The App That Finally Said 'Yes' — And How It Changed the Way We Learn
When the Local Dialect app first went live, it was a mix of excitement and uncertainty. But the moment it worked — when a learner said 'Yes, this is how I speak' — reminded me why I'm building these tools for real people in Kenya.
There's a strange kind of magic in the moment when the code you've written finally says 'yes' — not just in the sense of functioning, but in the way it resonates with the people it's built for. For me, that moment came when I watched a learner on Local Dialect say, 'This is how I speak.' It wasn't just a line of code running smoothly; it was a connection to a language that had been overlooked for far too long.
The journey to that moment wasn't easy. Local Dialect started as an idea — a way to bring Kenyan and African languages into the digital space. But building for languages that aren't widely supported by AI tools was a challenge. I had to find ways to make the app work with limited data, and that's where AI collaboration became essential. I used Claude and Codex to help structure the user flow and content architecture, ensuring that the app didn't just teach grammar, but real, conversational language.
There were times when the app didn't work as expected. I remember one day when the AI-generated lessons were too formal, too far from how people actually spoke. I had to go back and adjust the training data, making sure that the lessons reflected the way people talked in real life. That process taught me something important — the app wasn't just about the code, it was about the people it was meant to serve.
When the app finally worked, it was more than just a technical achievement. It was a reminder that building AI tools isn't just about writing code — it's about listening, adapting, and ensuring that the tools we create truly meet the needs of the people who use them.
Now, when I see learners using Local Dialect and hearing them say 'yes' to the way the app speaks, I know the work was worth it. It's not just a product; it's a bridge between technology and the everyday lives of people in Kenya.
That same kind of connection is what I hope to bring to all the tools I build — from the logistics platforms that help drivers manage their routes to the educational apps that help children learn in a way that feels natural and familiar. The human side of building AI-powered products is what keeps me going, day after day.
So, when the code says 'yes' and the people say 'yes' back, I know I'm on the right path — not just as a builder, but as someone who wants to make sure the tools we create truly belong to the people they're built for.
