Obinna Chimdi started learning programming at age 16. “I started programming with my dad’s mobile phone,” he said to Techpoint Africa. He completed his first project in three months, teaching himself as he went along, he said.
The Nigerian student was inspired by Mark Zuckerberg, describing him as his idol. “I loved automations too, I wanted to have my own AI company, and I had to learn how,” he said. Chimdi went on to build a social media platform called Wall Street to connect business people but his most ambitious project yet is ChatATP, which allows users to chat with any website to perform actions.
The 18-year-old Mathematics and Computer Science student at the University of Port Harcourt (UNIPORT), Nigeria, said he aimed to build something that makes large language models like ChatGPT do more than only chat with users.
“I realised that tools like ChatGPT are powerful, but they’re not built to solve problems end-to-end,” he said. “If you ask them to analyse data and send the report to someone by email, for example, they stop halfway. You still need to copy, paste, or do the rest yourself.”
This led him to experiment with combining different AI models and adding execution layers on top, he explained to Techpoint Africa. ChatATP was the result.
He essentially designed a system that connects AI models with websites through toolkits. The young innovator described these toolkits as small connectors that act like translators, defining particular actions, such as checking flight availability or sending an email from Gmail.
But the most important piece about his project is the building of the Agents2 protocol. Chimdi described Agents2 as “HTTP for AI agents” — “a simple, universal protocol that defines how models and toolkits talk to each other. Just as HTTP standardised how browsers fetch web pages, Agents2 standardises how AI agents call tools, making them interoperable and scalable,” Techpoint Africa wrote.
The 18-year-old explained that to get started with ChatATP, a user must first “configure an API key from any major LLM provider, install and enable domain-specific tool kits, and choose the model they want powering their agent. After that, website visitors simply type natural-language prompts, and the system reasons through the chosen model and tool kits to deliver results.”
The journey to creating ChatATP was tough, as he couldn’t find collaborators. “Everyone I wanted to work with declined.”
“They were too busy,” he recalled. Chimdi used six months to build his platform as he had to upgrade his skills along the way.
“I’m a backend developer; I could not find any frontend developers, so I had to learn. I couldn’t even get UI and UX designers.”
Currently, his platform has only three users—his neighbour and two course mates. He hopes to attract more users, but this would require funding, which he doesn’t have at the moment.
He needs to win over more users to attract investors and stay ahead of the competition. Despite these obstacles, Chimdi’s platform shows that Africa’s next generation of innovators are not only consuming AI but designing solutions to address various challenges.
