This Hackathon Team Used AI and OpenEdge to Reduce Manual Data Anonymization Effort

Back in September, the OpenEdge AI Hackathon took center stage at the Leeds Digital Festival and what unfolded was truly inspiring. The event highlighted the powerful combination of the Progress OpenEdge platform and AI innovation, with participants delivering creative, real‑world applications that demonstrated just how practical AI can be when built on OpenEdge.

One standout theme was data anonymization, a real and growing industry pain point. As organizations manage thousands of databases while facing strict regulations like GDPR, anonymizing sensitive data is critical, but often manual, complex and time‑consuming. The hackathon showed how AI can help OpenEdge customers automate this process, reduce compliance risk and introduce modern capabilities without rewriting existing applications.

We had the opportunity to sit down with the second‑place winning team—lead Razvan Stetcu, along with Stăncuta Porumb and Sergiu Vescan from Wayfare—to learn more about their project, the challenges they faced, and what they discovered by combining OpenEdge with AI.

The Hackathon Challenge: Bringing AI into an Existing Product

For Razvan, the motivation to join the hackathon was clear from the start.

“I’m always excited when I need to implement something that will use AI.”

Rather than building something entirely new, the team chose to enhance an existing Wayfare product called DBlur—a data anonymization tool designed to help organizations comply with GDPR and other privacy regulations.

The challenge? Scale.

“When you have hundreds of tables and a lot of fields inside, it’s a lot of work to check each table and decide what needs to be anonymized,” Razvan explains.

That made DBlur an ideal candidate for AI augmentation.

The Idea: AI‑Driven Suggestions for GDPR Compliance

The team’s goal was to use AI to suggest which database fields should be anonymized, dramatically reducing manual effort while keeping developers firmly in control.

Using Progress Agentic RAG, the solution analyzed GDPR and compliance rules uploaded as PDFs, extracting guidance from unstructured documents to recommend anonymization rules for a given database schema. This approach helped identify sensitive fields efficiently without relying on rigid, rule‑based logic.

Instead of starting from scratch, developers can review AI‑generated suggestions, adjust them as needed and then proceed with anonymization.

“The purpose was to review what AI selected, add or remove a few fields if needed, and then just move forward,” Razvan says.

Importantly, the AI does not act autonomously. Human validation remains a core part of the workflow, helping avoid mistakes and ensuring compliance.

How OpenEdge Powered the Solution

OpenEdge played a central role in the project’s architecture.

“DBlur’s backend is in Progress OpenEdge,” Razvan explains. “The frontend is React, and for the AI we used Progress Agentic RAG.”

With OpenEdge handling backend logic and database operations, the team focused on integrating AI where it added the most value—field identification and decision support—without re‑architecting the application.

The result was a modern, hybrid architecture: OpenEdge remains the system of record and core business logic engine, while AI services deliver intelligent analysis and recommendations. This model enables organizations to enhance existing OpenEdge applications with AI without disrupting proven systems or requiring large‑scale migrations.

The Hackathon Experience: Fast‑Paced and Collaborative

The team described the hackathon as intense, fast‑paced, and highly collaborative.

“The idea was very nice. Building something that uses AI, building the team and the fact that we managed to communicate and understand each other from the very first step,” Razvan says.

Time constraints were the biggest challenge. Early on, the team explored a different idea before realizing it was too ambitious.

“At first we wasted like two days on an idea, and after that we changed it because it was too much work and we didn’t have enough time,” he admits.

Even so, the pressure helped sharpen their focus and they delivered a working solution by the end of the event.

Learning AI with OpenEdge

For some team members, the hackathon marked their first hands‑on experience combining AI with OpenEdge.

“It was the first interaction with AI—and especially with Progress,” says Stăncuta Porumb. “It was a nice experience, and I learned a few new things.”

Sergiu Vescan echoed that sentiment, highlighting the practical learning opportunity.

“I learned a lot of new things about the AI field,” he says, “and I had the opportunity to write Progress OpenEdge code to send POST requests to Agentic RAG, which was the first time in my life.”

What’s Next for the Project?

Future enhancements could include deeper automation, tighter integration with OpenEdge APIs and newer AI capabilities such as the OpenEdge AI Assistant (formerly MCP Connector for ABL) and the OpenEdge MCP Server—both discussed as potential next steps toward production‑ready AI workflows.

Why It Matters

This hackathon project demonstrates a practical, business‑focused approach to AI adoption. Instead of replacing existing systems, the team used AI to augment an OpenEdge‑based application—saving time, improving accuracy and keeping developers in control.

It’s also a strong example of how OpenEdge continues to evolve alongside modern technologies like AI, enabling innovation without forcing teams to abandon the systems they already rely on.

As Razvan summed it up simply:

“It was a great experience.”

Discover What’s Possible with Progress OpenEdge

This project shows how organizations can use AI with existing OpenEdge applications to automate workflows and improve efficiency without rewriting their systems. With modern integration capabilities from Progress OpenEdge, developers can quickly add intelligent features while preserving core business logic.

• Get started with OpenEdge MCP Server to begin integrating AI into your applications
• Explore OpenEdge AI Assistant to extend AI‑driven workflows