Overview
Real-time, hands-free natural-language interaction in the browser, with the Web Speech API and OpenAI GPT-4o mini.
The challenge
Real-time, hands-free natural-language interaction in the browser, with the Web Speech API and OpenAI GPT-4o mini.
Solution & approach
- Built an AI virtual assistant on OpenClaw for enterprise customers and a real-time browser voice assistant (Web Speech API + GPT-4o mini); architected a shared design system and frontend dashboard across concurrent client projects; led monorepo adoption and testing to 70% coverage; connected Claude with Linear/Jira, Figma and the codebase for ticket-to-code traceability.