Launch HN: Vela (YC W26) – Vela：用于复杂排程的 AI
5 分•作者: Gobhanu•6 个月前
大家好，我是 Gobhanu 和 Saatvik（兄弟），我们正在构建 Vela (<a href="https://tryvela.ai">https://tryvela.ai</a>) - 一种 AI 智能体，可以处理多方、多渠道的日程安排。<p>日程安排是一个伪装成电子邮件的约束满足问题！当只有两个人、一个时区、一个渠道时，这很容易。但当输入来自多个通信渠道的非结构化自然语言，约束条件在中途发生变化，并且目标函数包括正式场合不存在的社交动态时，它就变成了一个约束满足问题。<p>如果日程安排自动完成会怎样？例如：招聘人员发送一条消息，然后针对五位候选人、三位招聘经理和两个时区的所有面试都会自动预订、确认和更新。没有链接，没有来回沟通，没有人花费数小时处理 20 封电子邮件。每个人都可以在正确的时间，通过他们实际使用的任何渠道收到正确的邀请。这就是我们构建 Vela 的目的。<p>您可以将 Vela 引入您的电子邮件、短信、WhatsApp、Slack、电话或集成到 ATS 等系统中，它将接管：读取上下文、检查日历、建议时间、在人们不回复时进行跟进，并在情况发生变化时重新预订。<p>我们的第一批客户之一是一家招聘公司，他们花了将近八年的时间寻找日程安排解决方案。他们的协调员管理着数百次候选人与客户的面试，每一方都需要单独的电子邮件线程、单独的 Zoom 帐户以避免重复预订链接，以及连接从未直接沟通的各方的日历邀请。客户重新安排一次面试，就会级联到其他四次。候选人通过短信回复了电子邮件开始的线程。Vela 在短短 10 分钟的入职培训中就解决了这个问题。<p>最困难的部分是数据问题。不同人群的日程安排行为差异很大。高管人员会在几小时内回复电子邮件，并期望正式的 3 选项提案。申请物流职位的卡车司机会在奇怪的时间通过共享设备回复短信，内容是“y tm wrks”。失败模式不是解析——而是对错误的细分市场应用错误的交互模式，并眼睁睁地看着对话中断。我们一直在从数千次真实交互中构建行为数据集：按角色划分的响应延迟、按人口统计划分的渠道偏好、跟进时间曲线、在您陷入决策瘫痪之前要提出多少个选项。这些数据在任何地方都不存在。<p>核心智能体挑战是跨渠道的状态。当有人通过短信回复了电子邮件开始的线程时，Vela 需要统一身份、合并上下文，并在不丢失信息的情况下继续进行。电话号码无法清晰地映射到电子邮件，人们在短信中使用昵称，共享设备意味着回复者可能不是您联系的人。时间 NLU 本身就是一个问题——“下周五”在周一和周四的含义不同。我们从自然语言中提取结构化约束，并根据日历状态进行解析。当无法解决歧义时，Vela 会提问——但决定何时提问与推断取决于出错的风险。<p>我们已经与付费的企业客户合作，并且每个客户仍然会发现让我们感到惊讶的边缘情况。案例研究请访问我们的网站 (<a href="https://tryvela.ai/case-studies/">https://tryvela.ai/case-studies/</a>)。您可以在这里查看演示：<a href="https://www.youtube.com/watch?v=MzUOjSG5Uvw" rel="nofollow">https://www.youtube.com/watch?v=MzUOjSG5Uvw</a>。<p>我们欢迎任何从事多智能体协调、跨渠道对话式 AI 或在混乱的现实世界领域进行约束满足工作的人提供反馈。期待您的评论！
查看原文
Hi HN! We're Gobhanu and Saatvik (brothers), building Vela (<a href="https://tryvela.ai">https://tryvela.ai</a>) - AI agents that handle multi-party, multi-channel scheduling.<p>Scheduling is a constraint satisfaction problem disguised as email! It’s easy when it’s two people, one timezone, one channel. But it becomes a constraint satisfaction problem when inputs are unstructured natural language across multiple communication channels, constraints change mid-solve, and the objective function includes social dynamics that don't exist formally anywhere.<p>What if scheduling just happened? For example: a recruiter sends one message, and every interview across five candidates, three hiring managers, and two time zones gets booked, confirmed, and updated automatically. No links, no back-and-forth, no one spending hours with 20 emails. Everyone just gets the right invite at the right time, on whatever channel they actually use. That's what we built Vela to do.<p>You loop in Vela into your emails, SMS, WhatsApp, Slack, phone or integrate into an ATS etc and it takes over: reads context, checks calendars, proposes times, follows up when people ghost, and rebooks when things shift.<p>One of our first customers is a staffing firm that searched for a scheduling solution for almost eight years. Their coordinators manage hundreds of candidate-client interviews where each side needs separate email threads, separate Zoom accounts to avoid double-booking links, and calendar invites connecting parties who never directly communicate. A client reschedules one interview and it cascades into four others. A candidate responds on SMS to a thread that started on email. Vela solved this in just 10 minutes of onboarding.<p>The hardest part has been the data problem. Scheduling behavior varies enormously across populations. C-suite folks respond to email within hours and expect formal 3-option proposals. Truck drivers applying for logistics roles respond to SMS at odd hours from shared devices with "y tm wrks." The failure mode isn't parsing -- it's applying the wrong interaction pattern for the wrong segment and watching the conversation die. We've been building behavioral datasets from thousands of real interactions: response latency by role, channel preference by demographic, follow-up timing curves, how many options to propose before you hit decision paralysis. This data doesn't exist anywhere.<p>The core agent challenge is state across channels. When someone responds on SMS to a thread that started in email, Vela needs to unify identity, merge context, and continue without losing information. Phone numbers don't map cleanly to emails, people use nicknames on text, shared devices mean the responder might not be who you reached out to. Temporal NLU is its own problem -- "next Friday" means different things on Monday versus Thursday. We extract structured constraints from natural language and resolve against calendar state. When ambiguity can't be resolved, Vela asks -- but deciding when to ask versus infer depends on the stakes of getting it wrong.<p>We're live with paying enterprise customers and every client still surfaces edge cases that surprise us. Case studies on our site (<a href="https://tryvela.ai/case-studies/">https://tryvela.ai/case-studies/</a>). You can check out a demo here: <a href="https://www.youtube.com/watch?v=MzUOjSG5Uvw" rel="nofollow">https://www.youtube.com/watch?v=MzUOjSG5Uvw</a>.<p>We'd love feedback from anyone who's worked on multi-agent coordination, conversational AI across channels, or constraint satisfaction in messy real-world domains. Looking forward to your comments!