Self-service reports issued monthly
650+Source systems unified
8Median query response time
< 15 s
The customer is an Austrian healthtech startup that turns supply-chain and pharmaceutical data into clear analytics. The company earned European Health Innovation Forum recognition for secure data governance and rapid rollouts across university procurement hubs. As its customer base of pharmaceutical buyers grew, the platform had to ingest, process, and present millions of transactional records per day without a hint of delay.
Each procurement team required live price and inventory updates within seconds, while analysts needed the same data for retrospective cost reviews. Once the platform expanded to new organizations, response times slipped, dashboards froze, and complex SQL requests stalled during peak bidding windows.
Relevant Software stepped in when the slowdown reached a critical point. The audit revealed the need for a new architecture to restore performance and support growth. We had to integrate real-time analytics and natural-language querying into their system. That would allow buyers to ask plain-language questions and instantly access structured insights, without writing SQL or waiting for overnight reports.
Founder & CEOWe received a solution powered by an AI agent that connects directly to our database, interprets plain-language questions, and delivers precise SQL results within seconds. Relevant Software fine-tuned the system for speed and accuracy, giving procurement teams immediate, intelligent access to critical data.
Our team built an AI chatbot that converts plain-language questions into accurate database queries. Pharmacy staff check availability, compare prices, view price history, explore pack sizes, and retrieve identifiers like PZN without writing SQL or using technical tools. The system responds instantly and simplifies access to critical product information.
The system captures data from a replicated PostgreSQL database used for safe proof-of-concept development. To support semantic search, product information is also vectorized, enabling accurate, similarity-based queries across key tables.
We implemented a multi-agent architecture that assigns each user query to the appropriate workflow. For data requests, a language model-based SQL generator writes and validates safe, relevant queries, adhering to strict formatting and security rules to ensure data integrity.
Our team built a demo interface that allows pharmacy staff to interact with the chatbot through a simple frontend. It includes quick-access prompts for common questions and displays the generated SQL for transparency. The demo runs securely through the client’s DNS proxy.
Real-time data visibility
Procurement teams can view up-to-date records instantly, eliminating overnight ETL delays entirely.
Zero-SQL reporting
Users ask questions in plain language, and the system returns validated scripts and charts without requiring SQL skills.
Secure multi-party data sharing
The platform delivers cleaned, de-identified datasets with row-level security, giving partners immediate access while meeting EU privacy standards.
Founder & CEOWe’re very satisfied with the results and the professionalism of the team. The collaboration was very productive and laid the groundwork for ongoing improvements.
Share details about your project and book a free call with us
to discuss your development strategy