---
type: case-study
slug: duodecim
client: Duodecim
clientUrl: 'https://www.duodecim.fi'
clientIndustry: Healthcare / Medical publishing
title: Building the future of medical knowledge search
summary: >-
  D-Haku, a next-generation hybrid search engine for 100,000+ medical documents
  — used daily across Finnish healthcare to navigate complex clinical questions
  in their native language with answers Finnish doctors can trust.
tags:
  - Search
  - LLMs
  - RAG
  - Product Design
  - NLP
  - Medical
year: 2025
status: live
heroMedia:
  type: image
  src: /work/duodecim/hero.jpg
  alt: Duodecim D-Haku search interface
cover:
  src: /work/duodecim/duodecim-cover.jpg
  alt: Duodecim case study cover
bento:
  images:
    - src: /work/duodecim/bento-5.png
      alt: DuoAI
    - src: /work/duodecim/bento-2.jpg
      alt: Medical professional
    - src: /work/duodecim/bento-3.jpg
      alt: Illustration
    - src: /work/duodecim/bento-4.jpg
      alt: X-ray of a chest
    - src: /work/duodecim/bento-1.jpg
      alt: Medical professional
testimonials:
  - quote: >-
      Working with Intentface has been excellent, and we saw results quickly,
      which has led to an expansion and deepening of our collaboration.
    name: Samuli Asmala
    title: 'CTO, Kuura Health / Duodecim'
    avatar: /work/duodecim/samuli-asmala.jpeg
  - quote: >-
      We've built the foundations for Duodecim's generative AI journey together
      with Intentface. Their expertise in building AI-powered search solutions
      has been invaluable as we navigate the evolving landscape of medical
      knowledge delivery.
    name: Jani Tikkanen
    title: 'CEO, Kuura Health / Duodecim'
    avatar: /work/duodecim/jani-tikkanen.jpeg
stack:
  ai: >-
    Multiple embedding models, reranking models, RAG architecture, hybrid
    search, custom Finnish lemmatizer, evals
  implementation: 'TypeScript, React, Node.js, Python'
impact:
  - >-
    Together with Duodecim we're creating the new standard for Finnish medical
    knowledge search. The hybrid approach ensures both precision for specific
    medical terms and understanding for complex clinical questions — handling
    Finnish language challenges while maintaining the reliability and speed
    critical for healthcare decision-making.
featured: true
hidden: false
publishedAt: '2025-04-01'
updatedAt: '2026-05-12'
---

> [Interactive: CaseIntro]


> [Interactive: ApproachCard]


> [Interactive: VideoLoop]


## What D-Haku does

> [Interactive: Row]


## Trust between medical professionals and AI

> [Interactive: MediaSplit]