TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Retool AI

248 点作者 donjh超过 1 年前

13 条评论

cuffe超过 1 年前
Hi all, eng who worked on vectors @ Retool here. We’re excited to get HN’s feedback on a new product I’ve been working on: Retool vectors. There’s been a lot of hype around AI, but as I was thinking about what we could launch, there were really very few AI apps that are today _actually_ delivering business value. For example, there are tons of chatbots, summarization bots, etc., but it wasn’t clear how to use them. There were bots that we could use for answering support tickets (we use Intercom), but when we tried using them, the results were far worse than expected (it only managed to close ~5% of our tickets, and required substantial human intervention).<p>I then tried building a custom AI chatbot for our support team, powered by a vector database (with previous answers, our docs, and community forum data). In my prototypes, the successful response rate was much higher (around 5 - 7x higher, ~30%). But it was surprisingly hard to build this bot: I needed to stitch together vector databases, custom integrations with Intercom, cronjobs to sync data, etc.<p>That’s why we built Retool Vectors. The idea is that we want to build a vector database that has full ETL from whatever inputs you have (e.g. Intercom, a postgres database, Salesforce, a community forum, a website, etc.). It’s always kept up to date. (We’re still working on some of these features, but I decided to try and launch this week because I just wanted to get feedback from HN, haha.) I think the industry has now settled on vector databases as the best way to provide context to LLMs. I hope that Retool Vectors can be a much easier way of getting data into it.<p>If you have any feedback please let me know!
评论 #37423479 未加载
评论 #37425392 未加载
评论 #37424454 未加载
评论 #37423302 未加载
评论 #37423120 未加载
orliesaurus超过 1 年前
My personal opinion (besides this constant flux of Retool product announcements) is that I truly tried and gave Retool a chance... but man, it was tough to get started, I rather just code from scratch with some boilerplate.
评论 #37424068 未加载
评论 #37423836 未加载
评论 #37425498 未加载
评论 #37429048 未加载
评论 #37423432 未加载
评论 #37423782 未加载
评论 #37429815 未加载
dominicwhyte超过 1 年前
We&#x27;ve been using the ChatGPT API from Retool Workflows (for spam detection) and it&#x27;s been valuable for our business. The built-in vector DB looks interesting
评论 #37422654 未加载
willsmith72超过 1 年前
Can someone who&#x27;s been there tell me how the &quot;Trusted by developers, startups, and Fortune 500s&quot; works? How does Retool (or any company) get another company&#x27;s logo here?
评论 #37425771 未加载
评论 #37428037 未加载
评论 #37426529 未加载
评论 #37427817 未加载
tipiirai超过 1 年前
How is it possible that Retool login page [1] loads 6.4MB of resources? The app.js [2] alone is 4.0M when loaded on local machine. Is this common?<p>[1]: <a href="https:&#x2F;&#x2F;app.retool.com&#x2F;auth&#x2F;login" rel="nofollow noreferrer">https:&#x2F;&#x2F;app.retool.com&#x2F;auth&#x2F;login</a> [2]: <a href="https:&#x2F;&#x2F;retool-edge.com&#x2F;app.cd90db16bade51faa017.js" rel="nofollow noreferrer">https:&#x2F;&#x2F;retool-edge.com&#x2F;app.cd90db16bade51faa017.js</a>
评论 #37427639 未加载
评论 #37427601 未加载
ajhai超过 1 年前
Most of the use cases we are seeing LLMs unlock look trivial in isolation when looked at it from content generation point of view but become super powerful when mixed into workflows. This is evident from all the startups we are seeing lately in this space and LLM integrations into existing products like Zapier, Hubspot and now Retool AI.<p>Granted these are still early days for LLMs, but it looks they are primarily going to revolutionize how knowledge work is done at a scale similar to what computers have done. There are exciting projects coming out every week putting LLMs into the workflows of more and more knowledge workers. open-interpreter is the recent of the bunch.<p>Similar to other workflow automation projects in this space, we started building LLMStack (<a href="https:&#x2F;&#x2F;github.com&#x2F;trypromptly&#x2F;LLMStack">https:&#x2F;&#x2F;github.com&#x2F;trypromptly&#x2F;LLMStack</a>) with a goal of scaling knowledge work pieplines. Exciting times ahead!
rocauc超过 1 年前
I&#x27;d love a template for: 1. Select internal document sources you want to ingest (Notion&#x2F;Slab, specific Slack channels, named Google Docs in a folder) 2. Enable Q&amp;A + augmented retrieval in response 3. Serve to end users in a Slack channel at our company
评论 #37427258 未加载
评论 #37425435 未加载
verdverm超过 1 年前
We hear about Retool here more than once a month, is there a new development we are to learn about today?<p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;from?site=retool.com">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;from?site=retool.com</a>
评论 #37422771 未加载
评论 #37423249 未加载
speedz007超过 1 年前
Looks neat. Do you guys plan to allow the use of custom AI models down the road? Especially for the enterprise use case.
评论 #37433542 未加载
cloudecon超过 1 年前
Nice. Would it be fair to say this is directly competitive with Zapier in terms of creating AI-powered workflows?
评论 #37423797 未加载
评论 #37422767 未加载
gaurangblaze超过 1 年前
Looks awesome, congrats! Do you provide any integrations for identifying hallucinated outputs and&#x2F;or showing references with the output (like Bing does)? Such a feature is critical for AI outputs, so it might be nice if it&#x27;s supported out of the box.
评论 #37470278 未加载
anoy8888超过 1 年前
Okay. If it is any good , we need to create an open source and free version for the community
评论 #37433432 未加载
wpydcr超过 1 年前
I would like to know how do you ensure the query accuracy of the vector database?
评论 #37470251 未加载