【Hacker News搬运】启动HN:DryMerge(YC W24)-用简明英语自动化工作流
-
Title: Launch HN: DryMerge (YC W24) – Automate Workflows with Plain English
启动HN:DryMerge(YC W24)-用简明英语自动化工作流
Text: Hi HN! We're Edward and Sam, the founders of DryMerge (<a href="https://drymerge.com">https://drymerge.com</a>), a tool to automate workflows with plain English. For example, a user can say "When I get an email from a potential customer, add their details to a google sheet and send me a text", and DryMerge sets that up end-to-end in seconds. Other examples might be “When I finish a Google Meet with a customer, record any issues reported in Linear”, or “Every morning at 9 am, text me a summary of my calendar events for the day”.<p>Here’s a video walkthrough: <a href="https://youtu.be/S4L3B21vXGY" rel="nofollow">https://youtu.be/S4L3B21vXGY</a>.<p>We initially set out to build a dev tool for API integration, and while building in the integration space, we realized existing workflow automation tools have a few key limitations. They still force users to do a lot of work like: Navigate through a sea of menus; Break down their workflow into discrete steps; Manually configure data transformations.<p>This led us to explore how we could make workflow automation way simpler by letting users describe what they want in plain English and having AI take care of the automation setup, replacing no-code GUIs or scripts.<p>Under the hood, DryMerge has two key components:<p>- A semantic layer that uses LLMs to interpret the user's request and map it to a series of pre-defined triggers and actions (we've built hundreds of these integrations).<p>- A data plane that orchestrates the actual execution, complete with smart field mapping, conditional logic, and human-in-the-loop checks.<p>When a user describes a workflow, our semantic layer generates multiple candidate plans, scores them, and selects the best based on prior successful/failed workflows. It extracts key entities and fields needed, and auto-generates a simple form for the user to fill in any missing details. Users can then iteratively describe, tweak, and test their workflow in the same chat.<p>The data plane then subscribes to the relevant event streams, executes the workflow steps, and handles gnarly aspects like pagination, retries, and rollbacks invisibly. We allow the semantic layer to delegate some values for runtime dependency injection from the data plane, to handle open-ended logic like classifying an email as urgent or summarizing a Google Meet transcript.<p>We integrate with 14 common services — we’d love for you to try it out and share what you think. Check it out at <a href="https://drymerge.com/app">https://drymerge.com/app</a>.
嗨,HN!我们;关于Edward和Sam,DryMerge(<a href=“https://x2F;/;DryMerge.com”>https://a>)的创始人,这是一种用简单英语实现工作流自动化的工具。例如,用户可以说“;当我收到一封来自潜在客户的电子邮件,将他们的详细信息添加到谷歌表单中,并向我发送一条文本“;,DryMerge在几秒钟内完成端到端的设置。其他例子可能是“当我完成与客户的谷歌会议时,记录Linear中报告的任何问题”,或者“每天早上9点,给我发一条当天日历事件的摘要”<p> 这是一个视频演练:<a href=“https://;/;youtu.be/!S4L3B21vXGY”rel=“nofollow”>https:///;youtu.be/;S4L3B21vXGY</a><p> 我们最初开始构建一个用于API集成的开发工具,在集成空间中构建时,我们意识到现有的工作流自动化工具有一些关键限制。它们仍然迫使用户做很多工作,比如:在菜单的海洋中导航;将他们的工作流程分解为离散的步骤;手动配置数据转换<p> 这让我们探索了如何让用户用通俗易懂的英语描述他们想要的东西,并让人工智能负责自动化设置,取代无代码的GUI或脚本,从而使工作流自动化变得更简单<p> 在引擎盖下,DryMerge有两个关键组件:<p>-一个使用LLM来解释用户的语义层;s的请求,并将其映射到一系列预定义的触发器和动作(我们已经构建了数百个这样的集成)<p> -一个协调实际执行的数据平面,包括智能字段映射、条件逻辑和人工循环检查<p> 当用户描述工作流程时,我们的语义层生成多个候选计划,对其进行评分,并根据先前的成功;失败的工作流。它提取所需的关键实体和字段,并自动生成一个简单的表单,供用户填写任何缺失的详细信息。然后,用户可以在同一聊天中反复描述、调整和测试他们的工作流程<p> 然后,数据平面订阅相关的事件流,执行工作流步骤,并在无形中处理棘手的方面,如分页、重试和回滚。我们允许语义层从数据平面为运行时依赖项注入委派一些值,以处理开放式逻辑,如将电子邮件分类为紧急邮件或汇总Google Meet记录<p> 我们集成了14个通用服务——我们希望您尝试一下并分享您的想法。请访问<a href=“https://;/;drymerg.com/!app”>https:///;drymerge.com/;应用</a>。
Url:
Post by: samuelbrashears
Comments:
camwest: I’m curious how this is different from Zapier which has added a conversational layer (<a href="https://zapier.com/ai" rel="nofollow">https://zapier.com/ai</a>).<p>In my experience a lot of people don’t know how to write with a level of specificity needed to map to pre defined triggers.<p>For example: instead of saying spreadsheet they may say “roadmap” or instead of saying “Notion database” they may say “bug tracker”<p>This stuff fails in Zapier.<p>Any chance you handle those cases better?
camwest: 我很好奇这与Zapier有什么不同,后者添加了一个对话层(<a href=“https://x2F;/;Zapier.com/x2F;ai”rel=“nofollow”>https://x2F!/!Zapier.com#x2F;ai</a>)<p> 根据我的经验,很多人不知道如何以一定程度的特异性来写作,以映射到预先定义的触发因素<p> 例如:与其说电子表格,他们可能会说“路线图”,或者与其说“Notion数据库”,他们可能说“bug tracker”<p>这些东西在Zapier中失败了<p> 你能更好地处理这些案件吗?
techietorontos: I love the UX and the concept. Will likely sign up as a customer.<p>FYI: In good faith, I asked some simple javascript questions and stuff like "who is michael jordan" and got answers from the LLM. Perhaps adding some additional guardrails to ensure queries are workflow based could save you some tokens.<p>Great work!
techietorontos: 我喜欢用户体验和概念。可能会以客户身份注册<p> 仅供参考:出于善意,我问了一些简单的javascript问题和类似于";谁是迈克尔·乔丹";并从LLM那里得到了答案。也许添加一些额外的护栏以确保查询基于工作流可以为您节省一些令牌<p> 干得好!
thoughtlede: Cool stuff.<p>1. For dynamic injection of arguments in your data plane, do you use LLMs?<p>2. What did you find you cannot do yet because of LLM limitations (and not because of lack of third-party integrations)?<p>3. I haven’t looked closely into your product, but is every “effect” of a workflow something that only the requesting user can see? Is this how you ensure bad or wrong things are not hurting other people or systems that are outside of user’s control?
thoughtlede: 很酷的东西<p> 1。对于在数据平面中动态注入参数,是否使用LLM<p> 2。您发现由于LLM的限制(而不是因为缺乏第三方集成),您还不能做什么<p> 3。我没有仔细研究过您的产品,但工作流的每一个“效果”都是只有提出请求的用户才能看到的吗?这就是你确保糟糕或错误的事情不会伤害用户无法控制的其他人或系统的方式吗?
Octopuz: Looks cool. Which 14 services does the free account support?
In the video I see SMS, Slack, Notion, Gmail, Google Sheets/Meet/Docs/Calendar/Drive, Salesforce, Hubspot, GitHub. I think Salesforce and Hubspot are in the $25/month subscription?<p>I would appreciate 'whenever I post on X or Mastodon add this to a sheet and put text and URL in its own column'Octopuz: 看起来很酷。免费帐户支持哪14项服务?在视频中,我看到了SMS、Slack、Notion、Gmail、Google Sheets/;会面/;文档/;日历/;Drive、Salesforce、Hubspot、GitHub。我认为Salesforce和Hubspot在25美元;月订阅<p> 我将不胜感激;每当我在X或Mastodon上发帖时,将其添加到表单中,并将文本和URL放在其自己的列中;
nicknow: Really great concept and execution seems to be pretty good. I'm a likely paying customer except that you don't support Microsoft 365. So I can use it for all my personal stuff which is GMail but none of my businesses which all run their email through Microsoft 365.
nicknow: 非常好的概念和执行似乎都很好。I-;我很可能是付费客户,除非你;不支持Microsoft 365。所以我可以把它用于我所有的个人信息,即GMail,但我的企业都不能通过Microsoft 365运行电子邮件。