Working With AI · Method

One shared brain, several independent hands

I am not a highly disciplined person. Low energy, scattered thinking, and a perfectionist streak. Over ten years I tried every mainstream knowledge-management method and none of them ever really ran, because they all assume someone willing to maintain them daily, and I am exactly the kind of person that assumption filters out. This page describes the one that finally worked, including the parts still unsolved.

10 yrsof failed attempts first
5 stepsfrom voice note to finished piece
4 thingsdeliberately given up
2 columnsdelegated vs. kept
5 skillspackaged as portable agents
00 PREMISE

The problem was never the tool, it was the assumption

PARA, Zettelkasten, every template system out there. They are all good, and they all assume one thing: the user is willing to maintain them daily. Every time I built a system I also quietly demanded that I become a more disciplined, more efficient person along the way. So once the system got complex and I could not keep up, I blamed myself and abandoned it. Again and again.

This time I changed the premise: instead of demanding I become a different person, redesign the process so the maintenance cost moves entirely to AI. I keep only two things, input and judgement.

The three layers below solve, from the bottom up: can material survive at all, will perfectionism jam the process, and what must never be handed over.

01 PROCESS LAYER

Let the material survive first

The whole chain is five steps, and the first two are deliberately thought-free.

Just dump itVoice notes, screenshots, messages to myself, no sorting
Weekly InboxOne basket per week; let material survive first
Weekly EditorAI reads the week and judges what could become an article
Semantic searchConnects something written two years ago to today
Finished work returnsPublished pieces go back into the vault as next round's input
The last step is the one that matters Once finished pieces flow back in, the vault stops being a pile of other people's sentences and becomes things that grew through my own thinking and life. A pile of clippings suffocates you. A pile of your own finished work does not.
02 RULES LAYER

Four constraints that keep perfectionism from jamming the process

I never touch Obsidian directly

A hard rule I set for myself: every edit goes through Claude Code or Codex. That leaves exactly two entry points, with sorting, naming, filing and writing handled by AI, so I never start "fixing" a category and get stuck in perfectionism again.

Four things I gave up

No complete tag taxonomy, no correct classification up front, no full source attribution, no maxed-out tool stack. Four times I let go in the same place. A working imperfect system beats a perfect one I never dare to touch.

No tag table to maintain

Topics keep growing, so a fixed taxonomy eventually becomes a burden. With semantic search, older entries written as "East Asian family," "intergenerational trauma" or "mother-daughter" all get gathered under the same question.

The system sits downstream, not in judgement

I once built two tidy writing systems, and the piece I liked most that month was dictated into my phone. The more systems I built, the more I feared writing, because they had moved between me and my own voice. Now the system is a tool I use when I want to.

03 BOUNDARY LAYER

What I hand over, and what I keep

Expression comes in two kinds. The sayable consensus has been said by countless people, can be flattened and can travel. The unsaid specific grows inside one person's particular life and was never indexed. AI became what it is by swallowing the entire library of the sayable, which is why it is so reassuring in the first kind. It has never been inside your life.

The sayable consensus

  • Structural scaffolding: outlines, logic, transitions
  • Breaking blank-page anxiety by reflecting the mess back structured
  • Red-teaming: verbal tics, gaps in reasoning
  • Polishing grammar and rhythm
  • Variant drafts (what is handed over is generation, not decision)

The unsaid specific

  • Private experience that was never indexed
  • Judgement and taste: whoever decides what stays and what goes
  • Strange but true descriptions (creation deviates from the mean)
  • Delivering a thought that has not been spoken yet
  • The felt sense of "does this read like me"
Give the world to the machine, and keep yourself.
04 STILL OPEN

A trap I fell into

When the style guide is too complete, the output carries a machine accent Lock the rules down and the model just fills them in, losing voice first. I now write style guides as guardrails rather than templates, meaning I only write what to avoid, not what to produce. This one is still open.

I leave it here because a method that only records its successes is worth nothing to anyone else. This system runs, and it runs with this known defect.

05 OUTPUT

What the system produced

Both series live on 紫海盐, including the parts that did not work.

06 SAME JUDGEMENT

I apply it to product work too

The logic behind my own system is "rather than demanding I become a disciplined person, redesign the process so that constraint stops mattering." When the product hit unstable agent generation quality, I did the same thing: instead of waiting for the model to improve, I changed the contest to judge prompts and backstories, routing around the generation layer entirely.

The judgement is identical in both cases. The constraint is not going away soon, so redesign the process until it stops being the bottleneck.

Read the creator ecosystem case →