Fashion Ecommerce is challenging because users have intents that could be very broad Eg: ''I want a dress to wear for my cousin's wedding''. Traditional single-shot retrieval mechanisms like search don't work very well for such intents. To solve this problem we developed ''Maya'', a conversational shopping assistant based on LLMs. Maya has been deployed in production and is available to select cohort of users at scale who come to our platform. It is arguably, one of the earliest production deployments of GenAI Fashion assistants at this scale. We describe the journey of building Maya and lessons post the production deployment.