Essays#
This is the place within Notes for reflections, opinions, observations, retrospectives, and direction-setting posts.
- Commentary on events and things I notice
- Notes on direction (blog, work, life)
- From short reflections to longer essays
Latest Posts
The Two Walls You Hit When You Hand an Agent a Browser
Two problems I ran into while having coding agents verify their work directly in a browser — Chrome collisions across parallel sessions and Google blocking sign-in — analyzed at the root and solved with the --isolated option and the attach pattern.
Context Switching in the Age of AI Agents — When You Become the Scheduler
As AI agents take over the final execution of work, the human bottleneck has shifted to context switching between agent sessions. Grounded in research on attention residue and resumption lag, this essay lays out three operating rules: no switching on notification, resume memos, and a cap on interactive tasks.
Hunting Down an Active-User Crash — Bots, Illusions, and an Indexing Collapse
When the Google Analytics active-user graph fell off a cliff, I chose to peel the data back layer by layer instead of trusting the number. A record of telling bot traffic from real readers, diagnosing an indexing collapse after a domain migration, and putting the sitemap on an index diet.
Why Do Coding Agents All Design Alike? — Research and Decisions Behind Choosing a Design Stack
An essay on why web designs produced by coding agents look similar and slightly unpolished, surveying the skills, MCP servers, and harness guidelines that address this, and walking through the decisions that shaped an actual project's design stack.
LLM Wiki, Opened Up — The 'Automatic Memory' Myth and a Schema That's Just a Few Lines
A record of actually applying Andrej Karpathy's LLM Wiki to my repository and what I learned. I correct the myth that it's 'automatic memory that updates itself,' show that the heart of the pattern is really 'a schema that's just a few lines,' and walk through how I brought it into my repository.
What Do Feature Flags Actually Solve? Single-Branch Collaboration and the Myth of Google-Style Trunk Development
An essay examining whether feature flags can fix the problems of having everyone push directly to a single shared branch. It lays out what feature flags actually solve, what they don't, and the real conditions that make Google-style trunk-based development work.
I Thought AWS Bedrock Was Just Relaying Models — Turns Out It Runs Them Directly
A record of digging into how AWS Bedrock serves external LLMs like Claude and GPT. It is not a dedicated-line relay but direct hosting, with cryptographic sealing and zero operator access protecting the model assets.
An AI Tools Knowledge Map — Lining Up the Materials for Process-Improvement Consulting
To reach a level where I can consult on improving work processes with AI, I organized today's AI tools by category and noted what each one is and how it can be used. From chatbots to coding tools, autonomous agents, and managed AI platforms — a living knowledge map I plan to review often.
I Decided to Call Them Harness Skills — Breaking the Illusion of Doing Well and Opening Up My Harness
A story that began with a question: what should we call tools like LLM Wiki and GStack? With no standard term available, I named them 'harness skills,' reflected on how confidence in my own harness became a trap for growth, and then surveyed the most widely loved harness skills.