Non-developer builds native iOS app using AI coding agents
Chemical engineer William Emo built Mural Chat, a real-time language learning app, using AI agents despite having no native mobile coding experience. He emphasizes that articulating design requirements is now more critical than coding knowledge.
William Emo, a chemical engineer with web development experience but no native mobile background, built Mural Chat, a real-time Norwegian language learning app, using AI agents. He chose Swift for iOS and Kotlin for Android to optimize user experience, despite having never written code in those languages. The app relies on OpenAI's GPT Live 1 for real-time voice interactions and GPT-6 Luna for other AI tasks. Emo used Codex to build the application, starting with a detailed prompt specifying an 'aesthetically pleasing' design with 'fall colors' and 'liquid glass' effects. The initial AI-generated design was rejected for being in dark mode, so he refired the prompt to enforce light mode. The app costs approximately $3 to $5 in API tokens for a 30-minute conversation. Emo made the project open source and allocated a $1,000 OpenAI budget for user usage. He contends that the barrier to building native apps has been removed by AI, allowing non-specialists to choose the best technology stack for user experience rather than the stack their human team knows. Emo emphasizes that the key skill is not coding knowledge but the ability to articulate design and product requirements with specificity.