Where things go, and how the agent keeps track of a project for you.
The questions are mine; the answers are yours. Everyone already has a filing system. It just isn’t written down.
my-paper/
├── AGENTS.md the rules, for the agent
├── README.md for people: what this is, how to rerun it
├── STATUS.md where we are, what's next
├── manuscript/ everything that ends up in the PDF
├── code/ everything that computes
├── results/ the numbers the paper relies on
├── dev/ notes, drafts, talks: in git, not published
└── local/ downloaded papers, raw runs: not in git
My four answers: AGENTS.md, STATUS.md, dev/, and manuscript/ with results/. It’s a skill: every new paper starts like this.
| In git and on GitHub | Published | |
|---|---|---|
manuscript/ code/ results/ |
yes | yes |
dev/ |
yes | no |
local/ |
no | no |
dev/ is work in progress: backed up, and your co-authors see it.local/ is listed in .gitignore, a text file that tells git what to leave alone. PDFs you may not share, big raw files.Here is how I work: [your four answers]. Propose a folder structure for this paper and a project file that says where things go. Show me first; don’t move anything.
Argue with it. Then “Go ahead”, and “Commit” if you use git.
At the end of each session, add what we did and what’s next to notes/log.md.
Keep literature/notes.md: one paragraph per paper we read, with the pages that matter.
Next time, start with:
Read the project file and the log, then tell me where we left off.
AGENTS.md in the folder. Both tools read it at every start.
More: the project file.
Memory is the AI remembering you. A skill is you writing it down.