if you use more than 1 AI, you probably copied the same instructions file into all of them.
that one big rules file doesn't work the same everywhere. your AIs don't all read the same file, format or folder. and they don't all read the whole thing.
so before you add another rule, have each AI look up its own official docs and tell you what it needs from you.
why one big rules file breaks
every AI tool has its own rules about instructions:
- which file it looks for
- where that file has to live
- how much of it it will load
the last one is the sneaky one. Antigravity (Google's AI coding CLI that runs Gemini) reported from its own docs that it stops reading a rule file past 24,000 bytes.
Grok, on the other hand, reported no size cap at all. same instructions, totally different limits.
the worked example: Auny's main rules file was 88,682 bytes, copied over to every tool as-is. that's one reason an AI can seem to ignore a random instruction it knows to follow.
[have you ever checked how much of your claude.md or agents.md your AI actually loads or reads? ask your AI]
have each AI read its own manual
the fastest way to find each tool's limits is to ask the tool. its own official docs know what it loads.
here's how Auny ran it. she sent 5 of her AI CLIs the same job at the same time: read your own official docs, then report which instruction file you load, where it lives and why you sometimes skip instructions, quoting the source.
each one came back knowing a limit the others didn't. they even caught each other's mistakes: one flagged that another AI's instruction file pointed at the wrong folder.
then she told them to optimize their own instruction files: keep the personal context they need intact, and truncate the instructions to make them more AI-friendly.
Codex went from 88,682 bytes to 26,938 bytes, and in a fresh chat it still quoted her standing rules word for word.
you can run the same thing. have your agent do this:
read your own official, current docs (release notes, change log, API docs, official blogs etc.) tell me which instruction file you load, where it has to live, how much of it you load, and what you need from me in it. quote the source for each answer
run a test
this part works even if you only use 1 AI.
open a fresh chat with no tools and ask:
quote the 3 most important rules from your instructions file, word for word
if it quotes them, the file loads. if it can't, or it makes rules up, that file probably isn't reaching it.
why no tools? with tools it can go open the file and read it to you, which proves nothing about what it carries into every chat.
the most trustworthy answer in Auny's run came from Hermes, the one AI she ran with no tools at all. instead of guessing, it wrote "UNVERIFIED" for every section. that's the report to trust, because it means it didn't hallucinate.
what to do today
- ask your AI which instruction file it reads and how much of it loads every session
- run the 10-second test in a fresh chat
- if anything comes back cut off or made up, shorten that file first
your rules only work if they load. run the test before you add another one.
1:1 call · matches this post
AI Workflows for Creators
want your instruction files set up so every AI you use loads the part that matters? That's the AI Workflows for Creators call.
