Have you ever seen a product or outfit that you liked but didn't know how to find online? Maybe you want a certain aesthetic, and putting that idea into words isn't really working. Try typing "green shoulder ties dress flowy bottom" into your favorite apparel store's search bar. If it doesn't return the right results, they're likely not using visual discovery. https://shimmer.so/search?q=gree... With Shimmer, powered by Mixpeek, shoppers can even combine pictures with words to find exactly what they're looking for. Search likes "I want this product, but in a retro style" are possible. Starting with the science: Amazon published a paper where they introduced visual search via an A/B test and noticed an entire 2% increase in CTR (clickthrough-rate). For a company that does 1.6m purchases per day [1], that's an instant increase in 32,000 purchases. Per day. This means every store that isn't using this technology is losing out on sales. You can even select the products you like, and refine them with another search. This takes the images you like and combines them with text to deliver results that overlap in similarity.

Congratulations on the launch Ethan! 🎉 My wife will be happy to know that there is such a cool product 😊

Congrats on the launch! The product looks amazing. Just a small feedback, When loading the pages I believe the website ends up showing No Items Found till the item is found, which makes it look a little weird from an end user experience. Also would it be possible in the future to also filter with shipping options? Like the query would become something like "Blue Nike High Tops shipping to England".

Congratulations on your outstanding launch! Your product is not only innovative but truly impressive. It has always been a tiring process to endlessly scroll in search of the perfect item. However, with your solution, the search becomes effortless and precise - knowing exactly what we're looking for and where to find it is truly remarkable. It's indeed an amazing advancement in product searching

Congrats on the launch, this is certainly an interesting use of AI. Could you share some of the problems you had trying to develop this? Was there anything that proved really difficult to get right?