does your AI give you the same answer it gives everyone else?
that's what a GENERAL intelligence is built to do. it serves everyone, but no 2 humans are the same.
your AI is an extension of you, your skills. the more it knows how you think, the better it serves YOU. so aim for A-P-I: Artificial Personalized Intelligence.
what makes an AI yours
a profile it reads first. who you are, what you do, how you talk. without it, every chat starts from almost zero on you, or from a hazy, irrelevant memory your AI stored over time.
your edits. every correction you make is a suggestion or rule it missed. have your agent log what you change and the things it gets wrong constantly, and have it learn from them.
how firmly you meant it. "i like" is a preference. "never" is a rule. spell out the weight behind your words so 1 offhand comment doesn't become a law your AI applies everywhere because it thinks you meant it.
memory you can open. if you can't read it and delete a line, you don't control what it thinks it knows about you. most LLMs now have a memory log in settings. review it, and have your AI edit or delete what's wrong.
how i do it
this is the worked example, from my own setup.
my AIs pull new and updated context about me from my vault whenever they work on a task: who i am, what i do and how i write. plus a behavior doc that tells them how to act with me. all of these are graph folders that update automatically from what i do, say and work on with Claude.
my Claude logs the way i talk to it, verbatim, in a ledger. so it knows i say "algo" not "algorithm", that i curse a lot when i'm angry, when to push back, and when not to test me and just get the job done.
it also weighs how firmly i said something: a gesture, a preference, a practice or a rule. when i said my emoji count is "circumstantial", it stopped flagging posts with 5 emojis as "you used too many emojis. was this deliberate?" while running analysis on my content.
it has ~500 memory files from working with me. every one is a file i can read, review, and tell it to update or delete if it's wrong.
and when i correct the same mistake more than twice, it becomes a guard: Claude double checks itself on that before any output.
[it sounds like a robust system. it started because re-explaining yourself every session is a waste of your time]
a real one from my workflow
my Claude prepped a first draft of my interview article with @suavecito585. i edited it and rewrote it my own way.
then i pasted my version back and told it to take notes on every correction i made.
it came back with 4 new rules it could record, and 3 it already had that the rewrite confirmed again. some of them:
arrows only for real lists. the story parts became short paragraphs. arrows stay for lists like his repo features
every name gets its @ X handle. including the person in the comments who asked questions
links get words. a "Github" you can tap, never a long bare URL
all of it went into my article notes, which my Claude reads before it drafts the next article.
try it on your next AI draft:
edit it until it sounds like you
paste your version back and say: "list every change i made and the rule behind each one"
save those rules where your AI reads them first: custom instructions, a CLAUDE.md or a project file
start yours in 1 command
i open-sourced my personalization protocol: agent-personalizer
with your permission, it reads your last 20 sessions (only what you typed), then your AI asks you up to 5 questions like "you've asked me to shorten replies 3 times this week. make it a rule?"
from then on, the 2nd time you correct the same thing, your AI asks if you want it saved as a rule
it writes the file each AI reads: Claude Code, Codex, Cursor, Gemini, whatever you use
it teaches your AI how firmly you mean things, so a throwaway comment about one session doesn't become a hard rule
it runs on your computer, so your info stays between you and your LLM
npx agent-personalizerneed to change something later? edit LEARNED.md (or tell your AI), then run it again. it updates its own files and keeps your edits.
your homework
ask your AI to describe you in 3 lines. if that description could fit 1000 people, it's not personalized yet 👀
then answer the questions in the installer and ask it again.
read it on the site too:
if you want 1-on-1 help from me... book a call here:
a call to set your AI up around how you actually work, with a profile, rules and memory you can open
all my calls are here:
hope this helps
SEE YOU ON THE NEXT ONE!
- AUNY 🧡