Case Studies / apoQlar
MEDTECH · INTERNAL PROCESS AUTOMATION
Replacing manual document search with a GenAI-powered virtual assistant
apoQlar’s support and operations teams were spending significant time manually searching through hundreds of product documents to answer customer and institutional inquiries. We built a generative AI assistant that lets them ask questions in natural language and get precise answers – with source references – in seconds.
Client: apoQlar GmbH – a MedTech company developing mixed reality solutions for healthcare.
KEY RESULTS
Instant
Natural language answers from hundreds of internal documents
Sources
Every response includes references to the original document
RAG
Vector database for fast, relevant information retrieval
Conv.
Stateful conversations with optimized context management
INDUSTRY
MedTech
USE CASE
Internal document retrieval & Q&A
AI APPROACH
LLM + RAG + vector database
USERS
Support & operations teams
DOCUMENTS
Product docs, reference materials
KEY FEATURE
Source-referenced responses
The challenge
apoQlar develops mixed reality solutions for healthcare – products that come with extensive technical documentation, product specifications, regulatory materials, and reference guides. When the support team received a customer inquiry or an institutional request, finding the right information meant manually searching through hundreds of documents.
This was slow and inconsistent. Different team members might find different information – or miss relevant details entirely. The time spent searching was time not spent actually helping customers or preparing documentation.
The core problem: critical product knowledge was locked inside hundreds of documents. Getting answers required manual search, and the quality of those answers depended entirely on how much time someone had and which documents they happened to check.
What we built
We built a generative AI virtual assistant that sits on top of apoQlar’s internal document base and lets team members ask questions in natural language – just as they would ask a colleague who had read every document.
Vector database for retrieval. All internal documents were processed, chunked into logical sections, and embedded into a vector database. When a user asks a question, the system retrieves the most relevant passages with minimal latency – far faster and more precise than keyword search.
Source-referenced responses. Every answer includes references to the specific documents and sections it drew from. This was a deliberate design decision: in a MedTech context, the team needs to verify and cite their sources, not just trust an AI-generated response. The reference system builds credibility and makes the assistant’s output directly usable in customer-facing communications.
Optimized context management. Conversational AI systems using long documents quickly hit context window limits. We built a system that maintains conversation state while keeping only the most relevant information in the prompt – optimizing both accuracy and response latency without losing the thread of multi-turn conversations.
Specialized text processing. Product documentation doesn’t come in clean, uniform formats. We developed custom processing methods to extract, clean, and logically group text from diverse document types – ensuring the retrieval system works reliably regardless of how the original documents were structured.
The results
BEFORE
Manual search through hundreds of documents for every inquiry. Slow, inconsistent, and dependent on individual team members knowing where to look.
AFTER
Natural language Q&A with instant, source-referenced answers from the entire document base. Consistent, verifiable, and available to the whole team.
The support team moved from manual document search to instant, conversational retrieval. Response times to customer and institutional inquiries improved significantly. The source reference feature meant that answers could be trusted and cited – critical in a regulated MedTech environment.
Beyond the immediate efficiency gains, the assistant created a new way for the team to interact with their own knowledge base – surfacing connections between documents that manual search would have missed, and making the organization’s accumulated product knowledge accessible to everyone, not just the people who’d been there the longest.
Technology used
“
The GenAI-powered virtual assistant has been a game-changer for our internal support team. It revolutionized the way we access and utilize information from our vast document base.
apoQlar GmbH
MedTech, Hamburg
More Case Studies
See how we’ve helped other companies
AUTOMOTIVE · LEADING LUXURY MANUFACTURER
Intelligent virtual assistant replacing manual planning queries across SAP and cloud systems
Product planners spent hours manually querying SAP BW and multiple data warehouses for every decision. We built a bilingual voice-and-text assistant that retrieves planning data on demand – no system expertise needed.
Hrs → Sec
Data retrieval
DE + EN
Voice & text
SAP BW
Integrated
MANUFACTURING · RADAWAY
Making email-based order processing reliable with LLMs
Staff were manually reading customer emails, identifying products, and entering orders by hand. We turned a promising AI prototype into a production system that handles it end to end, across languages, formats, and attachments.
-90%
Manual intervention
95%+
Match accuracy
LOGISTICS · FR. MEYER’S SOHN
Eliminating manual data extraction from thousands of daily shipping emails
Operations staff were manually reading German and English logistics emails to pull out routing and scheduling data, every single day. We built an AI pipeline that extracts, structures, and delivers the data automatically.
–80%
Manual effort
2 langs
DE & EN
On-prem
Deployed