• Semantic search
  • text mining
  • agile software development

We would like to give insight into our work by presenting our areas of expertise through an overview of some projects we have developed. Download Precognox Customers as a PDF document or read below.

Basis Technology - Multilingual Text Analytics

Basis Technology (USA)

We are an official partner of Basis Technology as a system integrator, and we also provide them search and text analytics related software development services.


Meltwater (USA)

We are providing text mining and custom natural language processing services to Meltwater, which is a leading media intelligence software provider.

Kilgray Translation Technologies

Kilgray Translation Technologies

We are developing a professional J2EE solution with an AngularJS frontend for Kilgray Translation Technologies. Kilgray is one of the most innovative companies in Hungary. Started in 2004 by three Hungarian language technologists, the company quickly evolved into a multinational, transatlantic company and has become one of the most important players of the translating market in the world. Kilgray is on the Deloitte Technology Fast 50 in Central Europe list since 2012. Their MemoQ product is the world’s most advanced translating environment.

To achieve the most efficient results and optimal user experience, Precognox and Kilgray cooperate using a flexible, agile, Scrum based software development methodology. Precognox is building the architecture that is designed to be scalable by triggering new servers to share the workload if necessary, thus enabling the cooperation of multiple and multipliable components. This solution secures fluent progression, dynamically reacting to load - practically within hours.



We are partners in this Horizon 2020 project working on the commercialisation of new multi-lingual medical text analysis and search services. The new medical information search services has the ability to empower healthcare and life science professionals and the public alike. The search service can provide the fastest and most relevant medical support information available from which users can make the best-informed decisions. 

The intelligent (semantic) search service can incorporate both published medical literature and in-house medical information sources (such as electronic health records or health registries). 

Our partners are top universities and great SMEs:
- Vienna University of Technology (Austria)
- Findwise AB (Sweden)
- Ontotext AD (Bulgaria)
- Trip Database Ltd (UK)
- Health on the Net Foundation (Switzerland)
- Qulturum, Region Jönköping County (Sweden)
- King's College London (UK)
- University of Sheffield (UK): GATE
- Charles University, Prague (Czech Republic)


Government Transparency Institute

Government Transparency Institute 

We provided text mining services to the Government Transparency Institute. We quote their testimony: "I had the pleasure to work with Precognox on multiple occasions to build databases using online, semi-structured public procurement data. They always delivered us excellent quality data even on tight deadlines. They are easy to communicate with; they understand our demands and deliver exactly what we need. I would recommend Precognox highly to anyone who is looking for a company that works precisely and generates much value to its clients." - Mihály Fazekas, Founder, Director

CEU Microdata

CEU Microdata - Central European University

We participated in the development of kozbeszerzes.ceu.hu, a portal that makes searchable the Hungarian procurement data. The site was developed by CEU Microdata, a research group at the Department of Economics of the Central European University, lead by Miklos Koren and Adam Szeidl. Procurement data has been released in unstructured documents by the government, so it is extremely hard to get useful information from the texts.

Precognox has developed a special text mining solution that extracts the relevant information from text files and stores them in a structured database which can be analyzed by researchers. Our company is very proud of the success of CEU Microdata. The site is simple and functional, and it is even robot friendly, so one can automatically harvest procurement data using kozbeszerzes.ceu.hu.

Miklos Koren, Associate Professor, CEU: "The product - shipped on deadline - exceeded our expectations" Their feedback in detail

Elsevier (USA)

HealthMash is now available on SciVerse Applications beta. The new application is the result of a partnership between Precognox and Elsevier, a world-leading publisher of scientific, technical, and medical information products and services. We have also developed a mobile interactive book application for them.

David Marques, VP Business Development, Workflow Solutions: "Precognox developed a product (an interactive book mobile application) for us, and they had frequent, clear communication, and a very much 'get-things-done' approach, just what we value in our partners. We had big problems with the technical quality of our content, and Endre and his team stepped up, went beyond what was required, and turned the project around. It was a pleasure to work with Endre and his team. He proved an excellent action-oriented leader whose team delivered. A good partner if you want to get things done." 

Kilgray Translation Technologies


The new, Solr-based search engine is highly customized to the needs of Cylex and is capable of index-time transformations, such as stemming and using payloads to store weights and increase score for specific terms or phrases. It refines retrieval by ranking arbitrary compound functions, using available customer data and business logic. The new generation search engine enables faster retrieval and even more relevant search targets due to improved linguistic and computational processing. The latest versions of the search engines for Cylex Business Directories by Precognox are already up and running for the British and the German market.

Imre Papuscan, Product Manager at Cylex: "At first we attempted building the search engine ourselves as we had a clear vision of what we wanted to achieve, but we got stuck in development and we had to admit not quite having the experience in Solr-based solutions. That was when we turned to the experts of Precognox and started an interactive developing procedure where we were stunned by their experience, competence and attitude towards their profession. We managed to overcome all the mishaps step by step, assembled the pieces of the puzzle piece by piece - as we knew how and where the data was stored and where the points were a slight change in the algorhythm was enough to solve a problem without the search result being much affected. Feedback so far shows that not only us but our customers are also delighted with the search engine."

Edgewater Federal Incorporated

Edgewater Federal Incorporated (USA)

We developed custom search solution for Edgewater Federal Incorporated for several years.


Akademiai Kiado

NOTA - Daily visit Medical Knowledge base Application

We developed the NOTA website for the Akadémiai Kiadó on the purpose to help searching in Medical literature sources with a platformfree application - it can be used from a smartphone standing next to the sick-bed. This application is useful for doctors and also in the medical education, research and development.

Webicina search

Aggregating and curating content is a hard, yet highly regarded task. Webicina provides medical professionals a tool for aggregating and curating high quality health-related content, and helps patients to find information relevant to their medical condition. Webicina offers a multilingual solution in 24 languages. Precognox helps Webicina to collect, filter and make searchable its curated content.

Try it online

ODR search

ODR Search Engine searches all the bibliographic data available in Hungary (more than 6.5 million records). ODR (Országos Dokumentumellátó Rendszer - “National Document Supply System”) is an inter-library custom search engine for the masses. In 1997 a law was passed in Hungary that enabled the setup of an inter-library document supply system that includes (on top of the inter-library document supply) the location records of these library documents. Various national, regional, and university libraries with professional or general focus are contributing to the ODR Search Engine. These sources in number and quality guarantee the successful outcome of a search.

The search engine is an easy-to-use, Google or Bing-esque user interface, enabling quick browsing and supporting  target-finding refinement by various search options, e.g. intelligent clustering of results. 

Try this online

iDEalista search

A search service developed for the University of Debrecen. The core engine also used by international customers, considers language-specific features (English, Hungarian, etc.) not only simple character-matching during document retrieval. The purpose of developing this service was mapping and indexing the data sources of the portal system along with creating a user-friendly search interface.

The system supports simple and complex, advanced search options as well.

Pre-search options include: “full iDEa”:  searches the full university database, “profiles”: searching persons or units, “publications”: ,searches in data of publications, “multimedia”: searches in audiovisual materials

Advanced-only pre-search options (with separate search fields): search by title, or author.

Search query options include: inflections in the results, AND/+: include all search query terms in the results, OR: include at least one of the query terms, amping by using “*” - taking only the stem of the search query in consideration, including all inflection in the results, quotation marks: searching the exact terms in the exact order

Post-search options include (clusters): Author, Institute, Type, Language, Date, Source

The system also supports various filtering options to refine search. The results include links to the original document. All these options were established to maximize the chance of retrieving the correct results with manual refinement if necessary.

Try this online

Vanderbilt University

Vanderbilt University (USA)

We have made a custom federated search engine for The Annette & Irwin Eskind Biomedical Library at Vanderbilt University Medical Center, USA. 


A major overhaul has been carried out on Jobmonitor.hu. It has become a vast collection of job advertisments to which we supply the crawling, collecting and searching solutions. We use our Infoharvester to collect the information, then we store it in a Hadoop cluster.


Profession is offering one of the most comprehensive collection of online job ads in Hungary. It serves its clients with results based on simply query matching. But job seekers are in a hurry, they do not try every possible name for a position, they make typos and they want relevant result in a blink of an eye. With Precognox’s purpose-built solutions, Profession is now offering a semantic search interface. The new search engine handles synonyms and common typos - so it can serve job seekers with more relevant ads in less time.

Try this online


Internfish is a one stop shop for students looking for internship and scholarship opportunities. Precognox’s InfoHarvester crawls the web for such opportunities and turns ads into a central, structured, searchable database. Students don’t have to spend hours digging the Web for every possible opportunity any more - they can find everything on Internfish! 

Try it online

Startlap Kereső

Sanoma's Startlap

Sanoma's Startlap is the most known starting page and thematic link collection in Hungary . It has about 2 million links, on more than 8000 lap.hu pages. We were doing theing their search engine from  2008 to 2012.

NIH Library

NIH Library (USA)

We are developing custom federated search applications for NIH Library. The NIH Library is an open stacks biomedical research library whose collection and services are developed to support the programs of the National Institutes of Health and selected U.S. Department of Health and Human Serivces (HHS) agencies.


WebFeat (USA)

WebFeat has been licensing our clustering technology for their federated search application from 2007 to 2009.



NIEHS Library, National Institute of Environmental Health Sciences Library and Information Services, NIEHS Library - intranet deployment

National Library of National Institutes of Health

U.S. National Library of Medicine,
Bethesda, MaryLand (USA)

ToxSeek Search & Clustering Engine for Environmental Health and Toxicology