruthless guardrails. The model mattered less than the system.

    Sep 17, 20253 min read

29. After Moore's Law: Where Tech Progress Is Actually Heading

    The easy hardware wins are behind us. Progress is shifting into new territory.

    Sep 9, 20252 min read

30. Measuring the Unowned Storefront: Observability for Agent Commerce

    Everyone is busy selling shovels. But the mine moved. Agents now sell on surfaces brands do not own. The win is not a better shovel. It is eyes and throttle on those agents: traces, attribution, consent, limits.

    Aug 27, 20259 min read

31. How AI Agents Will Reshape the Web Over the Next Decade

    The shift from search-and-scroll to conversational answers isnt theoretical. It's already redistributing traffic, revenue, and power.

    Aug 22, 20254 min read

32. Why I Burned My AI-Generated App to the Ground (Again)

    You can rush with straw or sticks, but the only way to survive the wolf of drift and fragility is to build with bricks.

    Aug 17, 20252 min read

33. Why AI-Native Development Needs Building Codes

    Were in an AI development gold rush. The same historical pattern applies: unregulated innovation, followed by standards that make outputs safe and repeatable.

    Aug 12, 20253 min read

34. When Your Framework Outgrows Your Ability to Explain It

    Ive been shipping features so fast that during a call with a friend, they asked how to use the framework—and I froze. That's observability debt.

    Aug 9, 20253 min read

35. How We Caught Our AI Framework Lying to Us

    We claimed features that didn't exist. Twice. So we blocked our own framework until we could prove we weren't full of it.

    Aug 9, 20252 min read

36. When I Asked the AI to Critique Its Own Framework

    Something broke, and instead of debugging the code, I asked the system why it hadnt caught the problem itself.

    Aug 8, 20253 min read

37. Why the Storefront Is Becoming an AI-Optimized Validation Layer

    Discovery has decentralized. By the time customers reach your product page, their minds are made up—or theyre gone.

    Aug 8, 20253 min read

38. When the AI Governance Framework Didn't Catch the Violation

    The framework didnt catch the violation. A human did. Me.

    Aug 8, 20252 min read

39. I’m Not Using GenAI. I’m Building a System Around It.

    Aug 7, 20253 min read

40. The Work Before the Words

    Meta-Companion to "Living The Gap"

    Aug 4, 20252 min read

41. Living in the Gap

    I live between presence and projection — here, but already ten steps ahead. It’s a tension of slowing down, waiting for others, holding the map while walking the same road. Leadership often means pacing yourself so we can arrive together.

    Aug 4, 20254 min read

42. 🌀 The Paradox of Velocity in AI Coding

    After sprinting through two weeks of AI-coded progress—and crashing into drift, chaos, and broken trust—I reset everything. This is the story of slowing down, building real structure, and defining a repeatable AI‑Ops workflow. From vibe coding to teardown, here’s what I learned.

    Aug 3, 20258 min read

43. When Intent Becomes the Source Code

    The past two weeks of AI engineering forced a shift I didnt expect—away from writing code and toward describing systems semantically.

    Aug 2, 20252 min read

44. What My JSX-Free React App Taught Me About AI-Assisted Engineering

    I still dont really know what JSX is. But if I'm asking AI the right questions, does it matter? Is this really different from architecting systems based on principles and relying on an engineering staff to understand the nuances?

    Aug 2, 20253 min read

45. Why My React App Doesn't Use JSX

    Most React apps are JSX-first. Mine isnt. That wasn't a bold opinion—it's just where I ended up after building a real system using AI as my primary coding partner.

    Aug 2, 20254 min read

46. Why I'm Skeptical of Agentic AI (Despite Using AI Every Day)

    I use AI to code, test, document, and enforce rules. But I dont trust autonomous agents to plan and execute on their own.

    Aug 2, 20253 min read

47. The Modern JavaScript Stack Is Powerful and Painful

    I re-entered full-stack development after a decade in enterprise architecture. The modern JS stack can be productive—but its also a house of mirrors held together by duct tape and package churn.

    Aug 1, 20255 min read

48. Am I Ever Not Working?

    If your value lies in how you think, are you ever really off the clock? Lately, I’ve been chasing AI workflows at all hours—and thinking through systems even when I’m not at my keyboard. This post reflects on the cost of always being “on,” and how to protect the infrastructure: you.

    Jul 31, 20253 min read

49. When Documentation Becomes a Contract Your AI Must Follow

    A styling bug taught me the difference between docs-as-code and docs-as-contracts—and why AI development demands the latter.

    Jul 31, 20252 min read

50. Skip the API: Building a Local ChatGPT Bridge for VS Code

    Can you skip the API and wire ChatGPT directly into VS Code? Turns out, yes — with a little browser magic. This post breaks down how I thought about building a local-first bridge that replaces Kilo and avoids token costs, all powered by curiosity and a builder’s mindset.

    Jul 31, 20254 min read

51. From Copilot to Enforcer: The AI Maturity Spectrum for Developers

    Or: What happens when AI stops just helping you code — and starts holding your system accountable

    Jul 30, 20254 min read

52. Tool-and-Die Thinking for the AI Age

    How AI coding tools helped me beat the overhead wall — and build faster than I think.

    Jul 30, 20253 min read

53. Why Demo Mode Should Be a First-Class Feature

    Building a sandboxed demo environment taught me that onboarding isnt just UX—it's architecture.

    Jul 30, 20253 min read

54. Why I Built Feature Toggles Into the Bracket App

    Sometimes the feature isnt for the user. It's for the system operators—the ones who have to keep the app online when the fire starts.

    Jul 30, 20252 min read

55. When Fast Isn't Fast Enough: From AI Coding to AI Concurrency

    Theres a strange kind of bottleneck that only shows up after you've gotten fast. The only real blocker left is waiting for a model to finish one thing before starting the next.

    Jul 30, 20254 min read

56. Designing AI-Enforced Safeguards for Development

    After a few bugs slipped past my AI assistant, I redesigned the system to make safeguards automatic.

    Jul 29, 20252 min read

57. How I Made a Cache Bug Impossible to Reintroduce

    A dropdown bug became a lesson in building automated guardrails that prevent architectural drift—especially when AI is generating your components.

    Jul 29, 20253 min read

58. Building a Production App Solo in Seven Days with AI

    The key wasnt using AI to write code—it was creating a system to govern AI's behavior, output, and role in the development process.

    Jul 28, 20253 min read

59. Tokens Are Dev Hours. Waste Is a Feature, Not a Bug.

    With AI development, waste isn’t hidden in team velocity or burndown charts — it’s itemized on your invoice. That’s not a flaw. It’s a feature.

    Jul 28, 20254 min read

60. The AI Engineer Has Joined the Team. Now What?

    AI isn’t just accelerating software development — it’s reorganizing it. This post unpacks what changes when you start designing teams, tools, and processes around a human–AI hybrid model. Planning shifts. Costs shift. Roles shift. The real question is: are we ready to shift with it?

    Jul 27, 20254 min read

61. How Structured Documentation Turned My AI Into an Engineering Team

    Documentation can be more than a reference—it can be a knowledge layer that both humans and AI agents use to build.

    Jul 26, 20253 min read

62. From Fear to Flow: How Building a Tournament Manager App Taught Me to Scale with AI

    I didn’t start with a strategy. I started with fear. Here’s how a grassroots volleyball app turned into my personal AI bootcamp—and the repeatable framework I built along the way.

    Jul 25, 20255 min read

63. My AI Engineering Team

    I didn’t set out to build an AI team. I just started with ChatGPT prompts for Lovable AI. Over time, it evolved into managing a layered squad of AI tools—architects, coders, and reviewers—working together like a real dev team. This changed how I work and lead AI-assisted projects.

    Jul 23, 20253 min read

64. When You Start to Hear the Music

    What happens when AI sharpens your mind, but drifts you further from those who don’t think that way? This post explores the private cost of clarity — and the quiet grief that comes from outgrowing the resolution your old relationships were built on.

    Jul 10, 20253 min read

65. From Prompt to Pattern

    This post wraps my “Help Me Help You” arc and opens a new question: If precision makes AI more effective, does it also increase human disconnection? I’ve felt the drift. The next thread I’m pulling on is: how to stay human inside all this structure.

    Jul 2, 20253 min read

66. How I Work With AIs (And Why)

    A behind-the-scenes look at how I use GPT and Lovable together. One rewrites the prompt. One generates the code. I just define the intent — and stay out of the way. This isn’t a tech stack. It’s a new mode of working.

    Jul 2, 20254 min read

67. Prompt Strategists, Agent Orchestras, and What Comes Next

    Prompting is evolving into orchestration. One AI clarifies, another executes, a third checks the result. We’re entering an era where modular intelligence matters — and prompts become the interface between thinking systems.

    Jul 2, 20254 min read

68. How I Used One AI to Train Another: A Tactical Reset in Data Architecture and AI Tooling Strategy

    Like most devs experimenting with AI tools, I’ve found myself juggling multiple platforms, APIs, and half-understood schemas to build things faster. Sometimes it works. Other times, it works against you.

    Jun 30, 20254 min read

69. The Lost‑Phone Test for AI: Could Your Org Still Function Tomorrow?

    Dropped phone, lost life. Same test applies to corporate AI: if your copilots vanished tomorrow, would work even slow down? The “Lost-Phone Test” exposes integration gaps and makes the case for a Chief Intelligence Officer to weave tools into real workflows.

    Jun 28, 20253 min read

70. It’s Time for the CIO 2.0

    Most AI conversations start in the wrong place — with tools, not capabilities. What’s missing isn’t another pilot. It’s a new executive role: someone to steward how your organization thinks, learns, and evolves.

    Jun 27, 20253 min read

71. From Shutdown to Speedrun

    The Cost of Surviving the Age of Constant Upgrades

    Jun 25, 20255 min read

72. You’re Sending Self-Driving Cars Down Unmarked Roads

    AI doesn’t fail because it’s bad — it fails because your data lacks the infrastructure it needs to navigate. Language models don’t just search — they interpret. Most orgs haven’t built for that.

    Jun 23, 20254 min read

73. The MVP Mirage

    Most MVPs aren’t minimum or viable — they’re just premature.

    Jun 20, 20253 min read

74. Signal or Spectacle?

    Even when I’m not trying to posture, sometimes it feels like the platform does it for me. This is about the moment when sharing something honest starts to feel like a performance — and how I’m trying to stay grounded in signal, not spectacle.

    Jun 16, 20253 min read

75. Put the Camera Down

    What if you're not here to capture the moment—but to be the aperture it passes through?

    Jun 14, 20253 min read

76. The Machine Loom

    If humans are the loom, AI is the thread—fast, abundant, and increasingly tangled.

    Jun 14, 20253 min read

77. The Human Loom

    You don’t have to be the thread. Or the pattern. Just be the thing that lets it all come together.

    Jun 14, 20252 min read

78. The Spotlight Isn’t the Stage

    A shiny idea isn't strategy. This post digs into decision hygiene: the discipline of thinking beyond the spotlight, and seeing the systems, ownership, and scope your choices actually live inside.

    Jun 12, 20253 min read

79. When Meta Conversations Start to Sound Like Sermons

    I’ve been writing and thinking so much about how I think, it’s started to shape my real-life conversations — sometimes in ways that feel disconnected. When does thoughtful reflection cross the line into sermonizing? And how do we find balance between clarity and presence?

    Jun 12, 20253 min read

80. The Gift I Can’t Give Myself

    I hold up the mirror for others all the time—clients, teammates, athletes. I just can’t seem to look in it myself. This post explores what it means to help others see their potential while still wrestling with your own.

    Jun 11, 20252 min read

81. The Real Work Is Reading the Signal

    The complexity isn’t in the tech—it’s in the noise. This final post in the Commerce Drift arc explores why reading the signal is the real skill behind every good commerce strategy.

    Jun 11, 20253 min read

82. The Stranger With My Name

    I’ve heard people describe me in ways I barely recognize. At first, it felt like they were talking about someone else. But now I’m wondering—what if they’re seeing something I haven’t figured out how to see in myself?

    Jun 11, 20253 min read

83. How I Wrote “Living in the Comments”

    This post was already about self-doubt. So writing it with an AI didn’t make it easier—it made the mirror sharper.

    Jun 10, 20253 min read

84. Living in the Comments

    Sometimes I’m not writing for clarity. I’m writing to defend myself against a comment that hasn’t been written yet.

    Jun 10, 20253 min read

85. When Custom Isn’t Better: The Burden of Bespoke

    We romanticize personalization. But sometimes the problem isn’t lack of choice—it’s too much of it. Especially when we’re not sure what we really want.

    Jun 10, 20253 min read

86. Is Composable Just IKEA for Commerce?

    Composable promised freedom from the monolith. But in chasing modular flexibility, are we just assembling the same storefront with different colors and calling it strategy?

    Jun 9, 20254 min read

87. The Cost of Sophistication

    Getting sharper comes at a cost. The more refined your thinking becomes, the more you risk drifting into isolation. This post explores the hidden tax of clarity—and what it means to stay reachable without dumbing yourself down.

    Jun 9, 20253 min read

88. Writing Helped Me Notice I Was Seeing Differently

    I didn’t set out to write about personal growth. I just wanted to get clearer. But writing about other things helped me finally put into words a shift I’ve been feeling for years—that sometimes growth changes how you see the world before you even realize it.

    Jun 8, 20252 min read

89. Sharpened Doesn’t Mean Sterile

    As your work gets more refined, it risks losing the texture that made it real. But if you do it right, refinement doesn’t erase your voice—it reveals it.

    Jun 7, 20253 min read

90. Do I Still Sound Like Me?

    Your writing gets sharper. Your thinking gets clearer. Your tone gets cleaner. But somewhere along the way, you wonder if the people who liked the messy version of you still recognize the voice.

    Jun 7, 20253 min read

91. If the Storefront Is Dead, Where Do You Compete Now?

    If customers don’t convert on your site, where do they decide? Trust now starts upstream—off-site, in content, and with zero friction.

    Jun 6, 20252 min read

92. Why This Made You Ask

    When I started this blog, someone close to me asked, “What are you doing with this?” Not my photography. Not my DJ mixes. Just this. I’ve been thinking about why.

    Jun 6, 20252 min read

93. What Coaching Teaches Me About Consulting

    Coaching club volleyball taught me more about leadership than any workshop ever could. From managing expectations to building trust, this post breaks down the surprising overlaps between the gym and the boardroom.

    Jun 4, 20253 min read

94. Grid-Level Thinking Wasn't the Plan

    This wasn’t meant to be a thought leadership series. It started as a phone call—and a question: Where does AI actually help, right now, for real? I’m Not Hyping AI. I’m Just Using It.

    Jun 4, 20252 min read

95. Power Without Purpose Is Just a Bill.

    Post 4 of 4 in the Grid-Level Thinking series—why using AI for real work has changed how I design systems, think about leverage, and clarify what actually matters.

    Jun 4, 20253 min read

96. Plug In. Then Rethink the System.

    Post 3 of 4 in the Grid-Level Thinking series—adopting AI isn’t the hard part. Redesigning your system around it is.

    Jun 4, 20252 min read

97. Wired for Power: Everyone Got the Current. Not Everyone Built the City.

    Post 2 of 4 in the Grid-Level Thinking series—access isn’t the differentiator anymore. Application is.

    Jun 4, 20251 min read

98. Wired for Power: AI Is the Grid. You’re the Architect.

    Post 1 of 4 in the Grid-Level Thinking series—what we miss when we treat AI like magic instead of infrastructure.

    Jun 4, 20252 min read

99. The Entry-Level Developer: Evolution, Not Extinction

    The junior dev role isn’t dying. It’s evolving. The job is no longer about churning out syntax—it’s about navigating ambiguity, thinking critically, and collaborating with AI. Here’s what still matters, and how to coach for it.

    Jun 4, 20252 min read

100. How I Built Signal Reflex in a Week

     This blog isn’t a new habit—it’s just a new slice of my output. Here’s how I launched Signal Reflex in a week by treating it like any other creative drop: strategy, tools, publishing cadence, and what I learned by shipping.

     Jun 4, 20253 min read

101. The Storefront Is Dead

     Most customers already know what they want. They’re not browsing. The storefront isn’t where you win anymore—it’s just where you fulfill.

     Jun 2, 20252 min read

Looking beyond essays? Search all writing