On March 2^nd, the Library Navigator went live across the Kyyti library network: seven municipalities, 18 branches, 165,000 residents in southeastern Finland. Patrons can now receive recommendations for books, films, and music based on their loan history, ask library questions in their own language, and do it all at 2am on a Sunday if that’s when the mood strikes.

This post is about how we got here.

Built with a real library from day one

We built the Navigator with Kyyti as a development partner from day one. When we launched the first version, a helpdesk chatbot, in March 2025, it was Kyyti patrons who told us what worked and what didn’t. Kyyti librarians flagged when a conversation flow confused them or when the system needed to handle a question type we hadn’t anticipated.

That feedback loop shaped everything. Librarians ran hands-on testing sessions and gave us the kind of blunt, practical insights that no amount of internal QA can replicate. Mikko Vainio, Library Director at Kotka, backed the project from the start and helped us navigate the institutional side as well as practical choices such as the AI tone of voice.

“I believe AI will free us up to focus more on meaningful work.”

Mikko Vainio, Library Director at Kotka

Over the course of 2025, the helpdesk handled roughly 4,800 patron conversations without requiring staff intervention. That track record gave us, and the library, the confidence to go further.

The recommendation engine: solving the long tail problem

The headline feature of the Navigator is its new book recommendation system, which took a year of development. When a patron grants permission, the system reads their loan history and identifies patterns. It picks up on taste, not just genre labels. The difference between “I liked that thriller” and “I want something with the same atmosphere but faster paced” is exactly the kind of nuance the Navigator handles.

But the real value is in the long tail, the thousands of titles in a library collection that rarely surface through catalogue browsing or bestseller lists. New releases sell themselves (the hold queues prove it). The Navigator’s strength is in surfacing the award winners from a decade ago, the overlooked gems that a librarian loved in 2018, the books sitting on shelves right now, available immediately, no queue required.

Traditional recommendation engines optimise for popularity. The Navigator optimises for fit. That means your collection works harder and patrons leave with something they didn’t know they wanted. (Read more in the Navigator product page.)

Pekka Väisänen, a library automation expert with decades of experience in Finnish library systems, sees the technical integration as significant:

“What makes this interesting is the depth of the ILS integration. This isn’t a chatbot sitting on top of a catalogue — it’s reading loan histories, checking real-time availability, by connecting directly with Koha and Finna. That kind of deep connection between AI and library infrastructure is genuinely new territory for libraries.”

Pekka Väisänen, library automation expert

GDPR: solving it meant solving it for everyone

No one had done this before in Finland, or anywhere in the EU. An AI system that processes patron loan histories to make personalised recommendations raises legitimate questions, and we heard every one of them.

Conversations with Data Protection Officers (DPO) were thorough, sometimes lengthy, and always productive. We explored a wide range of GDPR scenarios: does this data point constitute PII? What if library needs audit trails for security incident detection? What about conversation logging with a fixed retention window, or not saving conversations at all? For each scenario, we found a technical solution that satisfies the requirements. The result is a system that can be configured to match whichever privacy posture the municipalities’ DPO agree on.

The baseline is firm, but the details matter. Getting this right took time. It was worth it.

What patrons are saying

The first days have been encouraging. Many patrons tried the loan history analysis for the first time, and the reactions have been enthusiastic. Through our feedback form and the thumbs-up/thumbs-down system built into the interface we are collecting feedback, and we’re hearing things like:

“Feels like magic.”

“It found themes and patterns in my loan history that I would have never found out myself!”

That second quote captures something we designed for. The Navigator reads across a patron’s borrowing history and finds connections that aren’t obvious on the surface. A reader who borrows Nordic noir, cosy fiction, and Japanese culture guides has a rich, layered taste. The system sees that and recommends accordingly, rather than treating each genre as a separate bucket.

Always on, in every language

The Navigator works around the clock without requiring staff coverage. This matters for libraries that can’t resource chat support, and it matters for residents who are more comfortable in a language other than Finnish.

Patrons can ask in Finnish, English, Swedish, Sámi, Somali, Ukrainian, and dozens of other languages, and get responses in the same language. No separate “English version” to maintain. No language menu to navigate, as the Navigator picks up browser language as starting point. Just a conversation in whatever language feels natural.

For communities with new residents, immigrant populations, or anyone who simply thinks more clearly in their first language, this removes a real barrier. Multilingual support is built into how the system works. (Read more in the Navigator product page.)

What’s next

The Navigator is live, but we’re still building. Our roadmap is shaped by what we hear from Kyyti’s patrons, staff, and all the future customers of this new system.

“Kyyti taught us how to build this properly — with real patrons, real librarians, real privacy constraints. We’re proud of what came out of that year. Now we’d love to do it again with other libraries, and every new partner gets to start from where we finished.”

Andrea Balzarini, Biblioworks.ai

If you’re a library director curious about what this could look like for your network, we’d welcome the conversation.

Book a 30-minute demo and we’ll show you the Navigator working with real library data.

Or try it yourself at kyyti.finna.fi — the Navigator is the chat icon in the bottom right corner.

The Library Navigator is built by Biblioworks.ai, a Finland-based team specialising in AI for public libraries. Read more about the Library Navigator. Read more about the launch on the Kyyti library blog and the Kotka city website.

A short post to notify of a semi-public beta testing of The Library Navigator.

You can visit the Finna preview of the Library Navigator at Kyyti Library Network and evaluate the latest release. To begin, click on the helpdesk, bottom right of the webpage.
If you want to test the book suggestions based on the loan history, please send a message to   loading…