Dispatches · Writing

From the coach's corner.

Field notes on engineering leadership, team systems, and the shift toward AI-assisted development.

№ 060 AI Leadership Aug 2026

Should We Build This Has No Test Suite

AI can plan, build, test, and review software. None of those capabilities can prove that the objective deserved the investment.

AI StrategyDecision-MakingOrganizational Intelligence
Read →
№ 059 AI Leadership Jul 2026

Good AI Management Is Just Good Management

Agent loops and spec-driven development give AI workers what good managers give junior developers: the right context, delivered at the right time, inside clear boundaries.

AI CodingAgent LoopsSpec-Driven DevelopmentAI Standards
Read →
№ 058 The AI Stack Jul 2026

DeepSeek Did Not Make Local AI Inevitable

Open weights made cheaper AI possible. They did not make hybrid AI easy. The missing product is the routing and operations layer that lets an ordinary enterprise use more than one model safely.

Local AIOpen ModelsModel RoutingAI Economics
Read →
№ 057 The AI Stack Jul 2026

One User Can Spend Your AI Budget

The moment one employee can consume half a team's AI allocation in a day, AI stops being a productivity subscription and becomes infrastructure that needs governance.

AI GovernanceToken CostsDeveloper ToolsAI Adoption
Read →
№ 056 The AI Stack Jul 2026

What AI Companies Can Learn From the Auto Industry

Frontier labs do not need one model for every job. They need a product ladder that gives customers Toyota economics, Porsche capability, and Koenigsegg performance when the work earns it.

AI EconomicsModel ProvidersToken CostsModel Routing
Read →
№ 055 The AI Stack Jul 2026

The Prediction Is Already Becoming Testable

Eighteen days after I predicted Anthropic would be the first major frontier-model provider to fail, the mechanism behind that prediction has started to become testable.

ComputeModel ProvidersAI Market
Read →
№ 054 Code Quality Jul 2026

Tech Debt Has Gravity

Technical debt does not just slow teams down. At enough mass, it becomes gravity. Escaping it requires deliberate energy, protected capacity, and leadership willing to spend effort climbing instead of pretending every sprint is forward motion.

Tech DebtEngineering LeadershipTeam Systems
Read →
№ 053 Code Quality Jul 2026

Spartan Simplicity: Carry Less

Every platform, pattern, library, and tool becomes something the team has to carry. Spartan simplicity is the discipline of keeping only what helps the team do the work right.

Code QualityArchitectureEngineering Judgment
Read →
№ 052 Team Systems Jul 2026

QA Belongs in the Loop

QA is not a final inspection step. QA helps the team orient, shorten feedback loops, and understand what correct means while the work is still cheap to change.

Team SystemsQualityEngineering Leadership
Read →
№ 051 Code Quality Jul 2026

Boundaries Preserve Optionality

Good architecture is not about adding layers for their own sake. It is about preserving future options by putting decisions where they belong.

Code QualityArchitectureEngineering Judgment
Read →
№ 050 Code Quality Jun 2026

Taste Is Fast (and Earned) Orientation

Taste in software is not magic. It is fast orientation, and it only becomes useful when it can be examined, explained, and turned into judgment other people can use.

Code QualityEngineering JudgmentStandards
Read →
№ 049 Engineering Leadership Jun 2026

Your Team Is Fast. Can It Turn?

A top-fuel dragster is faster than a Ferrari until the road turns. Engineering teams make the same mistake when they optimize for feature output and lose the ability to maneuver.

Engineering LeadershipTeam SystemsCode Quality
Read →
№ 048 Strategy & History Jun 2026

A Fighter Pilot Is Hiding in Your Engineering Practices

Scrum, CI/CD, postmortems, and now agent loops all share one skeleton. A fighter pilot most engineers have never heard of sharpened it, and the part everyone keeps dropping is the part that matters.

OODAEngineering PracticesDecision-Making
Read →
№ 047 AI Leadership Jun 2026

The Loop Is the Easy Part

Everyone is hyping agent loops. The loop was never the hard part. A fighter pilot figured that out half a century ago, long before the rest of us typed a prompt.

AI CodingAgent LoopsDecision-Making
Read →
№ 046 The AI Stack Jun 2026

The Mainframe Era of AI Is Ending

AI began in centralized data centers, but hardware, local models, and enterprise sovereignty are starting to move inference closer to the user.

Local AIAI HardwareModel RoutingCloud AI
Read →
№ 045 Engineering Leadership Jun 2026

Constantia: Principles Under Pressure

Standards matter most when following them feels unnecessary. Constantia is the discipline to preserve the controls that protect the team, even when the work is already good.

Roman VirtuesConsistencyStandards
Read →
№ 044 Engineering Leadership Jun 2026

Virtus: Courage as Managerial Action

Courage in engineering leadership is not bravado. It is saying what is true, advocating for what is right, and accepting the consequences of doing so.

Roman VirtuesCourageExecutive Communication
Read →
№ 043 The AI Stack Jun 2026

Anthropic Will Be the First Major AI Company to Fail

Anthropic leads the business AI coding market. I predict that its lack of control over compute will also make it the first frontier-model provider to fall.

ComputeModel ProvidersAI Market
Read →
№ 042 Engineering Leadership Jun 2026

Results Are the Only Thing That Matters

Clean code matters because results matter. Working software deserves respect, but respect is not immunity from change.

ResultsLegacy SystemsPragmatism
Read →
№ 041 Code Quality Jun 2026

The Disciplined Codebase

Healthy codebases are not built by chasing what feels exciting. They are built through restraint, standards, boring consistency, and doing the necessary work in the right order.

StandardsDisciplineTechnical Debt
Read →
№ 040 Engineering Leadership Jun 2026

Gravitas: Be the Calm

When pressure hits, the engineering leader's job is not just to avoid panic. The job is to project enough calm that the team can think, diagnose, and move.

Roman VirtuesIncidentsCalm
Read →
№ 039 Code Quality Jun 2026

Disciplina: Standards Beat Preference

A healthy codebase cannot depend on every engineer carrying a private version of good. Disciplina turns taste into shared standards the team can actually follow.

Roman VirtuesStandardsDiscipline
Read →
№ 038 Engineering Leadership Jun 2026

Pietas: Duty Is Not Always Gentle (Or Easy)

A manager has a duty to the struggling employee. That duty does not erase the duty to the team, the business, the customers, and everyone else absorbing the cost.

Roman VirtuesDutyTeam Protection
Read →
№ 037 Strategy & History Jun 2026

Roman Virtues for Engineering Leaders

Engineering leadership is tested under pressure. The old Roman virtues give us a useful language for the practical behaviors leaders need when the system gets hard.

Roman VirtuesLeadership
Read →
№ 036 Engineering Leadership Jun 2026

You're Accountable for the Team. You're Not in Charge of It.

Tech leads are accountable for team outcomes they can influence, but cannot command. That is the job.

Tech LeadsAccountability
Read →
№ 035 AI Leadership Jun 2026

Effectiveness = Management × Contribution²

AI is collapsing the timeline on strategic initiatives. Work that used to take months of mapping and planning now takes days. That collapse changes the math of who should be building.

AI LeverageManagementContribution
Read →
№ 034 Strategy & History May 2026

The Stoic Engineering Leader

You inherited the codebase you inherited. Leadership starts when you stop being offended by reality and start improving what is within your practical grasp.

StoicismLegacy CodeLeadership
Read →
№ 033 The AI Stack May 2026

The Harness Wars Have Started. We've Seen This Before.

Claude has already won. Copilot is dead in the water. Cursor is Elon's fantasy play. Every one of those takes is pontification dressed in the robes of an oracle.

HarnessesModel SwitchingInteroperability
Read →
№ 032 Code Quality May 2026

Stop Reading AI Code. Score It.

The question was never read or measure. It was human or agent. The reviewer does not have to be you.

Code ScoringAI ReviewMetrics
Read →
№ 031 Code Quality May 2026

I Scored Four Codebases. The Humans Lost.

I scored four codebases against the same rubric. The two that failed were 100% human-written. The two that nailed it were 99% AI-written. Quality is not a human trait.

Code ScoringAI CodeMetrics
Read →
№ 030 AI Leadership May 2026

How to Set Agentic Coding Standards Across Multiple Teams

One dev uses Claude, another uses Copilot, a third uses Cursor. They're all generating code in your codebase. Without shared standards, you don't have standards.

AI StandardsGovernanceMulti-team
Read →
№ 029 AI Leadership May 2026

Your Org Needs an Internal AI Skills Marketplace

AI skills are distributed software with privileged access. Treat them like part of your supply chain, not random files developers install from strangers.

AI ToolsGovernanceSkills
Read →
№ 028 AI Leadership May 2026

Your AI Instructions File Should Be a Router, Not a Novel

Most teams dump everything into one massive AI instructions file and wonder why their agents ignore half of it. The fix is architecture, not more words.

AI StandardsModel ContextStandards Router
Read →
№ 027 AI Leadership May 2026

Vibe Shipping Is the Real Problem

The generation method isn't the crisis. Giving up intentional control over what ships is.

AI ShippingOperating Model
Read →
№ 026 Strategy & History May 2026

The Art of Software Development

Good engineering strategy makes brute force unnecessary. Five lessons from Sun Tzu show how roadmaps, measurement, terrain, constraints, and systems turn struggling teams into predictable ones.

Ancient StrategySoftware Development
Read →
№ 025 Strategy & History May 2026

Software Development Has Always Been Moving in One Direction

From assembly to compilers to frameworks to AI: software development keeps moving toward higher abstraction, faster feedback, and clearer intent.

Paradigm ShiftsAbstractionAI
Read →
№ 024 AI Leadership May 2026

Give Your AI Agent a Map of Your Codebase (For Free, Locally)

Every AI coding session starts with your agent scanning the codebase to figure out what's going on. A code map eliminates that cold start entirely.

AI AgentsCode MapsLocal Tools
Read →
№ 023 AI Leadership May 2026

The Three-Agent Playbook for Legacy Code Modernization

Legacy rewrites fail because business rules buried in old code get lost in translation. A three-agent pipeline extracts that knowledge before anything changes.

AI AgentsModernizationLegacy Code
Read →
№ 022 Career & Craft Apr 2026

The Jordan-Karpathy Effect

AI amplifies the foundation you bring to it. Senior engineers get leverage because they have judgment, standards, and enough context to direct the tool.

Senior EngineersAI LeverageLearning
Read →
№ 021 AI Leadership Apr 2026

Vibe Coding Is Not a Strategy

AI can write code quickly, but engineers still own intent, architecture, standards, review, and the decision to ship.

AI CodingIntentStandards
Read →
№ 020 Code Quality Apr 2026

Good Code Isn't Taste. It's Measurable.

Calling code quality 'taste' sounds sophisticated. It's actually the reason teams can't teach it, can't enforce it, and can't get AI to meet it.

Code QualityTasteMetrics
Read →
№ 019 AI Leadership Apr 2026

AI Doesn't Write Spaghetti Code. You Do.

AI can produce spaghetti code. It usually does so when the organization gives it no standards, no local context, and no meaningful way to check the work.

AI StandardsCode Quality
Read →
№ 018 Career & Craft Apr 2026

Stop Telling Kids to Major in Computer Science

AI writes the code now. The skill that matters is understanding the business problem. For most software careers, a business degree with a CS minor wins.

Career AdviceEducationAI
Read →
№ 017 AI Leadership Apr 2026

Your Internal NuGet Packages Are an AI Blind Spot

AI coding tools know every public package cold. Yours? Brand new to them. Here's what happens when the AI guesses, and how to fix it.

Internal PackagesAI ContextDocumentation
Read →
№ 016 AI Leadership Apr 2026

Your AI Can Write Code. It Still Needs Stories.

AI can generate features from a prompt. That's exactly why you need stories more than ever. Without them, you ship generic output and call it productivity.

AI CodingRequirementsStories
Read →
№ 015 AI Leadership Apr 2026

The AI-Powered Requirements Pipeline That Makes Planning Faster

Four AI skills chained together that help a product owner turn feature ideas into developer-ready stories without starting from a blank page.

RequirementsProduct OwnershipAI Agents
Read →
№ 014 Team Systems Apr 2026

In Celebration of the Product Owner

The product owner is the most undervalued role in software. Every team that skips it pays the price in rework, missed sprints, and developers building the wrong thing.

Product OwnershipDelivery
Read →
№ 013 The AI Stack Apr 2026

All Your (Code)Bases Belong to Us

AI companies are scraping public repos and shipping community innovations as features. If your code enhances an agentic platform, think twice before going public.

Open SourceAI PlatformsRisk
Read →
№ 012 Team Systems Apr 2026

You're Reading DORA Backwards

DORA metrics tell you what elite teams look like. They don't tell you how to become one. Most engineering leaders get this backwards. And it's costing them.

DORAMetricsCapability
Read →
№ 011 Team Systems Mar 2026

Developers on Islands

When each developer owns their slice of the codebase and nobody else knows how it works, your team's velocity number is a fiction. Here's what it costs.

Knowledge SilosTeam Design
Read →
№ 010 AI Leadership Mar 2026

Engineering Leaders Have the Advantage in the Age of AI

Defining outcomes, reviewing output, managing feedback loops: the skills that make a great engineering leader are exactly what makes someone effective with AI.

AI AdoptionLeadership Leverage
Read →
№ 009 Team Systems Mar 2026

Splitting Stories: The Skill That Makes or Breaks Sprint Velocity

One of the surest ways to kill a team's productivity is to saddle it with large stories. The tricky part is they don't always look large on the surface.

Story SplittingScrumSprint Planning
Read →
№ 008 Code Quality Mar 2026

Tech Debt Is a Choice, Not a Failure

Technical debt can be a rational business choice. It becomes neglect when the cost disappears from view and the team keeps paying interest without reducing the principal.

Tech DebtRiskMaintenance
Read →
№ 007 AI Leadership Mar 2026

Your AI Code Quality Problem Is Actually a Standards Problem

Developers complaining about AI-generated slop are diagnosing the wrong problem. The code isn't bad because of AI. It's bad because of you.

AI StandardsCode Quality
Read →
№ 006 Team Systems Mar 2026

Your Team Is Doing Scrum. Does It Understand Scrum?

Most teams that 'do Scrum' have learned the ceremonies but missed the point. The ceremonies are not the methodology. They're just the surface.

ScrumAgileFeedback Loops
Read →
№ 005 Team Systems Dec 2024

Skills You Need as a Dev Manager: Product Owner

A development manager cannot lead delivery without understanding product ownership. Someone has to turn vision into sequence, protect priorities, and define work small enough to ship.

Product OwnershipManagement Skills
Read →
№ 004 Career & Craft Sep 2024

Think about RIOTS

CRUD describes what happens to stored records. RIOTS helps developers trace how data moves and changes between those operations.

Problem SolvingSoftware Design
Read →
№ 003 Engineering Leadership Apr 2024

High Performers vs Good Managers: Lessons from the Hardwood

The best contributor succeeds through personal output. The manager succeeds by creating the conditions for other people to produce excellent work.

ManagementPromotionLeadership
Read →
№ 002 Career & Craft Apr 2024

MVP in Personal Projects

The hardest discipline in personal projects is building the smallest thing that proves your idea works, not the grand vision you have in your head.

MVPPersonal Projects
Read →
№ 001 Engineering Leadership Mar 2024

Managing vs Orchestration and Enablement for Software Development Teams

A development manager is accountable for the performance, but does not produce it alone. The job is to understand the product, draw out each developer's strengths, and shape their work toward the result users need.

ManagementEnablement
Read →