Personal Knowledge Base: Four Types of Materials Collected Over a Year, and How They Became a Library I Can Query
A year ago, my materials were scattered: course slides in the Downloads folder, translations on the desktop, notes in the notes app, and formatting requirements buried in group chats. When I needed to write something, I remembered having “seen it,” but I couldn’t find it.
Now they are in one library. This post is about how the four types of materials go in, how I ask questions once they are in, and how I get back to the source.
Four Types of Materials, Three Ways of Handling Them
Course slides and handouts. These are the easiest: I file the whole document in. They are my “background layer,” and their purpose is to save me from having to look things up in textbooks again when I ask a basic question.
Literature I have read (including translated drafts). I only put in what is relevant to my research topic, not the complete set. My criterion is “Will I cite this?”—if I will cite it, it goes in; if I only read it, I record it in a literature log and do not add it to the library.
My own notes and experiment records. This is the most valuable category in my library, and the only one that must not be lost. I name them by “date + topic,” not with words like “inspiration” or “jotting”—the latter become junk after three months.
Specification documents (templates, formatting requirements, procedures). I do not consult these often, but when I do, it is urgent. After adding them, I no longer ask “What does the school require for figure captions?” but “What do my materials say about figure caption requirements?”
My Three Filing Rules
1. Use a consistent naming convention, or I won’t be able to find them when I ask questions.
2. Control granularity: whole files go in; no excerpt-style ingestion—excerpts lose context.
3. What does not go in: other people’s unpublished data, confidential corporate materials, and raw audio recordings.
How I Ask Questions
I ask, “What do my materials say about [something]?” rather than “What is [something]?”
The difference between these two ways of asking matters: the former requires it to return to the materials I uploaded, with answers that carry sources and can be traced back; the latter is asking for general knowledge and has nothing to do with my library. The official website describes this area as “supporting the collection of materials in multiple formats, and retrieval and questioning around one’s own knowledge accumulation,” with the emphasis on “one’s own” and “tracing back to sources”—that is, retrieval questions must be grounded in one’s own materials, not public knowledge.
Boundaries and Costs
· The library will not proofread for me. If something I wrote incorrectly goes into the library, it will still answer me according to my incorrect wording.
· The library is not a safe deposit box: I do not put classified or unpublished material into it.
· Cost: Q&A is charged by credits, and long-document retrieval costs more than short Q&A. So I split it into two tiers: frequently asked items go in the library, and occasional items stay local.
· The smoothest combination I have used together: materials are first managed by MuchSci’s personal knowledge base; when writing, I hand the passages selected from the library to MuchSci’s office assistant agent to lay them out as an editable document; where I need to add literature, I use MuchSci’s paper search assistant to look up DOIs and citation information.
· I clean the library once a month: delete what is wrong and mark what is outdated. The most easily overlooked step in this whole matter is cleanup—the larger the library, the more it needs someone to regularly delete things.
The value of materials is not in how much I have stored, but in whether, the next time I need them, I can find them and get back to the source within three minutes. This year my library grew by only a little over a hundred files, but my writing speed has indeed changed.
This is also where I think a graduate student AI assistant truly saves time: not by thinking for me, but by keeping things for me.