TE
테크에코
홈24시간 인기최신베스트질문쇼채용
GitHubTwitter
홈

테크에코

Next.js로 구축된 기술 뉴스 플랫폼으로 글로벌 기술 뉴스와 토론을 제공합니다.

GitHubTwitter

홈

홈최신베스트질문쇼채용

리소스

HackerNews API원본 HackerNewsNext.js

© 2025 테크에코. 모든 권리 보유.

Show HN: Super (YC W18) - Turn company data into answers & agents for your team

16 포인트작성자: christophepas4일 전
Hey there, Chris here<p>We&#x27;re known for our straightforward yet powerful Knowledge Base, Slite(YCW18).We launched our AI-powered search in Feb 2023 and after getting great response and usage, we dove deeper into solving the challenge of knowledge retrieval in daily work.<p>That&#x27;s why we&#x27;re now launching our second major product, Super(<a href="https:&#x2F;&#x2F;www.super.work" rel="nofollow">https:&#x2F;&#x2F;www.super.work</a>).<p>Super seamlessly connects your existing tools, providing accurate answers, streamlined workflows, automated digests, and much more.<p>You might wonder: Why not just link your apps together using something like an MCP? The problem is that MCPs can&#x27;t handle complex knowledge retrieval effectively. MCPs are basically LLMs equipped with API toolbelts. If you&#x27;ve ever tried asking a complicated question through an MCP, one that needs data from multiple different tools, you&#x27;ve likely faced frustrating delays. MCPs slowly make API calls one after another, causing long waits while they collect data from each endpoint.<p>By contrast, Super quickly searches through all the data that actually matters from all of your tools simultaneously. This means you&#x27;ll get your accurate answer in seconds, not minutes.<p>The limitations of MCP-based solutions become clear when you try to deploy them reliably within a team. They either won&#x27;t index your critical content effectively, won&#x27;t do it fast enough, or won&#x27;t cover all your tools at once. Properly chunking, embedding, querying, and filtering data from various sources is still essential. MCPs triggering APIs can&#x27;t match this integrated approach for speed and accuracy.<p>Moreover, Super understands the value of running multiple tasks simultaneously through LLMs. For example, one step may involve identifying search filters, while another simultaneously uses an LLM to aggregate and refine information. This parallel process quickly shapes the final, accurate answer for users.<p>Additionally, MCPs aren&#x27;t designed for enterprise-grade use. Businesses need standardized experiences, fine-grained user permissions, and consistent access controls across multiple tools. Super addresses these requirements by indexing data beforehand while still respecting each user&#x27;s access permissions.<p>Super offers: - Perplexity-like search experience on your team data - A growing selection of integrations with popular data sources - Customizable AI assistants tailored to your specific needs - An extension to embed Super directly into external websites you&#x27;re already using - A clear path for your company to adopt AI strategically, rather than letting individual employees scatter across different, incompatible tools.<p>And of course... It does comes with its MCP, which makes your agentic workflows actually able to properly tap on your data.<p>Here&#x27;s a quick video showing Super in action: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=L5A6BRW90K4" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=L5A6BRW90K4</a><p>Have you hit such walls with standard MCPs? Have you try building your own solutions?

2 comments

AnhTho_FR4일 전
Awesome, love the name. In terms of use cases, would you replace an agent created by something like Glean (let&#x27;s say the agent was dedicated to retrieving internal knowledge for CS teams or Sales teams)?
评论 #44052002 未加载
calyhre4일 전
Hey, I worked on this. Feel free to shoot any questions if you like