Astrid is a game changing AI personal shopper and stylist. She's like ChatGPT on steroids for apparel. She can help you decide your style vibe and search tens of thousands of products so you don't have to.
Free
Launch Team / Built With
Render Sandboxes: a computer for every agentGive every agent its own machine. Starts in under a second
Promoted
Having previously mapped out the architecture for a digital wardrobe assistant to tackle fashion decision fatigue, I know how difficult it is to translate subjective style into strict backend logic 😂. Relying on scraping and image embeddings rather than just static API feeds is a smart way to bypass the 'endless scroll' problem. I'm curious how you handle the latency issues you mentioned when the agent is scraping and filtering tens of thousands of live products in the background.
Really like the concept and the demo looks great, but it seems a bit slow, as you said. One question, is Astrid also for men?
@manuel_lemholt_berger Thank you!
We are working on way to make it faster. She does a lot of work behind the scenes which is the cause of the latency. But we have some ideas on how to fix this.
For now Astrid is only for women. We can open it up to men if there is enough interest! To make it easier to launch we chose one gender. The reason is because brands are different between women and men. There's a lot of brands that focus on just one gender. We technically have a lot of men's products in the catalog currently, but the brands are overwhelmingly focus on women. And so far getting brand data in has been one of the hardest challenges.
@kyle_rush Get it! Let me know when you launch for men.
Congrats on the launch @kyle_rush, my partner will love this! How are you planning on monetising?
@tsmith92 Thank you! We're planning on a subscription model similar to ChatGPT. The reason being is that we want this to be for the user. We want it to be your shopper and your stylist. We don't want it to feel like an online conversion funnel with cross-sells, upsells, and recommendations from the highest retail bidder. I think it'll be well worth the monthly subscription fee.
@kyle_rush Awesome, good luck!
Congrats on the launch everyone! Curious, what are the most unobvious challenges with surfacing styles based on user queries? Is it hard to get models to have good taste when it comes to picking products?
@asim_shrestha1 Good question! The models are surprisingly competent with fashion and style. We did a major project where we evaluated nearly all frontier LLMs on this (Gemini, OpenAI, Anthropic, Llama, Deepseek, etc.). Some models are head and shoulders above the rest.
I would say what's been the most unexpectedly hard thing is finding products via image embeddings. We tried CLIP (by OpenAI) and even fine-tuned it, but still it's quite hard to get results exact enough for fashion. We even experiment with Fashion-CLIP, which is CLIP fine-tuned on Farfetch product data.
All that said, after hitting those roadblocks and having all those learnings, I've never been more confident about deep learning models helping users in the fashion and style space. I think there's a lot of possibilities and we're not far off from some major unlocks.
@kyle_rush Amazing- can definitely see that work through the products Astrid surfaces!
Are you planning to release any benchmarks for what models did "best"/show what your grading criteria was? Would be super interested to learn more :)
@asim_shrestha1 Possibly! It was a really interesting learning exercise.
@kyle_rush - totally love the UX, branding and colours. I have two questions:
How do you plan to earn money / monetize it?
How do you get your data? Do you plan to integrate with shopify or amazon or something?
@rachitmagon Thank you!
We'll be a subscription app like ChatGPT; this is YOUR AI, not the retailer's AI;
We scrape our data from the internet; A lot of the products we have in our catalog are from retailers using Shopify; We really need to have the product data in our database to do interesting things with it rather than using an API or something; in the future we will probably have a shopify agent that can buy things for you; stay tuned...
@kyle_rush Interesting! Would love to talk more in detail some time but all the best
Interesting product. I'm curious to see how the audience utilizes it, and would you get any sort of commission from the vendor if the consumer purchases the product that the AI recommends?