Case study

Survey Website with Automated Report Generation and Questionnaire

The client's goal was to extend their courses from 1 to 20 companies simultaneously. Our team automated questionnaire analytics and built generation of editable Microsoft PowerPoint reports instead of static PDFs, giving the client flexible, presentation-ready outputs.

About the client

The client's goal was to extend their courses from 1 to 20 companies simultaneously. The specific course requires questionnaire processing and thus needs statistics analysis of data and presentation building. Before it was done manually via Excel. The specific need was to automate calculations and presentation building.

Background and problem

The client needed to scale a questionnaire-based training program from 1 to 20 companies in parallel. All analytics and reports were prepared manually in Excel, while a legacy Python 2.7 App Engine app only handled basic questionnaires and exports. They needed automated analytics and presentation generation, multi-company support, and a modernized platform.

Solution

Our team automated questionnaire analytics and built generation of editable Microsoft PowerPoint reports instead of static PDFs, giving the client flexible, presentation-ready outputs.
We extended the admin UI with multi-company course management and raw data export so the client could run and analyze courses for many companies in parallel.
Our team also enabled external stakeholders to participate via a pre-questionnaire participant information flow and upgraded the application to Python 3 with targeted legacy data clean-up to align with Google App Engine requirements.

More cases

See all cases

Health platform for IRIDIUM

The client is a US-based independent continuing medical education company focused on delivering high-quality, innovative learning activities for healthcare providers. They wanted to build several interactive AI Avatars acting as real patients simulating doctor visit and follow-up, along with LLM-powered subsequent dialogue analysis
AI-Powered Pilot Contract Analysis Platform

We built a smart AI chatbot based on a multi-agent architecture. The solution begins with Document Understanding and Structure Repair, using Gemini and OpenAI models with a sliding window technique to transform poorly-structured PDFs into clean, structured text with precise section coordinate mapping.
AI-Powered Horse Racing Intelligence Platform

We delivered a comprehensive platform consisting of a custom CMS, a public-facing website, and a sophisticated multi-agent AI companion. The main challenge was creating a reliable, multi-step AI that could reason over diverse, real-time data sources to generate accurate and context-aware responses. The platform now successfully manages and syncs data for thousands of horses and races from all over the world.