• Rapidly cull documents early in a case, reducing the cost and time associated with processing and review
  • Understand and contextualize core facts in documents, then create connections between documents by identifying relationships between relevant entities
  • Provide precise and actionable insight into the content of unstructured documents, like Word documents, emails, PowerPoint slides and PDFs; ayfie recreates email threads based on normalized subject lines, people and message content
  • Cluster and categorize documents to speed research and aggregate understanding of large content bases

Aided Intelligence for eDiscovery

ayfie's deep-text concept analytics technology used to search and manage electronic information. ayfie can artificially derive conceptual meaning from small datasets, documents and text, by using a combination of Machine Learning and Linguistics. With robust and customizable dictionaries and grammars, meaning can be analyzed across a few sentences, a few paragraphs, or an entire document.

With incredible accuracy, ayfie can then be trained on larger datasets to find all other similar concepts in a collection of documents. Using advanced mathematics and hundreds of dimensions, ayfie looks at individual words, how they are used, and how frequently they appear together to identify patterns across thousands of documents.

It then matches-up the values it derives against a given concept and assigns a relevance ranking to documents based on what it finds. Similarly, it ranks the individual words in documents so the ayfie index will contain values that show how everything is related. This enables it to provide conceptual search to create clusters of conceptually related documents.

ayfie technology aided review

ayfie enables systems for the electronic aspect of identifying, collecting and producing electronically stored information (ESI) in response to a request for production in a law suit or investigation. ayfie powers technology-aided review (TAR) through collection, processing, securing, organization, and search. The document store and linguistic technology runs in a highly distributed fashion by design while still maintaining cost efficiency and performance for small data sets. From a couple of word documents to petabytes of data, it can handle it all.

ayfie combines best of breed open source search and data technology with our proprietary super-performant language analysis and information extraction frameworks. Our platform enables powerful information discovery applications and helps users navigate to and find all related content across the enterprise. With the ayfie Lexicon our clients get access to high-coverage electronic dictionaries that help recognize all the different forms in which a word may appear. ayfie Lexicon is available for all major European languages.

Verticals or domains such as fashion, travel, consumer electronics or medicine require specialized dictionaries for proper query analysis and in-depth text mining. Through collaboration with industry experts, ayfie has gathered many man years' worth of specialized semantic resources. These resources include keyword lists, synonym and hyponymy tables and disambiguation rules.

  • Extensive out-of-the-box dictionaries for many verticals and domains
  • Proven and manageable processes to update and enrich these dictionaries
  • Processes to detect and harness reference lists available on the Web


The only way to correctly and efficiently extract the right information. Integrate information from every corner of your digital landscape. Connect to, index and search your CMS, DMS, CRM, email, business application, and so much more. Don’t see your system? We build custom connectors.

Best of breed in EDRM

Our proven ingestion component can collect data exhaustively from all relevant enterprise data sources. All documents are first collected into a reliable and redundant data store before any other processing takes place. This data store can be locked down and secured against tampering so that every document contained therein stays available for an indefinite amount of time.

Our products utilize state-of-the art optical character recognition and format conversion technologies to turn any conceivable document format into readable text. Apart from normal token-based deduplication, our platform also enables us to detect near duplicate documents that employ the same vocabulary or talk about the same topic.

Organization can be looked at in two ways: unattended and user-assisted. The unattended method looks at what's in a given collection — on a particular custodian's hard drive, for example — and identifies documents in logical, concept-based groups. The user-assisted method takes groups of examples provided by the user in the form of categories and locates everything that is similar to those examples (setting aside everything that falls below a threshold). Both methods generally create folder-based collections of documents based on conceptual relevance.

Using conceptual search is as simple as directing ayfie to find all the other documents that are similar to the document in question. This might be a concept search, where a document or a part of a document is entered as a query, or a find-similar search. "Find-similar" is very powerful for e-discovery: with one or two clicks, a reviewer can automatically retrieve all the documents that are conceptually similar to one being reviewed.

Early Case Assessment (ECA) Challenges Advanced Analytics Capabilities for ECA Vendors
Intelligently determine the best search terms and related terms Keyword search and keyword culls still play a part in discovery collaborations. Ayfie "instant query suggest" enables your customers to use known keywords to find conceptually similar terms and concepts. Ayfie provides a unique way to draw suggestions directly from the content while also offering approximative matching, structured search with appropriate ranking and blazingly fast performance.
Discover the merits of a case and formulate case strategy Ayfie conceptual search enables your customers to use example text (e.g. the complaint) to identify the most conceptually related documents and email conversations. Ayfie email threading reveals who's talking to whom, about what, and when, to show who is involved in the case.
Intelligently prioritize the documents, saving time and money Traditional methods for slicing and dicing document collections usually employ statistical or probabilistic algorithms on the individual word level. Our unique technology enables us to actually extract only the relevant concepts from the document (be those single words or multiple words such as "presumption of innocence") and employ linguistic methods to set them into relation with each other. This results in better performance of clustering and classification algorithms but also enables new and better ways to access the data through highly relevant tags.
Organize the data for the most efficient review The full advanced analytics Ayfie suite provides robust approaches to slice and dice the data, optimally preparing it for review teams to "dive right in" to the most relevant documents to the case organized for a more focused review. Features such as language identification, email threading and near duplicate grouping, can also have dramatic impact on cost estimates.


ayfie is built to scale from the get go. The document store and linguistic technology runs in a highly distributed fashion by design, while still maintaining cost efficiency and performance for small data sets. From a couple of word documents to petabytes of data, ayfie can handle it all. 

Our linguistic modules for eDiscovery

We solve business problems with data analysis tailored to your needs. Leveraging Machine Learning, Linguistic Analysis and years of experience solving complicated problems.

Contact us