About
Building Trust in Democratic Participation with a Reliable AI Chatbot Assistant
Challenge, approach, and impact
RAG-based AI architecture
Integrating Python, LlamaIndex, and vector databases for accurate retrieval of verified content.
Ethical interaction design
Crafting a transparent UX that shows data sources, session logic, and chatbot identity clearly.
Cost optimization
Testing multiple models—GPT-4o-mini, GPT-4o-nano, and self-hosted LLMs (like Bielik)—to balance performance and affordability.
Evaluation framework
Defining metrics for factual correctness, response faithfulness, and objectivity to continuously improve model behavior.
How we built
Testimonials
Monika Prus-Glaszczka
Center for Civic Education
“What sets Nomtek apart is their cross-functional approach: they assembled a diverse team with expertise spanning UX, development, and product strategy to ensure that the solution would be practical, scalable, and aligned with our long-term goals. Their collaborative mindset and ability to explain complex topics in an accessible way made the entire process feel like a true partnership. We’re excited to continue this journey together and can confidently recommend Nomtek as a reliable, proactive, and thoughtful partner for any AI-driven product development.“
Team structure
Client team
Monika Prus-Glaszczka
Head of the Civic Engagement Department at Center for Citizenship Education
Project stakeholder
The client stakeholders at Center for Civic Education were working closely with the team at nomtek
Agency team
1 x Backend
Production
1 x QA
Production
1 x Designer
Production
1 x Product Manager
Production