Get closer to the world of innovative technology

See what our dedicated authors are writing about:
ML, Big Data, Computer Vision, the Data Science UA Blog has it all!

Search

Explore our trending articles

Object detection: how it works

Best object detection models: How they work & how to choose

READ MORE
A recruiter who is searching for a staff

Staff Augmentation vs Outsourcing vs Dedicated Team (Data & AI)

READ MORE
A man who's checking out DS graphics

Data Science as a Service (DSaaS): How it works & costs

READ MORE

Data Engineering vs Data Science: Key differences & roles

READ MORE
a futuristic robot in a bank

Chatbot for banking: Key applications, challenges, and opportunities

READ MORE

SLM vs LLM: Key differences, use cases, and how to choose the right model

READ MORE

Are you ready to go beyond just reading?

Connect directly with our experts to get answers to all the questions.

Data analytics for finance

Data analytics in finance: Key benefits and applications

READ MORE
chatbot for insurance: how to use it correctly

Insurance chatbot: Use cases & benefits

READ MORE
AI agents for finance: features and steps to implement

Top AI agents for finance – Features, use cases & best picks

READ MORE
RAG vs. LLM approach

RAG vs LLM: Which AI approach fits your business

READ MORE
AI used in manufacturing

Top AI agents for manufacturing: How to boost efficiency in your factory?

READ MORE
What role does data play in business profitability?

Clean data – clean processes and decisions. We turn data into a business tool that brings measurable outcomes.

AI in marketing: how it works

AI personalization in marketing

READ MORE
Best AI agents for ecommerce only in this article

AI agents for ecommerce: Applications, types, and key advantages

READ MORE
How to use AI agents in logistics

Best AI agents for logistics and supply chain

READ MORE

AI Recruiter automating candidate screening for a pharma company

Company

NDA

Industry

Pharmaceuticals Manufacturing

Country of the Company

Ukraine

Type of Service

Development

The opportunity

  • One of Ukraine’s largest pharmaceutical manufacturers, manages nearly 100 open vacancies and 1,000 active candidates across Ukraine and Central Asia, generating up to 3,000 screening calls.
  • The existing scripted voice bot struggled with unexpected answers, completing only 75% of conversations without human intervention. Recruiters had to manually verify results, while rigid scripts contributed to candidate drop-offs.
  • The client needed an AI-powered recruiter capable of conducting natural conversations, assessing candidates against vacancy requirements, and automatically passing qualified applicants to HR.

Our approach

  • We replaced the scripted bot with an LLM-powered AI Recruiter capable of conducting natural, adaptive screening interviews in Ukrainian, Russian, Kazakh, and Uzbek.
  • Using an LLM reasoning layer and RAG knowledge base, the agent asks relevant follow-up questions, evaluates responses against role-specific criteria, and maintains a structured screening process.
  • We integrated the solution with CleverStaff ATS, automatically delivering call recordings, transcripts, candidate statuses, and AI assessments within 2 minutes after each interview.
  • A dedicated admin panel allows HR teams to independently manage vacancies, screening prompts, and voice settings without developer involvement.

Value created

  • Increased autonomous screening completion from 75% to 92%+, with 85%+ accuracy in matching candidates to vacancy requirements.
  • Reduced time to first candidate contact from 2 days to under 1 hour, with 24/7 availability and capacity to screen 10 candidates simultaneously.
  • Saved 35+ recruiter hours per week, with screening costs of approximately $1 per candidate.
  • Enabled natural, responsive conversations with under 3-second response times and automatic delivery of results to CleverStaff within 2 minutes.
  • Supported expansion into new regions in less than 1 day, without additional development.

Technologies Used

Azure OpenAI gpt-luna-6.1

Multi-agent orchestrator

RAG knowledge base with a vector database

Azure AI Speech

Google Sheets API

CleverStaff ATS API

Python backend

IP telephony for Ukraine and international calls

Microsoft Azure hosting with HTTPS

Company

NDA

Industry

Pharmaceuticals Manufacturing

Country of the Company

Ukraine

Type of Service

Development

Learn about our impact through case studies

Real-time AI digital human platform for interactive customer experiences

Company

NDA

Industry

AI-powered Services

Country of the Company

USA

Type of Service

Development

The opportunity

  • The client is developing an interactive AI digital human platform that enables real-time conversations with realistic video and voice avatars.
  • The goal is to turn AI avatars from a visual interface into practical digital representatives that can be embedded into websites and business environments for use cases such as customer support, sales assistance, and branded interactions.
  • The product needed to evolve from an actively developed solution into a more stable, partner- and API-ready platform capable of supporting business integrations and agentic functionality.

Our approach

  • We developed and advanced the platform’s real-time voice and video pipeline, enabling users to interact naturally with AI-powered digital humans.
  • Our work focuses on improving platform stability, integration capabilities, and readiness for partner/API deployment while supporting the transition from conversational avatars to more functional AI agents.
  • We are extending the interaction layer with agentic AI tools, enabling digital humans not only to respond to users but also to perform useful actions through connected tools and business systems.

Value created

  • The solution provides a more human-centered interface for AI interactions by combining realistic voice and video communication with conversational AI in real time.
  • The platform creates a reusable foundation for multiple business scenarios – from customer support and sales assistants to personal and branded digital representatives – rather than limiting the technology to a single use case.
  • By combining digital-human interaction with agentic capabilities, the platform is evolving beyond a conversational avatar toward an AI representative capable of both communicating with users and taking useful actions on their behalf.

Technologies Used

Real-time voice & video processing

Conversational AI & LLMs

Real-time communication infrastructure

Agentic AI & tool integration

APIs & business system integrations

Company

NDA

Industry

AI-powered Services

Country of the Company

USA

Type of Service

Development

Learn about our impact through case studies

AI-powered client engagement and personalization agent

Company

NDA

Industry

Fitness & Wellness

Country of the Company

EU

Type of Service

Development

Tasks

  • Develop machine learning models to analyze client behavior, segment users, and predict preferences.
  • Build a personalized recommendation engine for workout plans, services, and offers.
  • Create a scheduling optimization model to align client availability with trainer resources.
  • Integrate a large language model as the conversational core of client’s in-app virtual assistant.
  • Fine-tune the LLM to reflect the company’s brand tone, gym-specific procedures, and customer support guidelines.
  • Build an ETL pipeline to unify data from client’s mobile app, gym systems, and CRM/ERP into a centralized repository.
  • Implement secure cloud storage for models, logs, and backups using AWS S3.

Challenges

  • Historical records were incomplete or noisy, limiting early model accuracy.
  • Client preferences shifted over time, requiring continuous model updates, while new clients or services lacked sufficient data for meaningful recommendations.
  • The LLM occasionally generated plausible but incorrect outputs.
  • The platform needed to comply with data privacy regulations such as GDPR while maintaining user trust.

Solutions

  • Client data used for modeling was anonymized using salted one-way hashes; personally identifiable information was excluded from analytics workflows.
  • Custom instructions, prompts, and reinforcement feedback were used to shape the assistant’s responses, ensuring brand consistency and accuracy in gym-related queries.
  • Built a robust data pipeline to extract, clean, and centralize information from multiple systems, improving data reliability for ML models.
  • Combined behavior prediction, segmentation, and recommendations into one agent that could adapt based on real-time user feedback and platform usage patterns.
  • The mobile app was updated with a clear privacy policy and tools for users to view, export, or delete their personal data.

Outcomes

  • Successfully deployed a secure and compliant AI assistant that recommends content, manages schedules, and engages clients in personalized conversations.
  • Improved user satisfaction through more relevant recommendations and faster response times.
  • Maintained data privacy and built trust with clients through transparent handling of sensitive information.
  • Laid a scalable foundation for ongoing machine learning improvements and LLM updates.

Technologies Used

Pandas

TensorFlow

PyTorch

Scikit-learn

FastAPI

MLflow

Docker

psycopg2

Company

NDA

Industry

Fitness & Wellness

Country of the Company

EU

Type of Service

Development

Learn about our impact through case studies

AI agent for real-time price prediction and automated trading insights

Company

NDA

Industry

Financial Services

Country of the Company

UK

Type of Service

Development

Tasks

  • Build a machine learning model to forecast price movements across selected trading instruments.
  • Develop an AI agent that interprets model outputs to inform automated decision-making processes.
  • Integrate reporting functionality to generate and deliver performance metrics and KPIs.
  • Implement an external trigger system (e.g., email and webhook) to automatically activate the agent and handle follow-up responses.

Challenges

  • Financial markets are unpredictable; historical patterns may not hold during major geopolitical events or policy changes, especially within the UK market.
  • Extracting predictive signals from structured market data and unstructured sources like news or social media required significant effort, with no guarantee of impact.
  • Embedding robust trading safeguards (e.g., stop-losses, position limits) that adapt dynamically to model confidence and market volatility.
  • Models trained on historical data could fail in live trading environments, particularly when trained on limited market cycles.

Solutions

  • Developed adaptive models with online learning capabilities to regularly retrain on new data and adjust to changing market trends.
  • Integrated macroeconomic indicators and real-time event data into the model to improve responsiveness to market shifts.
  • Used automated feature engineering (AutoFE) tools to rapidly test and refine a wide range of input variables.
  • Worked closely with financial experts to vet model features and interpret market behavior accurately.
  • Deployed advanced NLP pipelines to extract signals from news headlines, social sentiment, and regulatory updates.
  • Hosted models on high-performance infrastructure, optimizing serving latency and throughput using FastAPI.

Outcomes

  • Delivered an AI agent capable of handling real-time price predictions for multiple instruments.
  • Enabled automatic activation via email or webhook, with the agent retrieving inputs, executing analysis, and sending back KPI reports.
  • Reduced manual intervention in forecasting and reporting workflows.
  • Created a scalable foundation for automated decision-support tools in financial operations.

Technologies Used

Python

TensorFlow

llama-index

AWS

FastAPI

Gemini

Company

NDA

Industry

Financial Services

Country of the Company

UK

Type of Service

Development

Learn about our impact through case studies

AI platform for streamlined design compliance and reduced project risks

Company

Compass GPT

Industry

AI

Country of the Company

USA

Type of Service

Development

Tasks

  • Develop a Generative AI-powered platform for design compliance.
  • Enable natural language queries of current IBC codes.
  • Incorporate ASCE 7-16 design standards into the platform.
  • Integrate IBC code tables and figures into tailored responses.
  • Allow iterative refinement of queries.
  • Generate project-specific building code review reports.
  • Ensure the platform is mobile and desktop ready.

Challenges

  • The main challenge was to develop an advanced Generative AI interface to address design compliance issues, reduce costly changes that derail project timelines and budgets, and provide easy access to design requirements and insights.

Solutions

  • Developed a Generative AI-powered platform with a ‘ChatGPT’ like interface.
  • Enabled tailored responses to natural language queries of current IBC codes.
  • Integrated key design parameters specified in ASCE 7-16 design standards.
  • Incorporated IBC code tables and figures into tailored responses.
  • Provided the ability to refine queries iteratively.
  • Generated project-specific building code review reports.
  • Ensured the platform is mobile and desktop ready.

Outcomes

  • Transformed the way users access design requirements and insights.
  • Improved efficiency in handling design compliance issues.
  • Reduced project timeline and budget overruns caused by non-compliance.

Technologies Used

LLM

Natural Language Processing (NLP)

Retrieval-Augmented Generation (RAG)

Mobile and Desktop Interface Technologies

COMPANY

Compass GPT

Industry

AI

Country of the Company

USA

Type of Service

Development

Learn about our impact through case studies

Forecasting material consumption and sales

Company

NDA

Industry

Pharmaceutical

Country of the Company

NDA

Type of Service

Consulting

Tasks

  • Implement AI/ML solutions to forecast material consumption and sales, optimizing procurement, supply chain, and production quantities in the Pharma industry.

Challenges

  • Ensuring accurate data collection and seamless integration with existing systems.
  • Managing data privacy and security, adhering to GDPR and HIPAA regulations.
  • Maintaining model accuracy and adaptability to dynamic market conditions.

Solutions

  • Implement ARIMA and LSTM models for time series forecasting of material usage and sales.
  • Integrate models with ERP and CRM systems for seamless data flow.
  • Establish a robust data governance framework.
  • Enable continuous model retraining to adapt to market changes.
  • Enhance procurement planning and production schedules to reduce material waste.

Outcomes

  • Achieve a 10-15% reduction in material waste, improving overall efficiency and reducing costs.

Technologies Used

LSTM

Integration with ERP and CRM systems

Data Governance Framework

COMPANY

NDA

Industry

Pharmaceutical

Country of the Company

NDA

Type of Service

Consulting

Learn about our impact through case studies

Leading AI-powered co-pilot solutions for manufacturing and assembly

Company

nFlux

Industry

Manufacturing

Country of the Company

USA

Type of Service

Consulting/Development

Tasks

  • esign and optimize ML pipelines for manufacturing.
  • Develop scalable cloud infrastructure for ML.
  • Prepare, clean, and annotate data for quality training.
  • Implement CI/CD pipelines for ML models.

Challenges

The main challenge was to create a robust, scalable ML pipeline to process large volumes of manufacturing data in real-time, ensuring reliability and efficiency to support AI-driven co-pilot solutions for operator assistance.

Solutions

  • Built a complete ML pipeline for data processing, training, and deployment.
  • Enhanced scalability and reduced costs with cloud resources.
  • Developed data cleaning tools for high-quality datasets.
  • Integrated CI/CD for seamless model updates.

Outcomes

  • Implementing the ML pipeline boosted manufacturing efficiency and accuracy, while the nFlux Guide™ enhanced operators’ achievement, safety, and reduced stress, leading to greater productivity.

Technologies Used

Python

Tensorflow

PyTorch

AWS

Azure

Docker

Company

nFlux

Industry

Manufacturing

Country of the Company

USA

Type of Service

Consulting/Development

Learn about our impact through case studies

Major energy and gas holding in Europe

Company

DTEK Group

Industry

Energy Generation

Country of the Company

EU

Type of Service

Consulting

Tasks

  • Develop a predictive model on the wind energy production forecast
  • Analyze historical data for accuracy
  • Implement and test the model

Challenges

Accurately forecast wind energy production based on historical data.

Solutions

  • Developed a predictive model for wind energy production
  • Utilized historical data for training and testing the model
  • Implemented machine learning techniques to enhance forecast accuracy

Outcomes

  • Model Forecast – mean Absolute Percentage Error was <10

Technologies Used

Python (pandas, numpy, scipy, scikit-learn)

PyTorch

LSTM

Company

DTEK

Industry

Energy generation

Country of the Company

EU

Type of Service

Consulting

Learn about our impact through case studies

Retail pioneer in health and beauty products

Company

Eva

Industry

Retail

Country of the Company

Ukraine

Type of Service

Consulting

Tasks

  • Analyze customer behavior
  • Identify upselling and cross-selling opportunities
  • Leverage data analytics to boost revenues
  • Increase the average basket size
  • Understand key customer segments
  • Retain customers in a competitive market

Challenges

Need a strategy to analyze customer behavior, identify upselling and cross-selling opportunities, leverage data analytics to boost revenue, and retain key customer segments in a competitive market.

Solutions

  • Developed a new recommender engine to grow the average basket size
  • Implemented a new churn retention strategy based on model’s predictions
  • Leveraged data analytics to understand key customer segments and opportunities

Outcomes

  • The new recommender engine allowed to grow the average basket size by 0.4 items
  • The new churn retention strategy based on our model’s predictions allowed early detection of churning clients, which led to a decrease in churn from almost 20% to 15%

Technologies Used

Python (pandas, numpy, scikit-learn, LightGBM, TensorFlow)

Ederned

Company

EVA

Industry

Retail

Country of the Company

Ukraine

Type of Service

Consulting

Learn about our impact through case studies

Outreach platform for increasing sales and reducing risks

Company

Outreach.io

Industry

Sales Execution Platform

Country of the Company

USA

Type of Service

Development

Tasks

  • Enable real-time audio and text recognition
  • Provide instant insights for sellers
  • Develop a new feature for customizing video and audio content

Challenges

Enabling real-time audio and text recognition, providing instant insights for sellers. Developing a new feature for customizing video and audio content, aiming to enhance the platform’s functionality.

Solutions

  • Released real-time audio and text recognition & processing to offer immediate information to sellers
  • Developed a new feature of video and audio customization
  • Data annotation for multilanguage audio data

Outcomes

  • Immediate information delivery through real-time recognition
  • Enhanced platform functionality with customizable video and audio content
  • Multilanguage data annotation for broader reach

Technologies Used

Python

Golang

React.js

Company

Outreach.io

Industry

Sales Execution Platform

Country of the Company

USA

Type of Service

Development

Learn about our impact through case studies

A global Big Four accounting and consulting firm

Company

Ernst & Young

Industry

Consulting

Country of the Company

UK

Type of Service

Consulting

Tasks

  • Establish a single client-consultant touchpoint for client questionnaires.
  • Enable advanced analytics for consultants.
  • Generate HRPP, Salary reports, and Graded Pay Structure.

Challenges

The main challenge was to create a system that ensures continuous availability, enhances customer experience, boosts consultant effectiveness, and minimizes their data-related tasks.

Solutions

  • Developed a secure, single-touchpoint service with dynamic dashboards and drill-down capabilities.
  • Built an autonomous system with a modern, user-friendly interface.
  • Used historical data for predictive analytics and personalized recommendations.

Outcomes

Improved customer satisfaction with a user-friendly service, enhanced consultants’ effectiveness, enabling greater project scalability, reduced consultants’ data tasks, freeing resources, and showcased EY’s commitment to modern solutions and brand value.

Technologies Used

Python (pandas, numpy, scipy, scikit-learn)

PyTorch

LSTM

Company

Ernst & Young

Industry

Consulting

Country of the Company

UK

Type of Service

Consulting

Learn about our impact through case studies