Projects

Case studies from real deployments.

36 projects across 14 industries and 9 business functions. Filter by the sector you are in, or by the part of the business you are trying to fix - a workflow proven in one industry is usually the same workflow in yours.

Industries

Functions

36 projects

Customer Support RAG Chatbot

SME client

Support answers come straight from the company's own documentation, day or night, instead of being retyped by staff.

#Legal
#Service - Helpdesk

Problem

Support answers already existed in the company's documentation, and customers still asked the team. Staff spent their day retyping answers that were written down somewhere, and anyone asking outside working hours waited until morning for a reply that was already in a file.

Solution

A context-aware chatbot answering from the company's own documents rather than from general knowledge, so responses reflect the current documentation and stay inside what the company has actually published. Questions it cannot answer from the source material are handed to a person instead of guessed at.

Benefits

Routine repeat questions are answered from the documentation without a person in the loop, and answers become available outside working hours. Estimated: the majority of first-line questions deflected, with a working prototype delivered in weeks rather than months.

Technical solution

Architecture

Documentation is chunked and embedded into a vector store, retrieved per question and passed to the model with the source context, served through an API behind the chat interface.

Technologies

LangChain, FastAPI, ChromaDB, OpenAI, Python

B2B Lead Generation Agent

Internal product, offered to B2B clients

Prospect lists built and qualified unattended, with the same criteria applied to the two-hundredth company as the first.

#Technology
#Sales - Prospecting

Problem

Building a prospect list means opening business listings one by one, visiting each website, and judging whether the company is worth approaching. It is a full day of work for a list that goes stale in a month, and the judgement applied on result number two hundred is not the judgement applied on result number two.

Solution

An autonomous agent that finds candidate companies through Google Maps, visits each website, and classifies whether it fits the target profile, applying the same criteria to every prospect. The output is a qualified list rather than raw search results, stored so it can be refreshed rather than rebuilt.

Benefits

Lead research runs unattended instead of consuming a person's day, and qualification criteria are applied consistently across the whole list rather than drifting as the researcher tires. Estimated: several hours of manual research replaced per list, with qualification consistency being the larger gain over speed.

Technical solution

Architecture

Discovery through the mapping source, browser automation to visit and read each candidate site, model-based classification against the target profile, results persisted to a relational store and reviewed through a web interface.

Technologies

Playwright, FastAPI, PostgreSQL, React, Python, LLM-based classification

Customer Support Automation Across Thirteen Markets

GymBeam

Thirteen thousand customer emails a month resolved end to end across thirteen markets, with the instrumentation to prove it keeps working.

#Retail
#Service - Ticketing

Problem

Around 13,000 customer emails a month arrive across 13 European markets, in as many languages, from where-is-my-order to returns to product questions. One general-purpose assistant handles all of them adequately and none of them well, human triage scales only by hiring, and a wrong answer reaches the customer before anyone notices.

Solution

An LLM router classifies each email and dispatches it to one of seven independent agents, each scoped to a single intent so it can be improved without regressing the others. Returns are resolved rather than drafted: the agent validates the order through the Magento API, issues the label and answers in the customer's language. A storefront assistant deflects product questions from the live catalogue before they become tickets. Around all of it, low-confidence cases go to a person, every execution is traced and costed, and changes are dry-run on historical tickets before release.

Benefits

Roughly 13,000 emails a month routed and resolved across 13 markets, with returns closing unattended and handling capacity no longer scaling with headcount. Agent behaviour, cost and failure modes are observable rather than assumed, which is what allows each further intent to be automated on evidence.

Technical solution

Architecture

Intent classification dispatching to seven independently deployed Cloud Run agents, tool-calling against the order platform for transactional cases, RAG over the product catalogue for the storefront assistant, and a control layer gating confidence, tracing execution and replaying historical tickets before release.

Technologies

Python, LangChain, Google ADK, Gemini, Cloud Run, FastAPI, Magento REST API, vector database, JavaScript widget, BigQuery, Tableau

GraphRAG over Slovak Legislation

Technical University of Košice

Legal answers retrieved through the reference structure of the law itself, every one traceable back to the provision it came from.

#Legal
#Legal - Compliance

Problem

Legislation is a graph pretending to be a library. Provisions amend, reference and depend on each other, so the passage that answers a question is often not the passage that matches its words. Vector search alone retrieves what sounds relevant and misses the cross-reference that changes the answer, and in a legal context an answer without a citation is unusable.

Solution

A GraphRAG system combining a graph representation of the legislation with vector search, so retrieval follows the actual structure of references between provisions as well as semantic similarity. Every answer carries the citations it rests on, making it checkable against the source text.

Benefits

Legal answers that follow the reference structure of the legislation rather than surface wording, each one citation-backed and verifiable against the original provision. Estimated: accuracy gains over pure vector retrieval concentrated exactly where it matters, on questions whose answer depends on a cross-reference.

Technical solution

Architecture

Legislation modelled as a graph of provisions and their references in Neo4j, combined with vector retrieval over provision text, with citations carried through to the generated answer.

Technologies

Neo4j, vector database, Python, LangChain, LLM generation with citation grounding

RAG Pipelines for Private Domain Documents

Siemens Healthineers

Private engineering documentation made answerable by question, with nothing leaving the organization's own infrastructure.

#Healthcare
#Service - Knowledge

Problem

Engineering and regulatory knowledge in medical technology sits in private document sets that a general-purpose model has never seen and must never be trained on. The knowledge is written down and still effectively unsearchable, because finding it requires knowing which document it is in.

Solution

Retrieval-augmented pipelines letting language models work over domain-specific and private documents, so answers come from the organization's own material with the documents staying under its control rather than being absorbed into a model.

Benefits

Internal document sets became answerable by question rather than by knowing where to look, without private material leaving the organization's control. Estimated: substantial reduction in time spent locating information across internal documentation.

Technical solution

Architecture

Document ingestion and chunking into a vector index over private corpora, retrieval feeding a generation layer, with the source documents remaining inside controlled infrastructure.

Technologies

Python, LangChain, vector databases, embedding models, RAG orchestration

Siml.ai: AI Surrogates and the Agentic Layer Above Them

DimensionLab

Simulations that took weeks run in minutes, with agents handling the setup that used to decide who could run them at all.

#Manufacturing
#Product - Engineering

Problem

Designing a fusion reactor, a wind farm or a hydrogen battery means running the same expensive simulation hundreds of times with slightly different parameters. Each run is costly and thrown away, so the number of designs anyone can explore is set by compute budget rather than engineering judgement. Setting the simulation up is itself expert work, which gates who can run one at all.

Solution

A platform where engineers train AI surrogate models that approximate the physics rather than solving it from scratch, trained once and then queried in real time. Physics-informed training constrains the model by the governing equations, not only by data, and geometry-informed neural operators handle the irregular meshes of real engineering parts. A packaged GPU environment removes the infrastructure assembly, and an agentic layer orchestrates language models across setup and analysis, with evaluation harnesses and guardrails deciding where a human must confirm.

Benefits

One customer achieved 96% cost and time savings on AI-driven simulations built on Navier-Stokes equations and physics-informed neural networks. Experimental phases that ran to weeks compress to hours. Simulators are trained once and reused, and agent assistance widens who can operate the platform beyond simulation specialists.

Technical solution

Architecture

Physics-informed neural networks and neural operators trained against governing PDEs, deployed for repeated real-time inference from a cloud-agnostic containerised GPU environment, with a multi-agent layer over the engineering workflow gated by evaluations and guardrails.

Technologies

NVIDIA Modulus and PhysicsNeMo, PyTorch, Fourier and graph neural operators, CUDA, Docker, agent orchestration, Anthropic Claude and OpenAI models, evaluation harnesses, guardrails

Agentic AI Platform for an Insurance Group

Insurance group

An insurance agent platform where new workflows are declared rather than coded, running as background tasks triggered by the data itself.

#Insurance
#Legal - Insurance

Problem

Insurance work is a long tail of judgement-heavy tasks sitting on top of records that change constantly. Automating any one of them individually produces a tool that cannot be extended, and enterprise procurement will not accept a system that has to be rebuilt each time a new process is added. The requirement is a platform that absorbs new workflows rather than a set of point solutions.

Solution

An agentic platform combining chat-based agents with declarative agentic workflows. Most workflows run as background tasks triggered by events rather than by users: a new record arrives in the database that needs evaluating, and the workflow starts itself. Orchestration is declarative rather than code-based, so adding or changing a workflow is a configuration change instead of a system rebuild, which is what makes the platform absorb new use cases rather than accumulate bespoke code.

Benefits

New workflows onboard without rebuilding the system, and event-triggered background execution means throughput is not bound by user interaction. Estimated: three business use cases are being migrated onto the platform progressively, indicating it is being treated as the target architecture rather than a pilot.

Technical solution

Architecture

Declarative multi-agent orchestration on Microsoft Agent Framework, with durable workflow execution handling long-running and resumable processes, vector and relational stores behind retrieval, and a deployment model spanning Azure and on-premises inference so data location can be controlled per workload.

Technologies

C# and .NET, Microsoft Agent Framework (MAF), Temporal, Qdrant, PostgreSQL, MS SQL, S3-compatible storage, Azure deployment, on-premises Mistral, DeepSeek, Qwen and open-source models, embedding and vision models

Chat-Based LLM Agents for Critical Infrastructure

Slovak and Czech organizations in critical infrastructure, including national security and audit authorities

Retrieval chat agents deployed inside critical infrastructure and security authorities, built before the standard frameworks existed.

#Government
#Service - Knowledge

Problem

Organizations handling classified or critical-infrastructure information had the same knowledge-access problem as everyone else and none of the available options. Sending queries to a commercial API was not permissible, and at the time the work started the tooling everyone now takes for granted did not exist.

Solution

LLM chatbots with retrieval over internal document sets, built from first principles because the frameworks that would later standardize this work had not been released. The systems grew by accretion, retrieval first, then progressively more capable agentic behaviour, with deployment moving to Azure as soon as the models became available there so that data location met the organizations' requirements.

Benefits

Internal knowledge became queryable in organizations where commercial AI services were not an option. Estimated: the early-mover position produced hard-won production experience in exactly the environments where AI deployment is hardest to get approved.

Technical solution

Architecture

Retrieval-augmented chat over internal corpora, hand-built orchestration predating the standard frameworks, later migrated to Azure-hosted models for data residency compliance.

Technologies

OpenAI services initially, later Azure OpenAI for data location, custom retrieval and orchestration code, vector search, .NET

Slovak Foundation Models

SlovakNLP, with the Institute of Artificial Intelligence TUKE and the Slovak Academy of Sciences

Open-weight Slovak models that can be self-hosted and adapted, closing the gap that made Slovak an API-only language.

#Research
#Product - Engineering

Problem

Slovak is a low-resource language. Open-weight models handle it badly, switching mid-sentence into other languages, looping, and pulling vocabulary from neighbouring Slavic languages. The commercial models that do handle Slovak well are closed, which rules them out wherever the data cannot leave the organization or the model has to be adapted to a domain.

Solution

A Slovak baseline model built by full-parameter fine-tuning of Mistral 7B on a large Slovak web corpus, followed by an instruction-tuned 14B model on the Qwen architecture. The result is an open-weight model that can be self-hosted, inspected and further adapted, rather than accessed through someone else's API.

Benefits

Grammatically correct and contextually coherent Slovak, with the code-switching, repetition and lexical interference of the base model eliminated. Available as open weights, so organizations handling regulated or confidential Slovak text can run them on their own infrastructure.

Technical solution

Architecture

Full-parameter fine-tuning of open-weight base models on a large Slovak corpus, followed by instruction tuning on curated Slovak sources, trained on national HPC allocation.

Technologies

Mistral 7B and Qwen 14B architectures, full-parameter fine-tuning, Araneum Slovacum corpus, Leonardo supercomputer, Hugging Face distribution

Predicting the Outcome of Judicial Appeals

SlovakNLP

Appeal odds estimated from the text of the decision itself, trained on a corpus of millions of Slovak court rulings.

#Legal
#Legal - Litigation

Problem

Deciding whether to appeal is a judgement made with almost no data behind it. Slovak court decisions are digitized in the millions but written as unstructured prose, so nobody can say what the realistic odds of reversal look like for a case of a given shape.

Solution

Court decisions are segmented into their logical parts, then domain-adapted language models are fine-tuned on Slovak legal text and applied to predict whether an appeal will succeed. Candidate models were selected by benchmarking a field of nine against generation metrics before adaptation, and the prediction itself was approached three ways, zero-shot, few-shot and with a dedicated classification layer, so the cheapest adequate method could be identified rather than assumed.

Benefits

Appeal prospects become estimable from the case text itself rather than from intuition, on a corpus drawn from millions of digitized Slovak decisions.

Technical solution

Architecture

Rule-based structural segmentation of decision texts, legal-domain adaptation of Slovak base models, then appeal-outcome prediction evaluated across zero-shot, few-shot and classification-head approaches.

Technologies

Qwen3-8B and Mistral-SK-7B, domain-adaptive fine-tuning, classification heads, Perplexity, BLEU and ROUGE benchmarking

Agentic Platform for the Biopharmaceutical Domain

Dr. Evidence

More than 25 specialised agents over 70 million documents, each narrow enough that its output can be checked rather than trusted.

#Pharmacy
#Legal - Compliance

Problem

Regulatory and labelling work is a chain of distinct tasks, each needing different sources, judgement and output. A single general assistant handles all of them mediocrely, and mediocre is not a usable standard when the output supports a regulatory submission. The literature it must draw on runs to tens of millions of documents, where ordinary retrieval architectures degrade.

Solution

An agentic platform orchestrating more than 25 specialised agents across three workflow families, each scoped to a task it can be evaluated on individually, with the orchestration layer deciding which agents a given piece of work requires. Underneath sits semantic search and RAG engineered to hold retrieval accuracy across 70 million documents, and instruction-fine-tuned models that return structured biomedical fields rather than prose.

Benefits

Regulatory and labelling workflows that previously required specialist manual effort at every step run as orchestrated agent workflows, with each agent narrow enough for its output to be verified rather than trusted wholesale. Literature search across tens of millions of documents became a single semantic query, and published literature became comparable structured records at scale.

Technical solution

Architecture

Multi-agent orchestration across three workflow families over a curated regulatory and scientific corpus, on distributed hybrid retrieval with cross-encoder reranking, fed by domain-specific extraction models with schema-constrained output.

Technologies

LangChain, LangGraph, Elasticsearch and Solr, FAISS/HNSW, cross-encoder reranking, Hugging Face Transformers, PEFT/LoRA, UMLS, MeSH and SNOMED CT, Kubernetes, Python

Big Data Platform for Predictive Control and Maintenance

MONSOON consortium, EU SPIRE-723650

Plant data processed fast enough to act on, with the analytics described semantically so they move between sites instead of being rebuilt.

#Energy
#Supply - Maintenance

Problem

Process plants generate continuous high-volume sensor data, and the value in it, predicting a failure or correcting a drifting process before it produces scrap, is only realized if the data can be processed fast enough to act on. Batch analysis after the shift tells you what you already lost.

Solution

A big data platform supporting predictive control and predictive maintenance over process data, paired with a semantic model that represents the data-analytics processes themselves, so an analytical pipeline is described in a form that can be reused across plants rather than rebuilt for each one.

Benefits

Predictive control and maintenance became possible on live process data, and the analytics themselves became portable between sites through a shared semantic description.

Technical solution

Architecture

Distributed batch and stream processing over plant sensor data, with a semantic layer describing analytical processes for reuse across deployments.

Technologies

Apache NiFi (plant-side integration), MQTT, Apache Kafka, Apache Hadoop HDFS and YARN, Apache Spark (batch, streaming and SQL), DL4J with Keras for GPU/CPU training, Hadrian scoring engine for PFA, Grafana, Apache Zeppelin, Apache Knox, Apache Ambari, OSIsoft PI historian connector. Semantic framework built on CRISP-DM, PMML, PFA, ISO 22400 KPIs and JSON-LD.

Collaborative Policy Modelling Platform

InterSoft a.s., partner in the OCOPOMO consortium, EU FP7 248128

Stakeholders write the scenarios, the simulation traces back to them, and policy models stop being a black box to everyone outside the modelling team.

#Government
#Strategy - Development

Problem

Policy models are built by modellers and the evidence behind them lives with stakeholders, in narrative form. The gap between the two is where trust in a policy simulation is lost: nobody outside the modelling team can trace why the model behaves as it does or which stakeholder input produced a given assumption.

Solution

An online collaboration and content management platform where stakeholders build narrative scenarios that are then transformed through conceptual models into formal policy simulations, with traceability maintained from each element of the model back to the evidence that produced it.

Benefits

Policy simulations became traceable back to stakeholder evidence rather than opaque, which is the condition for non-modellers to trust and use them. Piloted on EU structural funds and on regional renewable energy policy.

Technical solution

Architecture

Enterprise content management backbone supporting collaborative scenario authoring, with transformation into conceptual and then formal policy models, preserving traceability links throughout.

Technologies

Alfresco CMS, J2EE, agent-based simulation integration, semantic annotation

Semantic Service Bus for Networked Enterprises

SPIKE consortium, EU FP7 217098

Services from different companies discovered and matched semantically, so setting up a business alliance stops being a bespoke integration project.

#Technology
#Technology - Integration

Problem

Short-term business alliances need to share services across company boundaries, but every partner's services are described differently. Wiring each new alliance together by hand costs more than the collaboration is worth, which puts this kind of partnership out of reach for smaller firms.

Solution

Semantic extensions to an enterprise service bus, so services from different organizations are annotated against a shared model and can be discovered and matched to workflow tasks automatically, with data mediated between them rather than manually mapped.

Benefits

Cross-company service integration shifted from bespoke wiring per alliance to semantic matching, bringing the setup cost of a business alliance within reach of SMEs.

Technical solution

Architecture

Semantically enriched service bus with annotation-driven service discovery and data mediation across organizational boundaries, covering web services, cloud services and human tasks.

Technologies

SA-WSDL, Apache ServiceMix ESB, Apache CXF, OWL and WSMO ontologies, Liferay portal with portlets (JSR-168/286), OSGi, Java EE, XML SOAP and REST connectors

Semantic Platform for E-Government Services

Access-eGov consortium, EU FP6 IST-27020

A citizen states the goal and the platform assembles the right services from the right authorities, in the right order.

#Government
#Service - Knowledge

Problem

A citizen dealing with a life event faces a set of authorities that do not present themselves as a set. Each publishes its services in its own structure, so working out which apply and in what order is left to the citizen, and traditional counter services and electronic ones do not connect at all.

Solution

A platform for semantic integration of traditional and electronic government services, where services are modelled ontologically and a resolution component assembles the ones applicable to a citizen's goal into an executable sequence across institutional boundaries.

Benefits

Services from separate authorities, electronic and counter-based alike, became composable into one guided process driven by what the citizen is trying to achieve.

Technical solution

Architecture

Ontology-based modelling of government services with a core execution component that resolves a citizen goal into an ordered set of applicable services spanning authorities.

Technologies

WSMO and WSML service modelling, OWL, Protege, Sesame RDF store, Java EE, Apache Tomcat, Apache Axis web services

Object/RDF Persistence and Hybrid Semantic Search

KP-Lab consortium, EU FP6 IST-27490

Structured semantic queries and ordinary keyword search answered by one service, over an object API developers could actually use.

#Research
#Technology - Infrastructure

Problem

Knowledge-practice environments need to store richly interlinked objects and let people find them, and the two requirements pull apart. Semantic stores answer structured queries but not the vague ones people actually type; full-text search does the opposite and ignores the structure entirely.

Solution

An object/RDF persistence and query API giving applications a normal programming model over a semantic store, combined with a search service that answers semantic and free-term queries together rather than forcing a choice between them.

Benefits

Applications gained structured semantic querying without giving up ordinary keyword search, and developers worked against a familiar object API instead of writing RDF queries by hand.

Technical solution

Architecture

Object-to-RDF mapping layer with a query API over a semantic repository, and an integrated retrieval service combining semantic and free-term search paths.

Technologies

Sesame/OpenRDF repository, SPARQL, RDF and OWL, Java object-RDF mapping API, Apache Lucene, Apache Tomcat, Java EE

Trust Mechanisms and Transaction Analytics for an SME E-Marketplace

SEAMLESS consortium, EU FP6 IST-26476

Small firms got a basis for trusting cross-border counterparties, built on analytics over what actually happened on the platform.

#Retail
#Legal - Risk

Problem

Cross-border electronic marketplaces fail for small enterprises on trust rather than on technology. A firm will not transact with an unknown counterparty in another country without some basis for judging them, and marketplace operators had no analytical view of what was actually happening across transactions.

Solution

Analysis of trust-building mechanisms for an electronic marketplace and design of the operational scenarios to implement them, followed by a data warehouse with OLAP and data mining services giving the operator an analytical and rating view over platform transactions.

Benefits

Trust mechanisms moved from principle to implementable operational scenarios, and marketplace transactions became analyzable, supplying the evidence base for participant ratings.

Technical solution

Architecture

Data warehouse over marketplace transactions with OLAP cubes and data mining services feeding analytical and rating functions, alongside designed trust-building operational flows.

Technologies

JDM (Java Data Mining, JSR-73) and JOLAP APIs, Mondrian OLAP with Pentaho reporting, MySQL data warehouse, Weka and JBowl for mining, J2EE, SQL

Open-Source Text Mining Library and Analytical Platform

Technical University of Košice

An open-source Java library that made text mining a matter of composing components instead of rebuilding the pipeline every project.

#Technology
#Technology - Development

Problem

Text mining work was repeatedly rebuilt from scratch, every project reimplementing preprocessing, classification, clustering and evaluation before it could get to its actual question. Nothing modular and extensible existed for Java, and later the same code could not scale to larger corpora or run distributed.

Solution

An open-source Java library covering the whole text mining process, from corpus construction and preprocessing through classification and clustering to model evaluation, founded and maintained as a public project. It was later extended with a task-based execution engine for distributed processing and a graphical console, making it usable by people without programming skills.

Benefits

Text mining became a matter of composing an existing library rather than rebuilding infrastructure per project. The library was adopted across research projects and teaching, and the distributed engine extended it to corpora that no longer fit a single machine.

Technical solution

Architecture

Modular Java API spanning the text mining pipeline, with a task-based middleware execution engine for multi-threaded and distributed processing, and a web console over the library.

Technologies

Java SE and EE, Apache Lucene, Weka-compatible model interfaces, task-based middleware execution engine, Apache Hadoop for distributed runs, Apache Tomcat web console, distributed via SourceForge

Text Categorization for Direct Democratic Participation

WEBOCRACY consortium, EU IST-1999-20364

Citizen input classified and retrievable by subject, so participation at scale produces something an administration can actually answer.

#Government
#Administration - Correspondence

Problem

Opening public administration to direct citizen participation produces volume, and volume without organization is noise. Contributions arrive as free text on every subject at once, and the administration cannot route or answer what it cannot categorize.

Solution

A collaboration platform built on semantic web technologies for citizen participation in democratic processes, with text categorization and information retrieval so that contributions are classified by subject automatically and previous material on the same subject is findable.

Benefits

Citizen contributions became routable and searchable by subject rather than accumulating as an undifferentiated stream, which is what makes participation at scale answerable.

Technical solution

Architecture

Semantic web collaboration platform with automatic text categorization and retrieval services over citizen contributions.

Technologies

Webocrat system on Java and J2EE, RDF and RDF Schema, Apache Lucene retrieval, JBowl text categorization, Apache Tomcat, relational backend over SQL

Data Mining over Integrated GIS and Data Warehouse

GOAL consortium, INCO-COPERNICUS 977091

Spatial and analytical questions answered in one system, from regional water demand forecasting to scenario discovery for tourism operators.

#Utilities
#Supply - Planning

Problem

Geographic systems and analytical data warehouses were separate worlds. Questions with both a spatial and an analytical dimension, how consumption varies across a distribution network, which regions support which service scenarios, could not be asked in either system alone.

Solution

A data mining application integrated directly into a GIS over a data warehouse, applied to predicting water consumption across a regional distribution system and to identifying optimal operating scenarios for travel agencies.

Benefits

Spatial and analytical questions became answerable in one system, demonstrated on regional water consumption forecasting and on scenario discovery for tourism operators.

Technical solution

Architecture

Data mining components integrated with a GIS front end over OLAP services on a data warehouse, supporting spatially resolved prediction and scenario analysis.

Technologies

C/C++, MS SQL OLAP Services, ADO, GIS integration

Vowel Detection in Noisy Speech

UNIZA, University of Žilina

Treating noisy speech as images rather than sequences raised vowel detection accuracy by up to 16 points over published alternatives.

#Research
#Strategy - Innovation

Problem

Speech recognition degrades sharply once background noise enters the signal, and vowel segments are where that degradation does most damage. Existing approaches based on attention networks were leaving accuracy on the table under realistic noise conditions.

Solution

Audio is transformed into a spectrogram and individual segments are classified with convolutional neural networks, treating vowel detection as an image classification problem rather than a sequence modelling one.

Benefits

Detection accuracy 6 to 16 percentage points higher than comparable research using attention-based networks. Published and peer-reviewed: https://doi.org/10.1016/j.trpro.2021.07.112

Technical solution

Architecture

Spectrogram transformation of the audio signal followed by segment-level CNN classification, GPU-accelerated for training throughput.

Technologies

Python, CuPy, convolutional neural networks

Pairwise Weighted Classifier Ensembles

UNIZA, University of Žilina

A new weighting scheme for combining pairwise classifiers beat the best existing combination method on both CIFAR-100 and ImageNet.

#Research
#Strategy - Innovation

Problem

Multi-class classification can be decomposed into pairwise classifiers, but combining their outputs back into a single decision is where accuracy leaks away. Standard combination schemes were failing to extract the full value of strong individual models.

Solution

A new pairwise weighted ensemble method that combines the outputs of deep convolutional networks and vision transformers through tensor operations, weighting each pairwise decision by its reliability rather than treating all pairs as equal.

Benefits

Accuracy gains over the best combined classifier of 2 to 5 percentage points on CIFAR-100 and 1 to 3 on ImageNet-1k. Published in IEEE Access and TMLR: https://doi.org/10.1109/ACCESS.2023.3298057

Technical solution

Architecture

Pairwise decomposition of the multi-class problem, with a weighted tensor-based combination layer over the outputs of heterogeneous backbone models.

Technologies

Python, PyTorch, convolutional neural networks, vision transformers, R with ggplot2 for analysis

Public Service Network Design Under Conflicting Criteria

UNIZA, University of Žilina

Planners get the full range of viable trade-offs for a regional service network in a fraction of the time exact methods need.

#Government
#Strategy - Planning

Problem

Designing a public service network means trading off criteria that pull against each other, cost against coverage against response time. Exact methods produce provably optimal answers but take long enough on region-scale problems to be impractical for planners exploring alternatives.

Solution

A modified genetic algorithm that approximates the Pareto set rather than solving for a single optimum, so planners see the range of viable trade-offs instead of one answer conditioned on weights chosen in advance.

Benefits

Computation 50% to 85% faster than the exact method across the three largest Slovak regions, with solution quality that remains practically equivalent. Published: https://doi.org/10.1016/j.trpro.2019.07.185

Technical solution

Architecture

Multi-objective optimization via a modified genetic algorithm approximating the Pareto front, benchmarked against exact mathematical programming on real regional instances.

Technologies

Java, custom multi-objective genetic algorithm with Pareto-front archiving (NSGA-II family), FICO Xpress or IBM CPLEX for the exact benchmark, Slovak regional demand and network datasets

AI Assistance for Legal Document Work

SingleDraft

Facts checked against the public registries and clauses drafted from the firm's own precedent, both arriving as edits to accept or reject.

#Legal
#Legal - Compliance

Problem

Every party, property and statutory reference in a legal document has to be checked against the public registries, and lawyers were doing it by hand, one lookup at a time. In parallel, firms hold years of precedent in their own archive but cannot reach it while drafting, so clauses that already exist get rewritten. Both jobs are slow and both get skipped under deadline pressure.

Solution

Target information is located in the unstructured document text and matched against the commercial register, cadastre and collection of laws, returned as a comparison showing what agrees, what conflicts and what the registry knows that the document does not. Alongside it, a multi-branch RAG system combining deterministic routing with LLM-driven decisions returns its output as proposed changes to the document, so the lawyer reviews edits in place rather than retyping text.

Benefits

Manual registry lookup is eliminated, making full checking practical on every document rather than only the high-value ones, and editing and extending documents runs several times faster with proposals grounded in the firm's own corpus rather than generic model output.

Technical solution

Architecture

Heuristic entity extraction over unstructured legal text with fuzzy multi-pattern matching against public registry APIs, alongside a multi-branch retrieval pipeline whose output is structured as document change proposals for human approval.

Technologies

Python, LangChain, Pydantic, Qdrant, Langfuse, DeepL, FastAPI, Zeep, ahocorasick-rs, RapidFuzz, AWS S3 and DynamoDB

Tabular Data Extraction from Mixed-Format Documents

Arles

Orders arriving as PDFs, spreadsheets or plain email text all come out as the same structured line items, without retyping.

#Retail
#Sales - Ordering

Problem

Orders and quotations arrive by email in whatever format the sender happens to use, as free text, PDF, spreadsheet, XML or HTML. Someone has to read each one and retype the line items into the system before anything can be processed.

Solution

A proof of concept extracting tabular data from any of those formats into a single structured output, using multimodal models where the content is visual and structured LLM output to guarantee the result matches the expected schema.

Benefits

Demonstrated automation of the retyping step in order and quotation intake, removing the format-by-format manual handling that had made the process impossible to automate with rule-based parsing.

Technical solution

Architecture

Format-agnostic extraction with schema-constrained LLM output, multimodal handling for visually structured source documents.

Technologies

Python, LangChain, Pydantic

Agentic Data Discovery and Visualization

Internal R&D

The same agent built three times on three frameworks, producing a like-for-like comparison rather than an opinion about which to use.

#Technology
#Data - Visualization

Problem

Answering a data question often means finding the data first, and the data is scattered across the public web in tables nobody has consolidated. The step from question to chart involves searching, scraping, cleaning and plotting, each of which is individually simple and collectively too tedious to do by hand.

Solution

A two-stage agentic system with tools for web search, web scraping, and code generation for post-processing and rendering the chart. The same system was implemented three times, on LangGraph, Pydantic AI and the OpenAI SDK, to compare the frameworks against each other on identical requirements.

Benefits

Produced a direct comparison of the leading agent frameworks under identical conditions. Pydantic AI emerged as the working compromise between the breadth of the LangChain and LangGraph ecosystem and the bare building blocks of the OpenAI SDK, with type safety as the deciding advantage.

Technical solution

Architecture

Two-stage agent, discovery followed by processing, with generated code executing the post-processing and plotting step. Built three times against different frameworks for direct comparison, with full tracing on each implementation.

Technologies

Python, Pydantic AI, LangGraph, OpenAI Python SDK, Brightdata, Pydantic, FastAPI, Logfire, LangSmith, Langfuse

AI-Assisted Enquiry Management

Top-Tier Macroeconomic Policymaker (anonymized)

A drafting assistant grounded in the organization's own precedents saved at least €56k of manual effort while holding to corporate tone.

#Government
#Finance

Problem

Answering complex client enquiries meant searching manually for precedents and drafting replies that held to the organization's established tone and communication standards. The manual effort per enquiry was substantial.

Solution

A human-in-the-loop drafting system built on semantic search. The system retrieves relevant knowledge and historical precedents, then proposes a response aligned with the organization's own tone and past positions. Every output is reviewed and approved by a human operator before it leaves.

Benefits

Conservative ROI of €56,000 to €76,000 from measured time savings alone. Additional value, unquantified, came from higher response quality and automated adherence to communication standards.

Technical solution

Architecture

Semantic search pipeline coupled to a generative drafting agent, tuned for tone alignment and precedent retrieval.

Technologies

Python, LangChain orchestration, sentence-transformer embeddings, hybrid vector + BM25 for the precedent retrieval, hybrid retrieval with reranking, on-premises or private-tenant LLM, FastAPI, Langfuse tracing

Slashing Chatbot Operating Costs by 30x

altFINS.com

Redesigned routing cut chatbot operating costs thirtyfold and made it reliably trigger the right financial analytics.

#Finance
#Crypto
#Trading

Problem

The first implementation of the customer-facing chatbot routed messages poorly to the underlying analytics tools and ran up large operating costs.

Solution

A conceptual redesign of the routing logic. The new architecture intercepts the user message and directs it to the right analytical pipeline. The work also laid the groundwork for Model Context Protocol integration and for orchestrating multiple ad-hoc analytics directly inside the chat interface.

Benefits

30x reduction in operating costs against the original implementation. Production accuracy rose, with few on-the-fly fixes needed after deployment.

Technical solution

Architecture

Intent classification and routing layer that decouples the conversational interface from the analytical execution underneath.

Technologies

LLM based intent extraction and routing combined with vector based retrieval, Model Context Protocol servers for the analytics tools, prompt versioning and evaluation harness

Optimizing Ad Spend via Creditworthiness Prediction

hyperia.sk

A three-variable spreadsheet was replaced by a backtested 15-feature model, lifting credit prediction accuracy 20% and sharpening ad targeting.

#Finance
#Lending
#Advertisement

Problem

Advertising spend needed to be targeted at online loan applicants likely to qualify. The legacy model was a manually derived spreadsheet built on three parameters, too coarse to direct ad budget with any precision.

Solution

A stable, interpretable machine learning model trained on historical loan applicant records. The system evaluated 60 candidate features and narrowed them algorithmically to the 15 most predictive, yielding business rules the client could act on directly, such as homeowners being more than twice as creditworthy as non-homeowners.

Benefits

Prediction accuracy up 20% over the legacy model. Identifying applicants likely to receive higher loan payouts, and therefore higher commissions, let the client concentrate ad spend on high-value leads.

Technical solution

Architecture

Tabular ML pipeline built for interpretability and rigorous backtesting. Validated on a strict rolling window, 3 months training data, a 1-month gap and a 1-month prediction horizon, across 26 evaluation iterations.

Technologies

Python, pandas, scikit-learn, XGBoost and LightGBM, recursive feature elimination, interpretation of discovered patterns based on Tree models, SHAP, rolling-window backtesting

Uncovering Drivers of Member Retention

ver.di

Historical membership data was analyzed to isolate the behavioral profile where churn probability drops by a factor of six.

#TradeUnion
#Marketing
#Retention

Problem

The organization needed a data-driven picture of member behavior in order to spot flight risks early and put retention resources where they would matter.

Solution

Tabular machine learning applied to historical membership data to identify which features and behaviors correlate most strongly with retention.

Benefits

Isolated a specific combination of features marking members six times less likely to churn, giving the client a precise target profile for engagement campaigns.

Technical solution

Architecture

Exploratory data analysis and predictive modeling focused on feature importance and interpretability.

Technologies

Python, pandas, scikit-learn, XGBoost, recursive feature elimination, matplotlib and seaborn for the exploratory phase, SQL over the membership database

The Onion Framework: Stress-Testing RAG Reliability

Labour Digital Slovakia (methodology applied as a deployment gate across key client deployments)

An internal evaluation framework used on key client deployments exposed RAG failure modes before launch and eliminated major and medium-level post-deployment complaints in those applications.

#Technology
#SoftwareHouses
#Evaluation

Problem

RAG systems demo well and fail quietly. Retrieval misses, answers drift from the source, and the failure only surfaces once a user has acted on a wrong answer in production. Teams had no systematic way to know whether a system was ready to ship and face real-world queries.

Solution

A multi-layered evaluation methodology that tests a RAG application systematically layer by layer, starting from the core in-topic domain and ending with off-topic and adversarial layers. It was used with key Labour Digital Slovakia customers as a gate before production rather than as a post-mortem after deployment.

Benefits

Failure modes were identified and addressed before deployment rather than in production. Across the key customer deployments where the methodology was applied, major and medium-level complaints reported before its application fell to zero afterwards.

Technical solution

Architecture

Layered test harness over generation stress-testing app with questions mapping knowledge base and its edges, with LLM-as-a-Judge scoring plus curated ground-truth sets, run as a repeatable suite rather than a one-off assessment.

Technologies

Python, DeepEval, LLM-as-a-Judge scoring, Langfuse for trace capture

Semantic Interoperability for E-Government Services

European Commission (Access-eGov FP6 project; no commercial partner applicable)

An EC-funded proof of concept resolved citizens' goals into cross-authority service sequences and validated three public-service processes in three EU countries.

#Government
#PublicSector
#KnowledgeRetrieval

Problem

Citizens dealing with a life event such as a relocation or a business registration had to work out for themselves which authorities were involved and in what order. Each administration published its services in its own structure, so nothing could be composed across institutional boundaries.

Solution

Public services were semantically annotated against a shared model, letting a citizen's goal be resolved into the sequence of services that satisfies it, across authorities. The same annotation approach was extended to heterogeneous document repositories, making digitized collections searchable by meaning rather than by the structure each institution happened to use.

Benefits

Services from separate authorities became composable into a single guided process, and previously siloed collections became retrievable through one semantic layer. The R&D proof of concept ran from January 2006 to February 2009 and deployed and tested three concrete processes with public organizations in Germany, Poland, and Slovakia.

Technical solution

Architecture

Ontology-based service annotation with a resolution layer that assembles applicable services into a goal-driven sequence, plus semantic annotation pipelines for heterogeneous document collections.

Technologies

WSMO and WSML service modelling, OWL, Protege, Sesame RDF store, Java EE, Apache Tomcat, XML

INERTIA

European Commission (EU-funded INERTIA project; commercial partner: [CNET Svenska](https://www.cnet.se/))

A research prototype combined building schedules, IoT data and occupancy context to demonstrate how prosumers could expose flexibility for grid balancing.

#Energy
#IoT
#ProcessAutomation

Problem

Grid operation with renewable distributed resources needs robust, reliable prosumers (consumers and producers) to balance demand and supply and address local imbalances. Addressing those imbalances on the supply side alone is expensive and carries a risk of cascading blackouts from local to regional level.

Solution

Device and sensor data, including occupancy-related data, were semantically integrated with enterprise schedules. This made it possible to assess upcoming energy demand for appliances and HVAC systems across floors and entire buildings. Context- and occupancy-aware rescheduling then estimated consumption flexibility, enabling a prosumer to trade this information and operate as a local virtual power plant from the grid operator's perspective.

Benefits

The R&D proof of concept demonstrated prosumer flexibility and grid-balancing potential through a multidimensional evaluation covering energy demand, occupancy and comfort on a laboratory installation in a real building with appliances and HVAC. No quantified energy or cost reduction was established in the supplied project record. The work remained a research prototype, but [CNET Svenska](https://www.cnet.se/) subsequently used the technology as the basis for the [CheckWatt](https://checkwatt.com/sv/) spin-off.

Technical solution

Architecture

Semantic middleware layer bridging device networks and enterprise applications, with event processing that translates physical events into business-level context.

Technologies

LinkSmart (Hydra) semantic middleware, Java, RDF and OWL device ontologies, SOAP and REST connectors to ERP

Comorbidity Decision Support for Specialists

European Commission (PICASO H2020 project; commercial partner: [CNET Svenska](https://www.cnet.se/))

An EC-funded research prototype organized cross-condition patient data around clinically relevant interactions and later became the basis for CheckHealth.

#Health
#Clinics
#DecisionSupport

Problem

Chronic disease management breaks down when a patient has several conditions at once. The relevant history is scattered across systems and specialties, and the specialist has minutes to find what matters. The harder problem is not collecting the information but presenting it so the clinically significant interaction is visible.

Solution

Patient information relevant to the specialist's own question is collected across conditions and presented in one view, organized around the interactions between comorbidities rather than as separate per-condition records.

Benefits

The specialist could see the clinically relevant picture across all of a patient's conditions in one place rather than reconstructing it from separate records under time pressure. The result remained a research prototype rather than a production clinical deployment; [CNET Svenska](https://www.cnet.se/) subsequently used the technology as the basis for its [CheckHealth](https://checkhealth.se/) spin-off. Project dates were not specified in the supplied record.

Technical solution

Architecture

Aggregation across clinical sources into a unified patient model, with a presentation layer organized by clinical relevance rather than by source system.

Technologies

HL7 v2/v3 and later FHIR interfaces, SNOMED CT and ICD-10 vocabularies, semantic patient and comorbidity models, Java EE, D3.js visualization, SQL clinical data store

Public Procurement Data Analytics

TRANSPAREX, a.s.

The complete available history of Slovak procurement notices was transformed from nested XML into the analytical dataset behind a live product.

#Government
#PublicProcurement
#Analytics

Problem

Public procurement is published as open data but not as usable data. Notices arrive in deeply nested and inconsistent XML structures, which meant that questions about who wins what, how often, and at what price could not be answered without substantial manual work per question.

Solution

Complex procurement structures were parsed and normalized into a queryable model, turning published notices into a dataset that supports analysis across contracting authorities, suppliers and time.

Benefits

Procurement questions became answerable by query rather than by manual inspection, making patterns across authorities and suppliers visible at scale. From November 2019 to June 2021, the work processed the entire available history of Slovak public procurement published on [uvo.gov.sk](https://www.uvo.gov.sk/) and powered the live [Transparex](https://transparex.sk/) product.

Technical solution

Architecture

Extraction and normalization pipeline over heterogeneous procurement XML into a relational model built for analytical queries.

Technologies

Python, XML, XSLT, SQL

Recognise your problem here?

Most of these started as a half-hour conversation about where the work was piling up.

Book a call