PWV Portfolio Feed

if you're using coding agents seriously, curious what surprised you most about how your workflow actually changed.

here's what i didn't expect: rebuilding old projects to teach Command Code my taste is more valuable than i thought. each one reinforces patterns i want the agent to know. not because my way is universal, but because consistency matters when you're working at this pace.

the result isn't just speed. it's that i can trust the output without the usual "let me rewrite half of this" step. i'm shipping a project most days now because the friction dropped to nearly zero.

what changed: the agent actually learns how i code. my guard clause preference. my CLI patterns from 200+ tools over 10 years. functional style. it picks up my architecture decisions without me explaining them every time.

stopped watching TV lately. not because i'm disciplined. because building with coding agents (Command Code) became more interesting than Netflix.

sounds absurd. but i'm polyphasic. wake up twice a day. used to split it: once for work, once for TV. now both sessions are building sessions.

⌘ let's go!!

applescript and shell logic is preserved as searchable text. rich text is stripped to plain text. no manual exports. no noise. no leaks.

$ 𝚗𝚙𝚡 𝚝𝚎𝚡𝚝𝚎𝚡𝚙𝚊𝚗𝚍𝚎𝚛-𝚝𝚘-𝚛𝚊𝚢𝚌𝚊𝚜𝚝

if you are optimizing your local setup, this should save you quite a few gradient descent steps.

$ 𝚗𝚘𝚍𝚎 -𝚎 "𝚌𝚘𝚗𝚜𝚘𝚕𝚎.𝚕𝚘𝚐(𝚛𝚎𝚚𝚞𝚒𝚛𝚎('./𝚜𝚗𝚒𝚙𝚙𝚎𝚝𝚜.𝚓𝚜𝚘𝚗').𝚕𝚎𝚗𝚐𝚝𝚑 + ' 𝚜𝚗𝚒𝚙𝚙𝚎𝚝𝚜')"

review overfitted data separately:
$ 𝚗𝚙𝚡 𝚝𝚎𝚡𝚝𝚎𝚡𝚙𝚊𝚗𝚍𝚎𝚛-𝚝𝚘-𝚛𝚊𝚢𝚌𝚊𝚜𝚝 𝚜𝚞𝚐𝚐𝚎𝚜𝚝𝚎𝚍

- merge: relational uuid join of snippets and groups.
- filter: drop overfitted suggested snippets by default.
- mapping: deterministic type conversion and text stripping.

verification is built-in. check counts via node one-liners:

i wanted a clean migration with zero manual export. no xml fiddling or leaky suggested snippets. read weights directly from source plist and map to raycast json.

built using command code with my cli taste.

technical pipeline:
- access: direct binary plist reading via application support.

textexpander acts as an overfitted model on your keystrokes. it memorizes passwords, tokens, and private data. high entropy noise.

$ 𝚗𝚙𝚡 𝚝𝚎𝚡𝚝𝚎𝚡𝚙𝚊𝚗𝚍𝚎𝚛-𝚝𝚘-𝚛𝚊𝚢𝚌𝚊𝚜𝚝

introducing 𝚝𝚎𝚡𝚝𝚎𝚡𝚙𝚊𝚗𝚍𝚎𝚛-𝚝𝚘-𝚛𝚊𝚢𝚌𝚊𝚜𝚝 ⌨️

convert textexpander snippets to raycast snippets.

i used textexpander for a decade but started switching to raycast. only problem was migrating 1500+ snippets.

'apple in china' was a crazy read and so i'm pretty intrigued to find out if it's going to be mostly manufactured in mainland china / india / somewhere else. probably china, though.

tech enthusiasm: the apple macbook neo looks cool, actually, i'd get one in a number of circumstances. the price is impressive, though it probably has a ton of factory-labor skullduggery behind it. the macbook is overkill for most people anyway.

one thing that really radicalized me is realizing that the "ability to accept gigantic investments" is a feature of companies like this for huge investors who have to invest a ton of money and don't want thousands of companies in their portfolio, which helps this agglomeration happen

Know a woman building cool stuff with AI? Drop a link. 👇

AI is the new unfair advantage.

The same person with AI can research faster, write faster, code faster, and ship faster.

The gap will not be small. It will compound daily.

People who adopt early will look unstoppable later.

Are you building with AI yet?