Writing
What I'm working through
The decisions behind the products I build and run — what worked, what broke, and what I'd do differently.
Latest
How I build — the operator playbook
A look inside the system-first approach I use to manage and scale a portfolio of digital products as a solo operator.
The Taxonomy of Expertise
Turning years of professional experience into a digital product requires separating what you enjoy doing from what a market is willing to pay to solve.
The Solo Stack
A look at the technical and operational systems required to run a multi-product digital studio as a single owner.
The Architecture of Choice
Success in a solo digital studio is determined by the decisions made before the first line of code is ever written.
Context engineering for agents
A guide to using CLAUDE.md and codebase maps to provide the necessary structure and constraints for AI agents to operate effectively within a digital studio.
Guardrails for coding agents
Implementing deterministic boundaries for agentic engineering ensures that a software studio remains productive without risking the integrity of the codebase.
Inky's Secret: One Schema, Two Languages, Zero Mismatches
Tired of client-server mismatches? Inky's iOS app and backend share a single Zod schema, generating Swift types directly. This means your client and server always agree on data shapes, eliminating common integration headaches.
Agent-Augmented Ops: Split Financial Credentials for Security
When you hand an AI agent access to financial data, a single all-powerful API key is a risk. Learn why splitting credentials—read-only for most tasks, IP-locked write for mutations—is essential for secure agent-augmented-ops.
The Hidden Monorepo Bug: Stale Firebase Functions
You've fixed a shared package, type-checked, and passed CI, yet your Firebase function ships stale. The bug isn't in your code, but in the packaging step. Learn how to diagnose and fix this common monorepo deployment issue.
ShadowBrain: The MCP Server for Agent Operations
Building multi-agent systems often means duplicating operational logic. ShadowBrain, my studio's MCP server, centralizes financials, approvals, and health monitoring for every agent, streamlining operations.
The F1 Glossary: Your Quiet SEO & Lead Generation Machine
A jargon glossary isn't just a reference page; it's a powerful, understated tool for long-tail SEO, a genuine reader service, and a lead surface. Learn how to build one.
Profit First: The Cash Allocation Mechanic That Actually Works
Many solo founders read Profit First, set up accounts, but struggle with actual cash movement. The solution: separate Mercury accounts and a daily categorization cron.
A Silent Week: Resend Cron Routing Lessons from PPH-Build
My editorial newsletter went silent for a week due to a cron routing error. Learn why explicit destination testing is crucial for any cron fanning out to humans.
MCP Servers: Consolidate Tools for Agent Clarity
Building MCP servers? If your AI agents are calling the wrong tools, it's likely a scope issue. Learn why consolidating near-duplicate tools is critical for agent performance.
Unified Audit Framework: Beyond One-Off Drift Checks
Stop accumulating one-off cron jobs for system drift. A unified audit framework lets you register new checks as simple files, automatically surfacing results on a dashboard. This is how one operator manages complexity.
Claude Code: The Agent SDK You Might Be Overlooking
If you're an engineer planning to build a coding agent with the Anthropic SDK, you might be rebuilding the wheel. Claude Code offers a pre-solved workspace abstraction.
From Eight Dashboards to One Daily Brief: Agent-Augmented Ops
Tired of checking endless dashboards every morning? Learn how to replace eight context switches with a single, signal-rich daily brief, delivered before your coffee, using agent-augmented ops.
Building an AI Story App: Architecture and Lessons from Inky
A look inside the architecture and decision-making process of building Inky, an AI-powered storytelling application, as a solo operator with an agentic workforce.
Profit Over Revenue: The Math of a One-Person Studio
Stop chasing vanity metrics. Learn why a profit-first approach to digital products and services beats high-revenue, low-margin consulting every time.
Building an AI Story App: Architecture and Lessons from Inky
How I built Inky, an AI storytelling app, using a one-person studio model and an agentic workforce. Real lessons on architecture and product longevity.
Building a Shared Operational Substrate with MCP Servers
Stop duplicating service clients across your agent workforce. Learn how VERA uses MCP servers to expose studio financials and approvals to every agent through a single protocol.
Parallelizing Claude Code: Git Worktrees and Agent Workflows
Stop fighting git locks. Learn how to run multiple Claude Code agents concurrently using git worktrees and ephemeral branches for conflict-free agentic engineering.
MCP Servers vs. Skills: A Decision Framework for Operators
Most custom integrations don't require a full MCP server. This guide breaks down when to build stateful servers and when to stick to procedural skills for agentic engineering.
Building an AI Story App: Lessons from Shipping Inky
I am building Inky as a permanent asset for Total Ventures. Here is the architecture and the logic behind building an AI story app that lasts.