Skip to content

studenti.rs

A student community in Serbia, online since 2008. I built it at my first job, bought it back in 2022, and rebuilt it this year.

Running · 2008 to now · Original developer, then owner and sole developer

studenti.rs (opens in a new tab)

Registeredstudents
250k
Documents
40k
Online since
2008
The site today: searching, then opening a document.
studenti.rs in April 2010: a plain white page with the logo beside black silhouettes of students, a grey menu bar, a list of new papers and a list of categories.
2010, the earliest copy in the Web Archive.

A loop in five steps: a student uploads notes, it is checked and sorted, it becomes a page, search finds it, and another student opens it, which leads back to the first step. The library grows and stays clean without anyone reading uploads by hand. What still reaches me: uploads the final check is unsure about, held until I look; lifting a flag from an account; an alert when an upload gets stuck.

The whole picture

The library grows and stays cleanwithout anyone reading uploads by hand.

  1. StudentA student uploads notes
  2. Our AIIt is checked and sorted
  3. AutomaticIt becomes a page
  4. AutomaticSearch finds itGoogle + site search
  5. StudentAnother student opens it

What still reaches me: uploads the final check is unsure about, held until I look; lifting a flag from an account; an alert when an upload gets stuck.

The whole loop. The next squares show each part.

A flowchart in three lanes: the student, the system and me. The student uploads a file. A model asks if it is study material; if not, it is refused on the spot. The student confirms the details. An automatic check asks if it is a copy; if so, it is binned, and a strike. A model asks if it is good enough: if not, it is binned; if it is not sure, I decide; if yes, it is published now or on a future date. Published, the student is rewarded and told.

From upload to published

Every upload is checked, sorted and published without waiting for a person.

  1. Student: Uploads a fileAny office format. Nothing is public yet.
  2. The system, a model, asks: Study material?Junk and spam stop here.If no, it is refused on the spot. If yes, it goes back to the student.
  3. Student: Confirms the detailsTitle, subject and summary are written for them.
  4. The system, automatically, asks: A copy?The same notes cannot be uploaded twice.If yes, it is binned, and a strike. If no, it goes on.
  5. The system, a model, asks: Good enough?Clear cases never need me.If yes, it goes on. If not sure, it comes to me. If no, it is binned.
  6. Me: I decideHeld until I look.
  7. The system, automatically: Publishes now, or on a future dateThe library grows a little every day.
  8. The end: Published. The student is rewarded and told.
What happens to one upload, and why each check is there.

A pipeline. A student uploads any office file: Word, PowerPoint, PDF or another format. It is converted to a PDF, its words are extracted as Markdown, and a web page is published. One branch sends the Markdown to the site’s search index. All 45,000+ older documents were re-run. 7,000+ were removed: duplicates, low quality, or material that should never have been public.

From upload to web page

One upload becomes a page anyone can find.

  1. Any fileWord, PowerPoint, OpenDocument, RTF or PDF: whatever the student has.
  2. PDFEvery file is turned into a PDF, so each one is handled the same way.
  3. MarkdownThe words are read out as plain text. A model writes the title, summary and keywords from it.
  4. PageThe free pages become a real web page that search engines and AI assistants can read and quote.
  5. Search indexThe site’s own search reads the Markdown copy, so students can search by meaning, not only by exact words. About 37,500 Markdown files.
  6. Re-runAll 45,000+ older documents were re-run. 7,000+ were removed: duplicates, low quality, or material that should never have been public.
Any file a student uploads becomes a readable web page on its own, and its text feeds the site’s search.

Search, before and now. Before the rebuild, search matched titles and page text; the rest of a document was not searched. Now search reads whole documents and understands meaning, so a query can find a passage that says the same thing in other words. Before, 1 in 10 searches ended with the student finding what they wanted; 7 in 10 do today.

Search, before and now

Search now looks inside the whole document, not only at its title.

Before

Search matched titles and page text.

Now

Search reads whole documents and understands meaning.

1 in 10searches ended with the student finding what they wanted.

7 in 10do today.

What search could see before the rebuild, and what it sees now.

A count. The old library was a mess: badly written titles, missing tags, a catch-all subject and documents under the wrong institution. Then 38,263 documents were sorted by institution in January 2026. 20,672 matched from the text, 101 by reading the whole PDF, 57 still ambiguous, 15,367 with no institution named in the text, 2,066 with none confirmed from the PDF.

Sorting the library

The old library was a mess: badly written titles, missing tags, a catch-all subject, and documents filed under the wrong institution.

38,263Documents sorted by institution, Jan 2026

Documents sorted by institution, Jan 2026
GroupDocuments
Matched from the text20,672
Matched by reading the whole PDF101
Still ambiguous57
No institution named in the text15,367
No institution, confirmed from the PDF2,066
In five days 20,773 documents were linked to their institution; the rest were left blank instead of wrongly filled.

Before and after. Before the clean-up about 40% of documents were filed under the wrong institution; on 21 January 2026 none were, after 15,237 wrong links were removed. Filed under the right one: 35.7% before, 54% after. The other 46% never name an institution in their text and are left blank, not guessed.

Filed under the wrong institution

No document is filed under the wrong institution any more.

Before the clean-up
about 40%
After, 21 Jan 2026
0

15,237 wrong links removed.

Filed under the right one

Before the clean-up
35.7%
After, 21 Jan 2026
54%
The other 46% never name an institution in their text. They are left blank, not guessed.
About four in ten documents were filed under the wrong institution. Now none are.
A studenti.rs document page: a seminar paper on motor vehicle brakes, its first page beside a panel with the reading time, the page count, a summary, tags and the institutions it belongs to.
A document page: what a student comes for.

A flowchart in three lanes: the student, the Grok bot and me. Every day a student writes to info@: questions, payment reviews. The bot reads and sorts the mail and asks if it is simple. If yes, it checks the facts and replies in the site’s own voice, and the answer is sent without me. If not, I answer what it hands me: refunds, goodwill, billing disputes and legal.

Customer service, done by Grok bot

Simple questions get an answer without waiting for me.

  1. Student: Writes to info@Questions, payment reviews
  2. Grok bot, a model: Reads it and sorts it
  3. Grok bot, a model, asks: Simple?Cancelling, deletion, “we’re checking”If yes, it answers on its own. If no, it hands the mail to me.
  4. Me: I answer what it hands meRefunds, goodwill, billing disputes and legal
  5. Grok bot, a model: Checks the facts before it writes
  6. Grok bot, a model: Replies in the site’s own voiceShort paragraphs, the informal “ti”
  7. The end: Answered and sent, without me.
A Grok bot answers questions and reviews payments every day, without me.
The home page on a phone.