U.S.-Based Tech-Developer, Tony Okeke & Team, unveil Xploit To Secure Global AI Workflows

A United States-based 23 year old tech-developer, Tony Kabilan Okeke, led a five-man team of Drexel University, Philadelphia, Penn., U.S. alumni and students to develop Xploit, an automated cybersecurity testing tool for AI agents, an ambitious concept that addresses a growing problem in AI landscape.

Beside Tony Okeke who is the Team Lead, other members of the team are Kamdi Okeke, Kiitan Fawole, Dalu Okonkwo and Michael Moemeke.

Speaking to our reporter on the development, Tony said, “As more businesses deploy AI agents that can take actions and use tools on behalf of customers, these systems become potential security risks. Unlike simple AI assistants, agents have access to tools and can perform real actions – meaning a security vulnerability isn’t just a PR problem, it could have serious real-world consequences.”

The team envisioned a tool that could automatically test an AI agent for vulnerabilities – essentially playing the role of a digital attacker to identify weaknesses before real threats could exploit them. This was the outcome of their brainstorming on November 21, 2025, when Tony led the group to build and pitch Xploit in the “Start-Up In a Weekend” Hackathon hosted on November 21 – 23, 2025 in Philadelphia, by The Foundry & Velric, a Philadelphia-based founder-first community that act as a startup ecosystem catalyst.

Tony designed the system’s architecture and created the initial prototype of the user interface (UI). The UI concept was crucial: it needed to visually show how their automated attacker was thinking, strategizing, and attempting different approaches in real-time, all displayed through interactive graph showing the attack process as it unfolded.

Responsibilities were strategically divided amongst the team. Some members created sample AI agents to serve as “victims” for testing. Tony developed the core attacking system. One person refined the user interface, and others handled the technical infrastructure connecting all the pieces together.

The attacking system itself works like a strategic game player. It would first choose an attack strategy, then create a detailed plan, execute that plan step-by-step by sending messages to the target AI agent, and analyze the responses to determine whether to continue or try a different approach. Throughout this process, the web interface displayed everything happening in real-time, allowing users to watch the automated tester work.

The team then integrated everything — making the attacker communicate with the victim AI agent systems, ensuring the automated testing loop ran smoothly, and polishing the final product. They recorded their demo video and submitted their project before the 9 am deadline on November 23, 2025.

During the afternoon judging session, the team delivered their pitch, framing their project around a massive, unaddressed market shift, highlighting a critical market gap: while the explosion of AI agents in 2025 has seen enterprises deploy them to manage everything from infrastructure to sensitive tasks like financial analysis and customer support, small and medium-sized businesses (SMBs) are left vulnerable because they cannot afford to test them for security flaws. Unlike tech giants, SMBs lack the resources for dedicated AI security teams. Xploit, automated cybersecurity tool, directly addresses this need, positioning itself within a booming continuous automated red-teaming market projected to skyrocket from $495 million in 2024 to $4.9 billion by 2032. Xploit democratizes AI safety, levels the playing field, allowing any business to automatically test and secure their AI agents before deployment.

The judges were impressed enough that they took an unusual step — they asked to see the team’s code and development history to verify the project had actually been built during the hackathon weekend. This verification was necessary because the judges found it hard to believe such a polished product could be created in just one weekend.

The team won the “new project track” award and $1,500 in prize money.

“What made the achievement particularly remarkable” according to Kamdi Okeke, “wasn’t just that we built it over a weekend — it was that, competing amongst a diverse group of 100+ of Philadelphia’s most driven creators, we built Xploit in less than a day of actual development time, transforming an abstract idea into a working, polished prototype through focused collaboration and strategic planning.”

Speaking further, Tony said, “The experience at yet another hackathon, UEV’s Venture Building Weekend hosted in Philadelphia, March 12 – 14, 2026, was a turning point for us. The mentorship and feedback we received from industry operators helped sharpen how we think about the problem and where our approach fits in the market.”

United Effects Ventures (UEV) is a Philadelphia-based pre-seed venture studio. Through its Venture Building Weekend, a competitive hackathon, focused on problem validation and go-to-market strategy, teams refined their ideas with guidance from experienced operators and investors. After a grueling 48-hour sprint, Xploit came tops, outperformed 15 other competing teams, earning a cash award and two advisory sessions with partners at UEV; and most importantly, industry experts validated Xploit’s focus on continuous red-teaming as a strong approach to discovering vulnerabilities in AI-powered products.

Mentors at the hackathon validated both the team’s identification of the problem – the growing security risks posed by AI agents operating autonomously in enterprise environment – and their approach of framing the product as continuous red-teaming platform, which could support an ongoing service model.