> For the complete documentation index, see [llms.txt](https://www.isaacbowen.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.isaacbowen.com/2025/05/22.md).

# 20250522

not as simple as just a fractal, but

well, but you get what you expect

and if you can work and weave your expectation-set around such that it *produces* a fractal, you'll have something you can navigate in a way that's meaningful to you while still letting the system satisfy its own requirements around you, all without breaking your own experience of immersion

***

dye my hair?

(this is a contrived example to demonstrate a pattern; I do this kind of thing basically everywhere *except* my hair, lol)

dye my hair? only at intervals, all of it at once, but lightly, such that each session accumulates, showing the staggered rhythm of history aggregating down the length of my hair, the color getting stronger the further you get from the root

I don't do things that require constant touch-up to restore the effect of never having been any different

I think the underlying idea is that I want everything to be zero-knowledge debuggable and zero-knowledge maintainable, and that means showing your work

if I'm world-debuggable, then help can come from anywhere

***

intent is how we get things across long distances

across long distances \*intact

see: golf


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://www.isaacbowen.com/2025/05/22.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
