Dear Product Hunters! 👋 We’re thrilled to share the Design System Concierge with you! As Design Systems gain more and more traction these days, the amount of available content can be overwhelming, making it difficult to know where to start. Our AI-powered Design System Concierge can help by providing expert guidance and pointing you towards the right resources, whether it's implementation guides, architecture documents, adoption strategies, or other content. To get the best possible help from our Design System Concierge, we recommend asking detailed questions instead of engaging in a chat. The Concierge provides quick and transparent answers by summarizing the most relevant content sources. Every answer includes underlying sources that you can easily check and visit. Trust us to deliver accurate and reliable information for all your Design System-related queries. Please find some more insights on the Concierge in our blog post. We are on a mission to democratize Design Systems. Let us help you confidently navigate the broad Design System ecosystem. Try it, it's free 😊

🎉 Congratulations on launching! It's amazing to see how passion and curiosity can lead to such an innovative and helpful tool. Are there plans to expand the scope of the Concierge to other domains, or is the focus solely on Design Systems?

Super happy we can show this now! Got into this topic (Open AI / GPT-3 / Transformers, etc) out of sheer curiosity, and got kinda sucked in! Developing this was super fun, though... and for the more technically inclined people out there, I've added *all* the details to the following Miro board. Feel free to take a dive, and join us on Discord to chat about it further! And as is customary for us, we've added all the code to Github on an Open Source license, too! 💪 Some of the included tech: ⚡ Supabase PostgreSQL + pgvector + Edge Functions ⚡ Cosine similarity search for relevant sections in database ⚡ Transformed and spliced Server Sent-Events streaming ⚡ Python / Flask embedding webservice hosted on Fly.io ⚡ SBert based embeddings (no Open AI API credits for the embeddings!) ⚡ Open AI / GPT-3 for final answer, augmenting the returned stream ⚡ LangChain, TextSplitter, BeautifulSoup4 for text ingestion ⚡ Jupyter Notebooks and Github Codespaces for compute Miro: https://miro.com/app/board/uXjVM... Discord: https://discord.gg/mwKzD5gejY Github: https://github.com/kickstartDS/c... You can also read our blog post about it: https://www.kickstartds.com/blog...

sounds like an excellent tool to help users navigate the complex world of design systems. thanks for sharing this!

Congratulation on the launch...!

I have to say I find DS slightly complicated, especially if you are not familiar with it, so having KDS and now an AI assistant totally makes sense, I asked a few questions and it threw a few nice docs back to me, thank you!

I just love the execution here. It works really well, and the fact that you get the list of sources for further reading is wonderful, just how responsible AI implementations should be done. Great job kickstartDS team 👏🏻 We now have a link we can send anyone to to learn more about design systems effortlessly. P.S. the design is 😘

What a great idea! I reached out to the Concierge with a couple of questions and their response was spot on. Congratulations on the launch!

Our Concierge is a great way to get answers to your Design System questions. It's powered by AI and sources expert content from our vast Design System database. Simply ask any question and you'll be pointed to the right source.