# Vinny Carpenter

> Engineering leadership, platform strategy, and enterprise AI — from a Fortune 100 cloud and DevOps leader who still ships code.

Vinny Carpenter is the personal site of Vinny Carpenter, a Vice President of Engineering leading Cloud, Platform & DevOps at a Fortune 100 company, with over 30 years of experience in enterprise software development, engineering leadership, and architecture. The site's operating thesis: the bottleneck is never the stack. It covers engineering leadership, the agentic SDLC, platform engineering, enterprise AI, and hands-on software building.

## Site Structure

- [Homepage](https://vinny.dev/): The thesis, current essays, curated picks, and ways into the site
- [About](https://vinny.dev/about/): Who Vinny is — bio, track record, the thesis in brief, and the ten essays to start with
- [Start Here](https://vinny.dev/start-here/): Curated reader journey for new visitors — where to start depending on role
- [Blog](https://vinny.dev/blog/): Essays on engineering leadership, the agentic SDLC, platform engineering, and enterprise AI
- [Book](https://vinny.dev/book/): The Bottleneck Is Never the Stack — Building Software and Organizations in the Agentic Era. One continuous argument for building software and organizations in the agentic era, in an expanded second edition published August 7, 2026
- [Book Workbook](https://vinny.dev/book/workbook/): Putting the Book to Work — the free facilitator workbook companion to the book. Five working modes, all twenty-four Operating Kit artifacts, and completed Harborline examples (free PDF; get it by email or download it directly)
- [Point of View](https://vinny.dev/point-of-view/): Evergreen operating thesis on technology, teams, and engineering leadership
- [Tech Radar](https://vinny.dev/radar/): Interactive radar of beliefs across engineering, AI, leadership, and industry narratives
- [Glossary](https://vinny.dev/glossary/): The AI terms the essays lean on, defined in plain language the way Vinny actually means them
- [Now](https://vinny.dev/now/): What Vinny is currently working on, reading, and learning
- [Apps](https://vinny.dev/apps/): Applications and code projects — proof the leadership perspective is grounded in shipping software
- [User Guide](https://vinny.dev/user-guide/): A lighthearted guide to working with Vinny
- [Media](https://vinny.dev/media/): Media profile and press kit — editorial focus, biographies, press assets, and editorial standards
- [Podcast](https://vinny.dev/podcast/): Never the Stack — the essays as AI-generated audio conversations (Google NotebookLM), with an RSS feed at https://vinny.dev/podcast/feed.xml
- [Speaking](https://vinny.dev/speaking/): Talks and appearances, from a 2005 BEAWorld keynote panel to PlatformCon 2023, with current talk themes and invitation guidance
- [Essay Series](https://vinny.dev/series/): Curated reading orders over the archive, one argument per series
- [Agentic SDLC Series](https://vinny.dev/series/agentic-sdlc/): Seven essays in reading order, the spine of the book: from vibe coding to specs, workflows, and the AI Operating Ledger
- [AI Ledger Series](https://vinny.dev/series/ai-economics/): Six essays that follow the money through the agent era, from the subsidy itemized to where the saved hour goes
- [Rewrites, Repriced Series](https://vinny.dev/series/rewrites-repriced/): Three essays on the rewrite taboo breaking and how enterprises should spend the first modernization dollar
- [Human Bargain Series](https://vinny.dev/series/human-bargain/): Six essays on the deal builders owe the people AI reshapes, from honest narratives to the apprenticeship pipeline
- [Agent-Ready Platform Series](https://vinny.dev/series/agent-ready-platform/): Seven essays on platform engineering after the agent arrives, from the platform's second persona to keeping the agent replaceable
- [Contact](https://vinny.dev/contact/): How to reach Vinny — notes, speaking, and advisory conversations

## Feeds & Data

- [RSS Feed](https://vinny.dev/blog/feed.xml): RSS 2.0 feed of all blog posts
- [Sitemap](https://vinny.dev/sitemap.xml): Complete sitemap of all pages
- [Full Content](https://vinny.dev/llms-full.txt): Expanded book context and full text of every published essay

## Blog Topics

The blog covers: agentic-sdlc, ai-coding, ai-economics, ai-strategy, architecture, aws, claude-code, cloud, context-spine, design, engineering-leadership, finops, formula1, future-of-work, genai, ios, learning, open-source, platform-engineering, productivity, security, side-projects, software-engineering, spec-driven-development.

## Featured Posts

- [Jev Is Not a Faster LLM](https://vinny.dev/blog/2026-10-03-jev-is-not-a-faster-llm/): TypeSafe's Jev gives up prose for typed, probabilistic decisions. The engineering work is defining those decisions, measuring their errors, and deciding when software should ask for help.
- [The Return of the Personal Agent](https://vinny.dev/blog/2026-10-01-the-return-of-the-personal-agent/): I've used five personal agents to help with the work of everyday life. A restaurant call, a changed appointment, and a playoff-ticket search show what I can hand over, what still needs my decision, and how I know the job is finished.
- [The Agent Is Not the Platform](https://vinny.dev/blog/2026-09-30-the-agent-is-not-the-platform/): Building a portable software-development workflow across Claude Code, Codex, Goose, Pi and OpenCode.
- [The Agent Is Wearing Your Badge](https://vinny.dev/blog/2026-09-28-the-agent-is-wearing-your-badge/): An agent acting with your credentials can leave a record of your authority without a record of its involvement. Platform teams need to preserve who acted, under whose authority, and how to stop that access.
- [Your Platform Is Teaching Your Engineers](https://vinny.dev/blog/2026-09-22-your-platform-is-teaching-your-engineers/): Every default, error message, and exception communicates how work gets done. The question is whether that's the lesson you intended.
- [Omarchy: Linux Finally Reached My Desk](https://vinny.dev/blog/2026-09-18-omarchy-linux-finally-reached-my-desk/): Omarchy installed on a drawer laptop in two minutes and everything worked. The reason is a platform lesson: choose the defaults, keep the escape hatches, and make the system legible to the agent.
- [Bootleggers, Baptists, and the Case for Slowing Down AI](https://vinny.dev/blog/2026-09-14-bootleggers-baptists-and-the-case-for-slowing-down-ai/): The frontier labs are asking to slow down, and I think most of them mean it. Bruce Yandle's 1983 theory explains why sincerity isn't the question that matters. The question is who can afford the rules that follow.
- [Your Agent Workflow Needs a Release Process](https://vinny.dev/blog/2026-09-13-your-agent-workflow-needs-a-release-process/): Kiro's frontier engineering principles describe how to work well with agents. Making that practice dependable across a team means treating the shared workflow as a software release, with a version, a scope, an owner, and tests for when it should stop.
- [Worse Is Better, but Simple for Whom?](https://vinny.dev/blog/2026-09-09-worse-is-better-but-simple-for-whom/): Coding agents can reduce implementation effort without reducing every obligation that follows. Revisiting Richard Gabriel's argument raises a different question: which design is simplest to verify, use, change, and operate, and for whom?
- [The Developer Experience Ledger](https://vinny.dev/blog/2026-09-07-the-developer-experience-ledger/): An AI tool can save a developer an hour while the delivery journey consumes most of the saving. The developer experience ledger follows the work across that boundary, so platform teams can tell what they removed and what they merely moved.
- [From Faster Code to Better Engineering](https://vinny.dev/blog/2026-09-05-from-faster-code-to-better-engineering/): Sixteen months of building and writing taught me that AI makes implementation cheaper while raising the value of clear intent, trustworthy platforms, operational understanding, and human judgment.
- [The Best AI Developer Experience Might Be Invisible](https://vinny.dev/blog/2026-09-01-the-best-ai-developer-experience-might-be-invisible/): The obvious version of AI developer experience is a chatbot in the portal. The better version diagnoses the failure, repairs what the platform owns, and reruns to green before the developer opens the log.
- [Everyone Is Commoditizing Someone: Battle of the LLMs](https://vinny.dev/blog/2026-08-28-everyone-is-commoditizing-someone/): Open weights and closed models are moves in a fight over where margin survives. For enterprise teams, the durable assets are the evaluations, context, tool contracts, and audit evidence that keep model providers replaceable.
- [Nobody Pages the Agent](https://vinny.dev/blog/2026-08-24-nobody-pages-the-agent/): A gate proves a standard ran. It does not prove anyone can operate the result at 3 a.m. Operability has to become part of the spec, and the evidence has to survive the merge.
- [My Mac Ran Out of Headroom, So I Built Some](https://vinny.dev/blog/2026-08-23-my-mac-ran-out-of-headroom/): A runaway collection of agents, local models, and browser processes pushed my Mac past the point where Activity Monitor was useful. So I built System Headroom, and Apple's sandbox ended up shaping the product more than I expected.
- [The Golden Path Needs an Intent Interface](https://vinny.dev/blog/2026-08-20-the-golden-path-needs-an-intent-interface/): The golden path made the right way easier to follow. It still asks developers to learn the road. With AI, intent can become the interface while the platform keeps the standards, the controls, and the gate.
- [Context Is a Platform Capability Now](https://vinny.dev/blog/2026-08-15-context-is-a-platform-capability-now/): We treat enterprise context as something developers gather before they can use AI well. Platform teams should treat trusted context as something the platform provides.
- [Your Platform Has a New User: The Agent](https://vinny.dev/blog/2026-08-13-your-platform-has-a-new-user-the-agent/): We built internal platforms for developers. Those developers now arrive with an AI agent beside them, and how well your platform serves that second user is becoming the real maturity test.
- [The Accidental Podcast](https://vinny.dev/blog/2026-08-11-the-accidental-podcast/): I automated audio versions of my essays, looked away for four months, and found a 22-episode back catalog. Meet Never the Stack, the podcast I never meant to start.
- [Where the Saved Hour Goes](https://vinny.dev/blog/2026-08-09-where-the-saved-hour-goes/): AI can create a real time dividend for engineers, and history says unallocated capacity gets absorbed before anyone notices. The case for deciding where the saved hour goes.
- [The Frontier on Your Laptop](https://vinny.dev/blog/2026-08-04-the-frontier-on-your-laptop/): Open-weight models have raised the local capability floor while hosted intelligence keeps getting cheaper. The strategic question is no longer which side wins, but which model earns each workload.
- [Don't Automate the Apprenticeship Out of Engineering](https://vinny.dev/blog/2026-08-03-dont-automate-the-apprenticeship/): Entry-level work was never just cheap execution. It was the training system that produced the people capable of judging what the machines build.
- [The Modernization Backlog Just Got Repriced](https://vinny.dev/blog/2026-08-01-modernization-backlog-repriced/): The rewrite taboo broke for systems that can grade their own replacement. At enterprise scale, the first modernization dollar should fund the answer key, not the port.
- [The More AI We Have, the More Human Judgment Matters](https://vinny.dev/blog/2026-07-26-the-more-ai-we-have/): AI is making execution abundant. As intelligence becomes cheaper and more accessible, durable organizational advantage shifts toward judgment, context, verification, and leadership.
- [Everyone Knows You Never Rewrite](https://vinny.dev/blog/2026-07-17-everyone-knows-you-never-rewrite/): For twenty-six years, the full rewrite was the cardinal sin of software engineering. Then one engineer ported half a million lines of Bun from Zig to Rust in eleven days. The taboo was never about code. It was a price tag, and for systems whose intent lives in an executable oracle, the price just collapsed.
- [Paying for Intelligence Twice](https://vinny.dev/blog/2026-07-13-paying-for-intelligence-twice/): Satya Nadella named a real problem: AI workflows generate valuable learning exhaust from proprietary context and corrections. He is right about the asset. My practitioner's edit is simple: own the learning loop, not necessarily the model.
- [Two Gates and a Night Shift](https://vinny.dev/blog/2026-07-06-two-gates-and-a-night-shift/): My personal delivery pipeline runs on three Claude agents, three nested loops, and two explicit human approval gates. The gates sit where judgment is cheapest and most consequential, and the real bottleneck moved upstream to the clarity of the ask.
- [The Instrument and the Ledger](https://vinny.dev/blog/2026-07-04-the-instrument-and-the-ledger/): In June I itemized the AI subsidy by hand. This month I built the instrument that does it for me. It took an afternoon, and it was built by the very thing it measures.
- [Barometer: I Chased a New Primitive. I Was Standing on It.](https://vinny.dev/blog/2026-07-01-barometer-internet-weather-station/): I built a serverless internet health monitor because I wanted an excuse to learn Lambda MicroVMs. The better lesson was that Barometer did not need the newest primitive. It needed the boring, correct fit between the tool and the job.
- [Work Is Hard Enough](https://vinny.dev/blog/2026-06-28-work-is-hard-enough/): Work is already hard. Leadership should remove the avoidable human drag: unclear decisions, unsafe disagreement, personal friction, and cultures where telling the truth costs too much.
- [Still in the Code](https://vinny.dev/blog/2026-06-26-still-in-the-code/): I lead engineering at a Fortune 100 company, and I still ship my own software. Not because leaders need to prove they can code, but because AI is changing the work faster than secondhand models can keep up.
- [Complexity Is Inevitable. Drag Is Optional.](https://vinny.dev/blog/2026-06-22-turning-complexity-into-leverage/): Complexity is inevitable in modern engineering. Drag is optional. The work of leadership is turning repeated friction into platforms, defaults, and systems that help teams move faster with trust intact.
- [Native Was the Long Way Around. The Stack Wasn't the Point.](https://vinny.dev/blog/2026-06-18-native-was-the-long-way-around/): I rebuilt a working web app as native iOS and Mac software, not because native was magic, but because the discipline required to make it correct is the same discipline AI agents need to be useful.
- [The Subsidy, Itemized](https://vinny.dev/blog/2026-06-15-the-subsidy-itemized/): Twenty-six days of Claude Code showed $2,556 of API-priced work against a $200 subscription. The lesson was not the total. It was cache behavior, model routing, and a government kill switch that landed in my usage chart. Value lives in verified outcomes, not tokens, and the work has to survive the stop.
- [The Kill Switch Was Always There](https://vinny.dev/blog/2026-06-13-the-kill-switch-was-always-there/): A government order took Anthropic's Fable 5 and Mythos 5 offline. The lesson for enterprise AI is architecture: portability gets you out, verification gets you out safely.
- [The Agent Era Gets an Invoice](https://vinny.dev/blog/2026-06-11-the-agent-era-gets-an-invoice/): Build, WWDC, two confidential S-1 filings, and a tiered frontier model launch hit in the same two weeks. The agent became the interface just as the invoice arrived.
- [The AI Operating Ledger](https://vinny.dev/blog/2026-06-08-the-ai-operating-ledger/): Enterprise AI is entering its accounting phase. The winners will measure verified outcomes, not just tokens, subscriptions, or generated output.
- [Workflow.ts: When the Code Runs the Agent, Not the Other Way Around](https://vinny.dev/blog/2026-05-26-context-spine-workflow-js/): Agent loops let the model pick the next step. Workflows invert that. Code owns the control flow; the model owns the judgment inside each step. Here is the TypeScript file I am running today, type-checked against the live SDK, and the honest answer to whether you should build this now or wait for the official tool.
- [The Frame Is the Bottleneck](https://vinny.dev/blog/2026-05-24-the-frame-is-the-bottleneck/): My thesis is that as agents get better at execution, the primary constraint for organizations shifts from technical production to the human-led framing of problems.
- [The Bottleneck Is Never the Stack](https://vinny.dev/blog/2026-05-13-the-bottleneck-is-never-the-stack/): A year of writing, one argument, and a working theory of where software is going
- [The Spec Is the Product](https://vinny.dev/blog/2026-05-12-the-spec-is-the-product/): Code used to be the durable asset. In an agentic SDLC, that changes. Code becomes the regeneratable output of a system that runs on something more important: a clear, versioned, reviewable specification. That shift changes what engineering organizations invest in, how they govern delivery, who they hire, and what they actually ship.
- [Building Cloud From Zero: Five Decisions That Compounded and Three I’d Redo](https://vinny.dev/blog/2026-05-08-building-cloud-from-zero/): After two greenfield cloud builds in financial services, these are the decisions that aged well, the ones I would redo, and why the small choices in year one decide whether you have a platform or a pile in year five.
- [Spec, Standards, Specialists: How I Actually Build with AI](https://vinny.dev/blog/2026-04-30-spec-standards-specialists-final/): The strategy posts say AI software development is a system. Here is the working loop I run inside that system: a refined specification, a layer of standards, and a coordinated set of specialists doing the work.
- [The Agentic SDLC: Uniting the AI Tool Sprawl](https://vinny.dev/blog/2026-04-15-agentic-sdlc-uniting-ai-tool-sprawl/): Every tool in your product development life cycle is now an AI agent trying to do everything. Here is how to stop the chaos, draw the right boundaries, and build an orchestrated pipeline that actually works.
- [Pipeline-First Is Not a DevOps Initiative - It's a Culture Shift.](https://vinny.dev/blog/2026-03-26-pipeline-first-culture-shift/): Everyone sells pipeline-first delivery as a best practice. Remove access. Route through automation. Enforce consistency. What the slide deck leaves out is the part that actually determines whether this works.
- [Strip the Assumptions: What Enterprise AI Adoption Actually Is](https://vinny.dev/blog/2026-03-22-strip-the-assumptions-enterprise-ai/): Most enterprise conversations about GenAI are arguments about assumptions nobody has questioned. Here is what stays when you strip everything else away.

## All Blog Posts

- [Jev Is Not a Faster LLM](https://vinny.dev/blog/2026-10-03-jev-is-not-a-faster-llm/): TypeSafe's Jev gives up prose for typed, probabilistic decisions. The engineering work is defining those decisions, measuring their errors, and deciding when software should ask for help.
- [The Return of the Personal Agent](https://vinny.dev/blog/2026-10-01-the-return-of-the-personal-agent/): I've used five personal agents to help with the work of everyday life. A restaurant call, a changed appointment, and a playoff-ticket search show what I can hand over, what still needs my decision, and how I know the job is finished.
- [The Agent Is Not the Platform](https://vinny.dev/blog/2026-09-30-the-agent-is-not-the-platform/): Building a portable software-development workflow across Claude Code, Codex, Goose, Pi and OpenCode.
- [The Agent Is Wearing Your Badge](https://vinny.dev/blog/2026-09-28-the-agent-is-wearing-your-badge/): An agent acting with your credentials can leave a record of your authority without a record of its involvement. Platform teams need to preserve who acted, under whose authority, and how to stop that access.
- [Your Platform Is Teaching Your Engineers](https://vinny.dev/blog/2026-09-22-your-platform-is-teaching-your-engineers/): Every default, error message, and exception communicates how work gets done. The question is whether that's the lesson you intended.
- [Omarchy: Linux Finally Reached My Desk](https://vinny.dev/blog/2026-09-18-omarchy-linux-finally-reached-my-desk/): Omarchy installed on a drawer laptop in two minutes and everything worked. The reason is a platform lesson: choose the defaults, keep the escape hatches, and make the system legible to the agent.
- [Bootleggers, Baptists, and the Case for Slowing Down AI](https://vinny.dev/blog/2026-09-14-bootleggers-baptists-and-the-case-for-slowing-down-ai/): The frontier labs are asking to slow down, and I think most of them mean it. Bruce Yandle's 1983 theory explains why sincerity isn't the question that matters. The question is who can afford the rules that follow.
- [Your Agent Workflow Needs a Release Process](https://vinny.dev/blog/2026-09-13-your-agent-workflow-needs-a-release-process/): Kiro's frontier engineering principles describe how to work well with agents. Making that practice dependable across a team means treating the shared workflow as a software release, with a version, a scope, an owner, and tests for when it should stop.
- [Worse Is Better, but Simple for Whom?](https://vinny.dev/blog/2026-09-09-worse-is-better-but-simple-for-whom/): Coding agents can reduce implementation effort without reducing every obligation that follows. Revisiting Richard Gabriel's argument raises a different question: which design is simplest to verify, use, change, and operate, and for whom?
- [The Developer Experience Ledger](https://vinny.dev/blog/2026-09-07-the-developer-experience-ledger/): An AI tool can save a developer an hour while the delivery journey consumes most of the saving. The developer experience ledger follows the work across that boundary, so platform teams can tell what they removed and what they merely moved.
- [From Faster Code to Better Engineering](https://vinny.dev/blog/2026-09-05-from-faster-code-to-better-engineering/): Sixteen months of building and writing taught me that AI makes implementation cheaper while raising the value of clear intent, trustworthy platforms, operational understanding, and human judgment.
- [The Best AI Developer Experience Might Be Invisible](https://vinny.dev/blog/2026-09-01-the-best-ai-developer-experience-might-be-invisible/): The obvious version of AI developer experience is a chatbot in the portal. The better version diagnoses the failure, repairs what the platform owns, and reruns to green before the developer opens the log.
- [Everyone Is Commoditizing Someone: Battle of the LLMs](https://vinny.dev/blog/2026-08-28-everyone-is-commoditizing-someone/): Open weights and closed models are moves in a fight over where margin survives. For enterprise teams, the durable assets are the evaluations, context, tool contracts, and audit evidence that keep model providers replaceable.
- [Nobody Pages the Agent](https://vinny.dev/blog/2026-08-24-nobody-pages-the-agent/): A gate proves a standard ran. It does not prove anyone can operate the result at 3 a.m. Operability has to become part of the spec, and the evidence has to survive the merge.
- [My Mac Ran Out of Headroom, So I Built Some](https://vinny.dev/blog/2026-08-23-my-mac-ran-out-of-headroom/): A runaway collection of agents, local models, and browser processes pushed my Mac past the point where Activity Monitor was useful. So I built System Headroom, and Apple's sandbox ended up shaping the product more than I expected.
- [The Golden Path Needs an Intent Interface](https://vinny.dev/blog/2026-08-20-the-golden-path-needs-an-intent-interface/): The golden path made the right way easier to follow. It still asks developers to learn the road. With AI, intent can become the interface while the platform keeps the standards, the controls, and the gate.
- [Context Is a Platform Capability Now](https://vinny.dev/blog/2026-08-15-context-is-a-platform-capability-now/): We treat enterprise context as something developers gather before they can use AI well. Platform teams should treat trusted context as something the platform provides.
- [Your Platform Has a New User: The Agent](https://vinny.dev/blog/2026-08-13-your-platform-has-a-new-user-the-agent/): We built internal platforms for developers. Those developers now arrive with an AI agent beside them, and how well your platform serves that second user is becoming the real maturity test.
- [The Accidental Podcast](https://vinny.dev/blog/2026-08-11-the-accidental-podcast/): I automated audio versions of my essays, looked away for four months, and found a 22-episode back catalog. Meet Never the Stack, the podcast I never meant to start.
- [Where the Saved Hour Goes](https://vinny.dev/blog/2026-08-09-where-the-saved-hour-goes/): AI can create a real time dividend for engineers, and history says unallocated capacity gets absorbed before anyone notices. The case for deciding where the saved hour goes.
- [The Frontier on Your Laptop](https://vinny.dev/blog/2026-08-04-the-frontier-on-your-laptop/): Open-weight models have raised the local capability floor while hosted intelligence keeps getting cheaper. The strategic question is no longer which side wins, but which model earns each workload.
- [Don't Automate the Apprenticeship Out of Engineering](https://vinny.dev/blog/2026-08-03-dont-automate-the-apprenticeship/): Entry-level work was never just cheap execution. It was the training system that produced the people capable of judging what the machines build.
- [The Modernization Backlog Just Got Repriced](https://vinny.dev/blog/2026-08-01-modernization-backlog-repriced/): The rewrite taboo broke for systems that can grade their own replacement. At enterprise scale, the first modernization dollar should fund the answer key, not the port.
- [The More AI We Have, the More Human Judgment Matters](https://vinny.dev/blog/2026-07-26-the-more-ai-we-have/): AI is making execution abundant. As intelligence becomes cheaper and more accessible, durable organizational advantage shifts toward judgment, context, verification, and leadership.
- [Everyone Knows You Never Rewrite](https://vinny.dev/blog/2026-07-17-everyone-knows-you-never-rewrite/): For twenty-six years, the full rewrite was the cardinal sin of software engineering. Then one engineer ported half a million lines of Bun from Zig to Rust in eleven days. The taboo was never about code. It was a price tag, and for systems whose intent lives in an executable oracle, the price just collapsed.
- [Paying for Intelligence Twice](https://vinny.dev/blog/2026-07-13-paying-for-intelligence-twice/): Satya Nadella named a real problem: AI workflows generate valuable learning exhaust from proprietary context and corrections. He is right about the asset. My practitioner's edit is simple: own the learning loop, not necessarily the model.
- [Two Gates and a Night Shift](https://vinny.dev/blog/2026-07-06-two-gates-and-a-night-shift/): My personal delivery pipeline runs on three Claude agents, three nested loops, and two explicit human approval gates. The gates sit where judgment is cheapest and most consequential, and the real bottleneck moved upstream to the clarity of the ask.
- [The Instrument and the Ledger](https://vinny.dev/blog/2026-07-04-the-instrument-and-the-ledger/): In June I itemized the AI subsidy by hand. This month I built the instrument that does it for me. It took an afternoon, and it was built by the very thing it measures.
- [Barometer: I Chased a New Primitive. I Was Standing on It.](https://vinny.dev/blog/2026-07-01-barometer-internet-weather-station/): I built a serverless internet health monitor because I wanted an excuse to learn Lambda MicroVMs. The better lesson was that Barometer did not need the newest primitive. It needed the boring, correct fit between the tool and the job.
- [Work Is Hard Enough](https://vinny.dev/blog/2026-06-28-work-is-hard-enough/): Work is already hard. Leadership should remove the avoidable human drag: unclear decisions, unsafe disagreement, personal friction, and cultures where telling the truth costs too much.
- [Still in the Code](https://vinny.dev/blog/2026-06-26-still-in-the-code/): I lead engineering at a Fortune 100 company, and I still ship my own software. Not because leaders need to prove they can code, but because AI is changing the work faster than secondhand models can keep up.
- [Complexity Is Inevitable. Drag Is Optional.](https://vinny.dev/blog/2026-06-22-turning-complexity-into-leverage/): Complexity is inevitable in modern engineering. Drag is optional. The work of leadership is turning repeated friction into platforms, defaults, and systems that help teams move faster with trust intact.
- [Native Was the Long Way Around. The Stack Wasn't the Point.](https://vinny.dev/blog/2026-06-18-native-was-the-long-way-around/): I rebuilt a working web app as native iOS and Mac software, not because native was magic, but because the discipline required to make it correct is the same discipline AI agents need to be useful.
- [The Subsidy, Itemized](https://vinny.dev/blog/2026-06-15-the-subsidy-itemized/): Twenty-six days of Claude Code showed $2,556 of API-priced work against a $200 subscription. The lesson was not the total. It was cache behavior, model routing, and a government kill switch that landed in my usage chart. Value lives in verified outcomes, not tokens, and the work has to survive the stop.
- [Trust the Gate, Not the Actor](https://vinny.dev/blog/2026-06-14-trust-the-gate-not-the-actor/): AI has made generation cheap. The durable advantage now belongs to teams that can encode judgment into gates that verify whether the work should ship.
- [The Kill Switch Was Always There](https://vinny.dev/blog/2026-06-13-the-kill-switch-was-always-there/): A government order took Anthropic's Fable 5 and Mythos 5 offline. The lesson for enterprise AI is architecture: portability gets you out, verification gets you out safely.
- [The Agent Era Gets an Invoice](https://vinny.dev/blog/2026-06-11-the-agent-era-gets-an-invoice/): Build, WWDC, two confidential S-1 filings, and a tiered frontier model launch hit in the same two weeks. The agent became the interface just as the invoice arrived.
- [The AI Operating Ledger](https://vinny.dev/blog/2026-06-08-the-ai-operating-ledger/): Enterprise AI is entering its accounting phase. The winners will measure verified outcomes, not just tokens, subscriptions, or generated output.
- [Your First AI Reorg Should Be the Work, Not the People](https://vinny.dev/blog/2026-06-06-your-first-ai-reorg-should-be-the-work/): Most AI reorgs open with a headcount model. The better sequence redesigns workflows, decision rights, ownership, and evaluation loops first, then lets the org chart follow the work it is meant to describe.
- [The Subsidy and the Severance](https://vinny.dev/blog/2026-06-02-the-subsidy-and-the-severance/): AI's free-lunch phase is ending, and that makes AI-driven layoff math harder to defend. Two repricings, one ledger.
- [The Agent Team Tax: When AI Agents Need to Argue](https://vinny.dev/blog/2026-05-28-agent-team-tax/): Claude Code agent teams are powerful, but they are not faster subagents. They earn their cost only when the work needs real peer challenge, not polite parallel execution.
- [Workflow.ts: When the Code Runs the Agent, Not the Other Way Around](https://vinny.dev/blog/2026-05-26-context-spine-workflow-js/): Agent loops let the model pick the next step. Workflows invert that. Code owns the control flow; the model owns the judgment inside each step. Here is the TypeScript file I am running today, type-checked against the live SDK, and the honest answer to whether you should build this now or wait for the official tool.
- [The Frame Is the Bottleneck](https://vinny.dev/blog/2026-05-24-the-frame-is-the-bottleneck/): My thesis is that as agents get better at execution, the primary constraint for organizations shifts from technical production to the human-led framing of problems.
- [Code Review Your Prompts](https://vinny.dev/blog/2026-05-17-code-review-your-prompts/): Viral prompt threads borrow the language of science without the rigor. Here's a four-question code review for any prompt, plus a worked example that shows the gap between sounding authoritative and being right.
- [Stunning UIs Aren't Just Designed. They're Enforced.](https://vinny.dev/blog/2026-05-14-inkwell-design-system-enforced-ui/): A field report on building Inkwell, a pure-CSS design system that turns taste into repeatable constraints for people, teams, and coding agents.
- [The Bottleneck Is Never the Stack](https://vinny.dev/blog/2026-05-13-the-bottleneck-is-never-the-stack/): A year of writing, one argument, and a working theory of where software is going
- [The Spec Is the Product](https://vinny.dev/blog/2026-05-12-the-spec-is-the-product/): Code used to be the durable asset. In an agentic SDLC, that changes. Code becomes the regeneratable output of a system that runs on something more important: a clear, versioned, reviewable specification. That shift changes what engineering organizations invest in, how they govern delivery, who they hire, and what they actually ship.
- [AI Populism is a Builder's Problem](https://vinny.dev/blog/2026-05-10-ai-populism-builders-problem/): Jasmine Sun argues AI politics has a new meta, and the warning shots have started. Reading her piece as an engineering leader, here is what the narrative failure looks like from inside a large team, why sociopolitical alignment is our job, and what each of us owes our own career in a market this fast.
- [Building Cloud From Zero: Five Decisions That Compounded and Three I’d Redo](https://vinny.dev/blog/2026-05-08-building-cloud-from-zero/): After two greenfield cloud builds in financial services, these are the decisions that aged well, the ones I would redo, and why the small choices in year one decide whether you have a platform or a pile in year five.
- [AI Did Not Configure My Network. It Helped Me Understand It.](https://vinny.dev/blog/2026-05-06-ai_did_not_configure_my_network/): A weekend home-networking project became a practical lesson in AI-assisted reasoning, documentation, guardrails, and engineering judgment.
- [Spec, Standards, Specialists: How I Actually Build with AI](https://vinny.dev/blog/2026-04-30-spec-standards-specialists-final/): The strategy posts say AI software development is a system. Here is the working loop I run inside that system: a refined specification, a layer of standards, and a coordinated set of specialists doing the work.
- [Claude Code Is a Build System, Not a Chatbot](https://vinny.dev/blog/2026-04-25-claude-code-build-system/): After thirteen months of daily Claude Code use, I stopped treating AI coding as a prompt discipline problem and started treating it like an engineering system: configurable, layered, observable, and built to learn.
- [I Built a Design System in Two Hours. Figma, We Should Talk.](https://vinny.dev/blog/2026-04-18-claude-design-disruption-beyond-figma/): Anthropic's new design tool does not threaten senior designers. It threatens the apprenticeship that made them senior.
- [The Agentic SDLC: Uniting the AI Tool Sprawl](https://vinny.dev/blog/2026-04-15-agentic-sdlc-uniting-ai-tool-sprawl/): Every tool in your product development life cycle is now an AI agent trying to do everything. Here is how to stop the chaos, draw the right boundaries, and build an orchestrated pipeline that actually works.
- [Eleven Years, One Week, and an AI Co-Pilot: Rebuilding TravelTimes for iOS 26.4](https://vinny.dev/blog/2026-04-12-one-week-with-ai-copilot/): A decade-old side project, six major features, one week. How spec-driven AI-assisted development compressed months of work into a focused sprint on a real codebase with real constraints, and where the AI got it wrong.
- [The Dark Factory Model for AI-Driven Software Development](https://vinny.dev/blog/2026-04-05-dark-factory-model-for-ai-software-development/): Most engineers treat AI-generated code like work from a junior developer they don't trust. Simon Willison gave me a better mental model: the dark factory. Here is what it means, why experience is the raw material, and how to build a system that runs.
- [Open Weights, Real Stakes: Running Gemma 4 31B Locally](https://vinny.dev/blog/2026-04-04-gemma4-open-weights-blog/): Google dropped Gemma 4, and I had it running locally the same night. What open weights actually mean, the hardware reality, and why the most interesting AI architectures are about to go hybrid: on-device and in the cloud.
- [From Copy-Paste to Skill: What Thousands of AI Coding Sessions Taught Me About Guardrails](https://vinny.dev/blog/2026-03-28-coding-standards-skill/): After thousands of sessions with Claude Code, Codex, Kiro, and every other LLM-based CLI and IDE, I distilled what I learned into a reusable Claude Skill. Here's how those lessons became the guardrails that let me move faster and actually trust the output.
- [Pipeline-First Is Not a DevOps Initiative - It's a Culture Shift.](https://vinny.dev/blog/2026-03-26-pipeline-first-culture-shift/): Everyone sells pipeline-first delivery as a best practice. Remove access. Route through automation. Enforce consistency. What the slide deck leaves out is the part that actually determines whether this works.
- [Meet Roci: My Always-On Personal AI Agent, One Month In](https://vinny.dev/blog/2026-03-23-meet-roci-always-on-personal-ai-agent/): Back in January I wrote about OpenClaw as a concept. That post was the theory. This one is the implementation. One month running a dedicated EC2 instance, a name, and an agent I genuinely rely on.
- [Strip the Assumptions: What Enterprise AI Adoption Actually Is](https://vinny.dev/blog/2026-03-22-strip-the-assumptions-enterprise-ai/): Most enterprise conversations about GenAI are arguments about assumptions nobody has questioned. Here is what stays when you strip everything else away.
- [They're Using Claude to Ship Claude (And It Shows)](https://vinny.dev/blog/2026-03-21-theyre-using-claude-to-ship-claude/): Anthropic has shipped more meaningful product features in the last few weeks than most teams ship in a quarter. A theory, and what it tells us about what AI-assisted development actually unlocks when a team uses their own product to build it.
- [Yesterday's Feature Is Today's Bug](https://vinny.dev/blog/2026-03-15-yesterdays-feature-is-todays-bug/): Every long-tenured engineering organization inherits decisions that made sense once and make everything harder now. On building IT strategy that outlasts the people who built it, without freezing the org in amber.
- [Dark Fiber, Bright Future: Why the AI Infrastructure Boom May Need Its Bust](https://vinny.dev/blog/2026-03-11-dark-fiber-bright-future/): The companies that built the modern internet went bankrupt doing it. The companies building AI infrastructure may follow the same path. That is not a warning. It is how transformative technology actually works.
- [From iOS to Android in a Weekend: How I Used Claude Code to Build a Complete App Without Writing a Single Line of Code](https://vinny.dev/blog/2026-03-10-from-ios-to-android-app-in-a-weekend/): I took a production iOS app, pointed Claude Code at it, and had a fully functional Android app in eight hours over a weekend. Here's exactly how it worked.
- [From Caffeine Addict to App Builder: How I Vibe Coded a Pour-Over Coffee App in One Afternoon](https://vinny.dev/blog/2026-03-01-vibe-coding-with-coffee/): My wife started making pour-over coffee. I started building her an app. What used to take weeks of Swift development now takes hours with AI-assisted coding. Here's the story of PourCraft, caffeine dependency, and the moment I realized the game has changed.
- [The Companies Spending the Most on AI Have the Most to Gain From Convincing You It Will Take Your Job](https://vinny.dev/blog/2026-02-17-you-cant-automate-demand-ai-jobs-narrative/): The AI-and-jobs conversation gets framed as either inevitability or competition. Both frames are incomplete, and both conveniently align with the interests of the companies selling the technology. A third reading of what's actually happening to work.
- [How I Built a Production Notification System for TravelTimes in One Day with Claude Code](https://vinny.dev/blog/2026-02-06-building-notification-system-with-claude/): From 'users want commute alerts' to 1,800 lines of shipped, App Store-ready code in a single coding session. A deep dive into architecture, edge cases, and what AI-assisted iOS development actually looks like.
- [OpenClaw and the Rise of the 'Real' AI Assistant](https://vinny.dev/blog/2026-02-03-openclaw-and-rise-of-ai-assistant/): An honest look at OpenClaw, the open-source AI personal assistant generating real excitement. What it does, what I learned running it, and why it matters for the future of enterprise AI.
- [The Open Source Paradox AI Created](https://vinny.dev/blog/2026-01-11-the-open-source-paradox-ai-created/): Generative AI is accelerating open-source adoption while quietly breaking the economic models that sustain it. This is not a tooling problem. It’s a policy and incentive failure.
- [Building StillView 3.0: Raising the Quality Bar with Claude Code and Opus 4.5](https://vinny.dev/blog/2026-01-03-opus45-thinking-partner/): Using Claude Code and Opus 4.5 as thinking partners helped me rebuild confidence, clarity, and quality in a growing macOS codebase.
- [Getting Better at Getting Better in 2026](https://vinny.dev/blog/2025-12-31-getting-better-at-getting-better-in-2026/): Real change compounds when you build systems that make improvement unavoidable.
- [The New Abstraction Layer: AI, Agents, and the Leverage Moving Up the Stack](https://vinny.dev/blog/2025-12-30-ai-abstraction-layer/): Andrej Karpathy put words to something many engineers are quietly feeling: we have been handed a powerful alien tool with no manual. Where the leverage is actually moving up the software stack, and what that means for the people writing code right now.
- [The Year Ahead in AI, Enterprise Software, and the Future of Work](https://vinny.dev/blog/2025-12-20-year-ahead-in-ai-future-of-work/): From generative AI as a tool to AI as a strategic partner. Reflections on 2025 and what excites me most about 2026.
- [Frontier Models, Small Language Models, and a New Middle Path](https://vinny.dev/blog/2025-12-04-frontier-models-small-language-models-aws-nova/): The most strategic AI decision is not which model to use: it is knowing when generic intelligence is not enough. AWS Nova Forge marks the shift from consuming AI to owning a specialized slice of it, and why that middle path is where enterprise AI actually lives.
- [My Journey to Trusting GenAI With More of My Code](https://vinny.dev/blog/2025-11-15-journey-with-trusting-genai-and-coding-workflow/): How my workflow evolved from autocomplete magic to spec driven development, and why trusting GenAI with more of my code has changed how I build software.
- [When Winning Teams Lose: A Ferrari Leadership Lesson](https://vinny.dev/blog/2025-11-13-f1-ferrari-leadership-lesson/): Ferrari offers a masterclass in leadership anti-patterns. What their struggles reveal about accountability, culture, and building winning teams.
- [The Rise of MCP Servers: Why Every Developer Will Have a Personal AI Toolchain](https://vinny.dev/blog/2025-11-01-the-rise-of-mcp-servers/): From AWS to GitHub to Podman, MCP servers are quietly becoming the new plug-in ecosystem for developers, and it’s changing how we work.
- [From Procrastination to Privacy-First Productivity (Part 2)](https://vinny.dev/blog/2025-10-26-task-management-to-mcp/): After building two open-source task managers to battle procrastination, I took it further: secure cloud sync, end-to-end encryption, and now an MCP server that connects your tasks to AI.
- [The Art of Enough: Why Minimalism Matters in Software Engineering](https://vinny.dev/blog/2025-10-20-the-art-of-enough/): Software gets slower faster than hardware gets faster. Exploring Wirth's Law and why real progress might not be about adding more, but mastering the art of enough.
- [Building My Own Productivity Tools: A Procrastinator's Journey](https://vinny.dev/blog/2025-10-09-a-procrastinators-journey/): After testing every productivity app under the sun, I did what any reasonable engineer would do. I built my own. Two open-source, privacy-first task managers to help procrastinators like me get things done.
- [When Winning Feels Like Losing: Leadership Lessons from McLaren’s F1 Drama](https://vinny.dev/blog/2025-10-07-leadership-lessons-mclaren-f1/): Even championship teams can lose the narrative when leadership loses clarity. McLaren’s latest Formula 1 victory is proof that success without alignment can still feel like failure.
- [Beyond the Hype: Why GenAI Adoption in Development Isn't the Silver Bullet We Expected](https://vinny.dev/blog/2025-09-30-genai-adoption-in-development/): The resistance to GenAI tools isn't simply about developers being stubborn or afraid of change. It's a rational response to tools that haven't yet proven their value universally, in an environment where people are already managing substantial change fatigue, and where the quality bar for production code remains high.
- [Coaching Your LLM with Software Craftsmanship Principles](https://vinny.dev/blog/2025-09-27-coaching-your-llm-with-software-craftmanship-principles/): By coaching LLMs with timeless software design principles like SOLID, DRY, and YAGNI, you can transform raw code generation into consistently clean, maintainable, and production-ready software.
- [From AI to Agents: Building Smarter Systems that think, decide and act](https://vinny.dev/blog/2025-09-14-From-AI-to-AI-Agents/): Exploring the evolution from AI to AI Agents with a hands-on FinOps example. Learn how AWS Strands enables autonomous agents to monitor cloud spend, notify on overages, and free humans to focus on higher-judgment work.
- [My AI Subscription Problem (or is it obsession)](https://vinny.dev/blog/2025-09-07-My-AI-Subscription-Problem/): A humorous confession about subscribing to nine different AI development tools in my quest to find the best tool(s).
- [What worked in 2010 is our blueprint for the AI-infused future](https://vinny.dev/blog/2025-09-01-Blueprint-for-AI-infused-future/): Just like Cloud before, today's AI transformation demands companies rebuild their operating models, leadership structures, and developer experience instead of retrofitting AI onto existing workflows.
- [The Future of Interfaces](https://vinny.dev/blog/2025-08-28-The-Future-of-Interfaces/): AI-powered interfaces are evolving beyond traditional graphical UIs toward intent-based interactions, where users describe desired outcomes rather than navigating through menus and clicks.
- [September Read List](https://vinny.dev/blog/2025-08-28-September-readinglist/): Four September reads all emphasize intentional leadership through simplicity and focus over busyness.
- [We are standing at the edge of another tech revolution](https://vinny.dev/blog/2025-08-19-Another-Tech-Revolution/): AI represents the third major tech revolution (after the internet and mobile), and like previous waves of creative destruction, it will eliminate some jobs while creating entirely new careers and opportunities for those who adapt quickly.
- [10 Years Later: A Journey of Continuous Learning Through Side Projects](https://vinny.dev/blog/2025-08-10-Reflecting-journey-continous-learning/): Reflecting on a decade of staying hands-on in tech, fueled by curiosity, side projects, and a desire to never stop learning.
- [From Vibe Mode to Spec Mode: Why I’m All In on Kiro](https://vinny.dev/blog/2025-08-10-From-Vibe-Mode-to-Spec-Mode/): A hands-on look at how AWS Kiro transforms AI-assisted development from chaotic vibes into structured, spec-driven engineering.
- [Back to Blogging: Two Decades in the Making](https://vinny.dev/blog/2025-05-17-back-to-blogging/): After two decades, I’m returning to blogging, back to sharing ideas, experiments, and the joy of connecting with curious minds.
- [I just ran a 20-billion-parameter LLM entirely offline, from my Mac at home](https://vinny.dev/blog/2025-05-17-Twenty-Billion-Parameter-LLM-at-home/): Successfully running OpenAI's 20-billion-parameter open-weight model (gpt-oss-20b) locally on a Mac M4 Pro, highlighting the potential of offline AI that rivals cloud-based models without internet dependency or costs.