Skip to main content
Isometric white robot juggles golden coins on a bright yellow background flanked by white arrows.

Wrapping Up the Second International GenAI Raiffeisen Tech Hackathon

What happens when 75 colleagues from Poland, Romania and Kosovo get 1.5 days to experiment, collaborate and turn real business challenges into AI-powered solutions? Hack’a Token, the 2nd International GenAI Raiffeisen Tech Hackathon, brought together 19 teams to find out.

  • By Klaudia Bednarczyk, Iulia Trica
  • Case study

On 16–17 November, teams worked from Warsaw, Bucharest and Pristina, as well as remotely. All 19 joined the Development Stream to build working applications using Agentic Engineering, agentic workflows and AI-assisted development.

Teams posing at a Raiffeisen backdrop, a seated audience and gold medals.
Audience of young adults seated on stools and sofas watches a presentation in a bright, modern office.

This year’s edition went one step further. Alongside building working applications, participants explored Agentic Engineering, modern AI-driven development practices and RBI PDLC, while paying particular attention to responsible AI and token consumption.

Yellow signs on black benches advertise a "Conference pass" prize, with a robot mascot, at a Raiffeisen hackathon.
Rows of gold medals with yellow centres and a cartoon robot mascot lie on a black surface.
Yellow paper bags printed with "Make it happen" and the Raiffeisen Bank International logo line a wooden shelf.

The result was 1.5 intense days of coding, testing, learning and exchanging ideas across locations.

75 Participants

19 Teams

1.5 Days

7 Use Cases

An International Development Challenge

The teams — 10 from Poland, 5 from Kosovo and 4 from Romania — each chose one of seven business challenges and had 1.5 days to build a working solution.

1.      APEX Change Intelligence Agent

An AI assistant to help Service Management teams assess deployment risks, dependencies and impacts, recommend deployment sequences, and turn insights from tickets and discussions into updates to SOPs and technical documentation.

 

2.     Employee Onboarding Assistant

An AI assistant guiding new employees through onboarding, from credentials and system access to project-specific information, to help them get started faster.

 

3.     GDS MyHR

A redesign of the Appian-based myHR application using Angular 22 and Java Spring Boot, aligned with the GDS Web experience. It combines employee self-service with role-based tools for HR teams to manage records and approve requests.

 

4.     Margin Engine for FX Products

A solution to help local banks manage FX products across customer segments and channels. Insights into customer needs and price sensitivity support pricing decisions, more tailored offerings and opportunities to increase gross income.

 

5.     Raiffeisen Knowledge Base Center (RKBC)

An AI knowledge assistant bringing Jira, Confluence, GitHub, Splunk, ServiceNow and Microsoft Teams into one conversational interface. Employees can ask questions in natural language and find source-backed answers without switching between tools.

 

6.     NextGen eBanking Frontend

A modern eBanking frontend concept for RBKO, initially using mocked data and designed for future REST API integration with existing banking systems — a potential alternative to the current solution.

 

7.     Sprint Guard AI

An AI agent connected to Jira, Confluence and Zephyr that checks user story readiness and testability, supports capacity planning and scope control, and assists with sprint closure to improve delivery predictability.

 

 

Colleagues work at laptops in a bright open-plan office, with a man in glasses in the foreground.
Colleagues work at desks with multiple monitors in a bright open-plan office beside a yellow "Raiffeisen Tech" panel.
Four men work on laptops around a wooden meeting table, while a wall screen shows lines of code.
Three men work on laptops at a table, watching a wall-mounted screen in a small meeting room.
Three men work on laptops at a table while a wall screen shows code behind them.
Women work together at a wooden table with laptops beside a yellow bag reading "Make it happen".
A woman in a black top works at a computer in a bright open-plan office, with colleagues working behind her.
Three colleagues gather around a computer screen in a bright office, one pointing and another laughing.
Four colleagues talk around a long white table with laptops, water bottles and coffee cups in a meeting room.
Three colleagues gather around a laptop on a white table in a bright meeting room, studying the screen together.
Three men work side by side on laptops at a desk in a bright office with plants and monitors.
Three colleagues work on laptops at a wooden table in a meeting room with concrete walls.

Experimenting With AI Responsibly

Hack’a Token was not only about what teams could build. It was also about how they built it.

Participants were encouraged to explore Agentic Engineering and AI-assisted development while keeping a close eye on responsible AI and token consumption. The hackathon also provided an opportunity to experiment with RBI PDLC, the new AI development framework, and explore how it can support modern software development practices. AI coaches and technical experts and organisers helped with technical issues, token limits and the available tools.

1.5 Days to Build, 5 Minutes to Convince

Each team had five minutes to demo its solution to an international jury of AI and technical experts, followed by a two-minute Q&A. The jury assessed innovation, business value, technical implementation, responsible AI use, presentation quality and overall impact.

A man in a yellow T-shirt works on a laptop in a lounge with yellow Raiffeisen-branded boxes and a large screen.
Four men watch intently from a desk while a colleague in the foreground types on a laptop.
A young woman in a black cardigan smiles at a laptop on a wooden desk in a bright office with posters.
Three colleagues gather around a computer screen in a bright office, one pointing and another laughing.
A man in a black T-shirt holds up a sheet of paper and speaks beside a woman, with yellow posters reading "1st place".
A man in a navy polo shirt gestures while speaking beside laptops at a hackathon in an office.
Four colleagues gather around a laptop at an office desk, smiling as they look at the screen together.
Screenshot of a Raiffeisen login dialog on a monitor during a video call, marked as a demo with simulated sign-in.

Hackathon Results and Winners

After 1.5 days of intensive development and a full round of team demos, the jury selected the projects that stood out most strongly in terms of innovation, business value, technical quality, responsible AI usage and overall execution.

Two colleagues shake hands in a bright office while two others look on and smile.
Man in a yellow shirt holds a first-place sign above gold tokens while two people look on at a hackathon.
Four people pose with gold medals and a woman holds a "1st place" conference pass sign in an office.

Design is my passion – Poland

How do you turn an AI-generated interface into an experience that works for its users? For the five designers behind Design is my passion, the My HR challenge brought AI-assisted development together with UX expertise and user testing. They built a working application for employees, managers and HR, covering leave requests, personal data changes, payslips, contracts and training, with requests moving between the relevant roles for approval. Alongside implementing an AI assistant, they refined the AI-generated interface through UX expertise and user testing.

LGTM – Poland

At the heart of LGTM’s prototype was RTECH: an AI banking assistant that can answer questions using the customer’s banking context — and refuse requests for investment advice within its defined guardrails. Around it, the team built a new digital banking application covering accounts, transactions, transfers, notifications and customer profiles. Automated testing, security scanning and CI processes supported the prototype, bringing the story beyond the interface to the engineering behind it.

AI Need Coffee – Kosovo

Everyday banking was only part of the picture for AI Need Coffee. Their new e-banking experience paired a responsive prototype covering accounts, transactions, payments, cards, statements and other everyday banking services with an AI Financial Coach. The coach analyses a user’s financial situation to provide a financial health score, insights, risk alerts and recommendations. An additional AI assistant supports banking activities, bringing day-to-day tasks and financial insights into the same experience.

Two smiling women hold a yellow "2nd place" award sign with a robot illustration in an office.

UnauthorizedAccess - Poland

An answer is more useful when you can check where it came from. UnauthorizedAccess put that principle into practice in the Raiffeisen Knowledge Base Centre challenge, building an AI assistant that searches connected company knowledge sources and provides answers backed by citations. Users can follow those citations to original sources such as Jira or GitHub, ask follow-up questions and return to previous conversations. Access has a clear boundary, too: the solution respects existing user permissions, preventing users from seeing information they are not authorised to access.

MADS & Machine – Romania

MADS & Machine set its sights on Sprint Guard, designed to help Product Owners and Scrum Masters keep sprints on track. Their solution checks whether stories are ready for development, identifying issues such as missing estimates, insufficient descriptions or acceptance criteria, and missing Zephyr tests. AI can suggest improvements, while Scope Guard monitors changes introduced during an active sprint.

Tokenheimer - Kosovo

How do you turn an AI-generated interface into an experience that works for its users? For the five designers behind Design is my passion, the My HR challenge brought AI-assisted development together with UX expertise and user testing. They built a working application for employees, managers and HR, covering leave requests, personal data changes, payslips, contracts and training, with requests moving between the relevant roles for approval. Alongside implementing an AI assistant, they refined the AI-generated interface through UX expertise and user testing.

For the Top Three Teams

The next opportunity to learn will be an AI-focused event, conference or workshop in 2027. For selected projects, the journey may also continue through further presentations to business and technology stakeholders to explore development opportunities.

More Than a Competition

Hackathons at Raiffeisen Tech are not simply about prizes or rankings. They create a chance to experiment with technologies that are rapidly changing software development, test ideas in practice and learn from colleagues working across different locations and areas of expertise.

Beyond the competition, Hack’a Token gave colleagues across three countries a chance to test new approaches to AI-assisted development and learn from one another — experience they can take back to their everyday work.

Team of prize winners with gold medals holds "2nd place" and "1st place" signs in an indoor lobby.
rtech

Three Countries. One Shared Vibe

Thank you to all participants, AI coaches, jury members, experts and organisers who made the second edition of our International GenAI Raiffeisen Tech Hackathon possible.

Want to get a feel for Hack’a Token? Hit play and meet the people who brought the ideas, teamwork and energy to life.

Authors

  • Klaudia Bednarczyk

    Communications Expert, Organizer of Hack'a Token - Raiffeisen Tech Poland

  • Iulia Trica

    People, Culture & Communication Lead, Organizer of Hack'a Token - Raiffeisen Tech Romania