The Field Notes
Field notes are short, practical writeups based on lived workflow experience.
Not hype. Not product announcements. Not benchmark debates.
Each entry focuses on what happened, why it matters, and what to do differently next time.
If you want structured evergreen frameworks, start with the Guides section. If you want real-world lessons from using these tools under load, you are in the right place.
The 20 Rooms That Matter
More than forty years ago, I found myself sitting in one of those old corporate boardrooms that looked exactly like you would expect an old corporate boardroom to look.
Mahogany everywhere.
Big table.…
Read more
Sometimes You Have to Stop the Train
PageSnip was getting close.
Not small-project close, where you’ve got three things left on a checklist and you’re pretty sure two of them are cosmetic.
This is a large application that has been growin…
Read more
The Build That Worked Until I Opened Yesterday's Database
The build worked.
At least, that's what the tests said.
We'd made several focused changes to ProHelp Viewer. A retired-topic restore problem was working again. The Viewer was correctly handling PageSn…
Read more
Watch the Tide
A fellow programmer in an AI forum recently posted a link to a new Anthropic article about working with its latest generation of Claude models.
The title was The New Rules of Context Engineering for C…
Read more
Try, Try Again
I recently listened to an episode of The OpenAI Podcast with Tejal Patwardhan, who leads OpenAI's frontier evaluations team.
Her job is to help test the newest models and determine how capable they're…
Read more
The Day the AI Had to Read the Code
I recently ran into one of those AI-assisted development failures that was frustrating while it was happening and useful once I had a little distance from it.
That’s usually how these lessons show up.…
Read more
The Day One More Thing Became the Real Bug
I didn’t notice the pattern all at once.
At first, it just looked like normal software work.
We’d fix something in PageSnip. Then we’d polish something near it. Then I’d notice another behavior that w…
Read more
The Good, the Bad and the Ugly
This isn’t a controlled benchmark, and I’m not claiming that one AI will always write better code than another.
It’s a comparison of what happened when I used Claude and ChatGPT during a difficult, mu…
Read more
The Day Claude Tried to Sell Me My Own Workflow
A few days ago, I had one of those AI conversations that got more interesting as it went along.
I was talking with Claude about whether I should change the way I code with AI.
Right now, my normal wor…
Read more
Help Me Help You, AI: The Day the Side Threads Started Pulling Their Weight
I've been using a workflow lately that's working well enough that I know it's going to stick.
It started as one of those practical adjustments you make because something in the sessions keeps botherin…
Read more
When “Done” Wasn’t Ready to Release
There is a particular kind of temptation that shows up when a project gets close to release.
You can see the finish line. The features are there. The rough edges feel survivable. And because AI makes …
Read more
When the Conversation Became Part of the Bug
I ran into one of those AI-assisted development failures recently that was miserable while it was happening and useful after I had a little distance from it.
That's usually how these lessons show up.
…
Read more
The Elephant Does Not Walk Into the Room
I was working through a familiar kind of job recently: taking older working code and moving the parts worth saving into a newer, cleaner framework.
That sounds straightforward enough.
It usually isn't…
Read more
Do Not Give the Agent the Keys to the Kingdom
I've been thinking through agentic coding from a practical standpoint, not just from the usual "can it write code?" angle.
I can see the appeal.
If I'm paying for the tokens, I don't just want the age…
Read more
The day I realized AI was building daysailers
I've spent a lot of time lately thinking about the difference between software that looks like progress and software that's actually built to last.
Part of that came from watching how AI tends to beha…
Read more
When the Fix Became the Next Bug
One of the patterns I ran into pretty quickly with AI coding work was this:
I'd ask for a fix, and the answer would come back as a series of patch instructions.
Change this block.
Replace that functio…
Read more
When LinkedIn Became LinkedOut
There was a time when proving you owned an online account meant demonstrating control of the email address tied to it.
Apparently that is no longer enough.
Recently, LinkedIn restricted my account aft…
Read more
When Working Code Isn’t Enough
There is a moment with AI-generated software that is easy to admire and easy to misunderstand.
You describe something you want. You go back and forth a few times. And before long, you have something t…
Read more
When our AI workflow became a junk drawer
I ran into this recently on a fairly involved software project where we were using AI heavily across multiple stages of the work.
The project had real complexity. Existing constraints. Existing conven…
Read more
The Moment I Realized the AI Needed the Rules First
I ran into this in a session that started out harmlessly enough.
The AI and I were discussing one of my projects in general terms. Caught up in one of the ideas, I let the conversation slide into actu…
Read more
The Moment I Realized I Was Losing the Big Picture
I ran into this while working on an older control we were trying to improve without replacing outright.
The approach was to layer newer behavior on top of legacy behavior. At first, that worked pretty…
Read more
The day Claude told me to take a nap
If you use AI casually, you might never run into the limits.
If you use it hard, you will.
My workflow is tab-heavy. I often have six to twelve AI sessions open at once, each doing something different…
Read more