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.
★tag · 57 essays
#engineering-leadership
All essays tagged engineering-leadership.
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
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
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
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?
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
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
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
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
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
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
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.
★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.
★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.
★Don't Automate the Apprenticeship Out of Engineering
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
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
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
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.
★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.
★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
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.
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.
★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
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
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
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
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
AI's free-lunch phase is ending, and that makes AI-driven layoff math harder to defend. Two repricings, one ledger.
Workflow.ts: When the Code Runs the Agent, Not the Other Way Around
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
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
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.
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
A year of writing, one argument, and a working theory of where software is going
★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
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
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.
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
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
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.
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
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.
★The Dark Factory Model for AI-Driven 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
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
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.
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
Most enterprise conversations about GenAI are arguments about assumptions nobody has questioned. Here is what stays when you strip everything else away.
★Yesterday's Feature Is Today's 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
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.
Getting Better at Getting Better in 2026
Real change compounds when you build systems that make improvement unavoidable.
When Winning Teams Lose: A Ferrari Leadership Lesson
Ferrari offers a masterclass in leadership anti-patterns. What their struggles reveal about accountability, culture, and building winning teams.
When Winning Feels Like Losing: Leadership Lessons from McLaren’s F1 Drama
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
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.
What worked in 2010 is our blueprint for the 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.
September Read List
Four September reads all emphasize intentional leadership through simplicity and focus over busyness.
We are standing at the edge of 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
Reflecting on a decade of staying hands-on in tech, fueled by curiosity, side projects, and a desire to never stop learning.
Back to Blogging: Two Decades in the Making
After two decades, I’m returning to blogging, back to sharing ideas, experiments, and the joy of connecting with curious minds.