01 / THE SIGNAL

我们发现了什么

Small teams can run far more work in parallel than ever before thanks to AI, but someone now has to connect all that context manually. If you’re a 2 to 10 person team where one person is spe

  • 来源:Hacker News发现于 2026-08-21
  • 证据等级:D · 发现产品或需求信号,暂未获得可核验的商业证据。
  • 商业模式:待核验
  • 主题:独立产品
  • 初筛评分:19/100 · 收录 1
#独立开发#待验证#产品发现
02 / SOURCE & EVIDENCE

证据,比故事更重要。

发现产品或需求信号,暂未获得可核验的商业证据。

规则清洗与初筛,未经人工商业核验。原文语境、实际客户和付费情况仍需自行验证。

引用与数字披露

来源类型(原作者自述/第三方测算/媒体转引)需采集端标注,本版尚未落字段。

短句引用
作者
未标注
抓取日期
来源类型
未标注
数字口径
币种
未标注
口径
未标注
披露主体
未标注
披露日期
未标注

中文辅助译文(全文)

嗨,HN!一家初创公司的日常工作流程是什么样的?大概是这样:> 一位创始人与客户沟通 > 另一位创始人负责开发 > 客户提出需求。第一位创始人向第二位解释需求,第二位创始人再向 Claude 解释 > 两周后,任何一位创始人都会问以下问题之一:\ 我们为什么要这样做?\ 这里发生了什么?\ 我们答应过 ACME 要做什么?\ X 这件事进展如何?> 然后你在内心尖叫,因为你必须弄清楚到底发生了什么…… 在智能体出现之前,负责某一部分工作的人通常会在脑中保留一张心智地图,他们可以将这些上下文分享给他人。但现在越来越做不到了。借助 AI,小团队可以并行运行比以往多得多的工作,但现在必须有人手动把所有这些上下文串联起来。一个产品变更背后的推理过程,如今可能分散在一次客户通话、两封邮件、一个 Slack 线程和四段 Claude 对话中。Praxos 是一款团队消息应用。它像你预期的那样提供频道、群组和话题线程。然而,工作发生的地方——Github、harness、邮件、通话——会被关联起来并转化为一份持续更新的公司记录。这意味着每个人都能随时了解最新的进展。智能体可以加入对话,并继承与人类相同的上下文。以下是我们已在生产环境中看到的示例:你与一位客户沟通。之后,当工程师或编码智能体开始处理这个功能时,你的对话和该客户的信息已经处于上下文中。一位新工程师接手一个现有项目,他可以立即获取谁负责代码库哪一部分、各次变更之间的差异,以及他们与编码智能体对话的详细视图。无需再向 CTO 反复盘问。三周后,有人询问工程师为何针对该功能做出了某个决策。

Praxos 会调取这位工程师的对话记录、最初的功能请求以及创始人与工程师之间的通话记录,然后梳理出该工作的上下文。我们仍处于早期阶段,但核心产品已经可用并正在被使用。你可以获得消息、搜索、记忆和连接器。你可以接入你自己的智能体,使用我们提供的,或者两者兼用。桌面应用将于下周上线。我们正在开发原生通话功能和移动应用,以便公司历史中的所有通信都能在 Praxos 上完成。如果你们是一个 2 到 10 人的团队,其中一人全天与客户打交道,而团队其他成员则在用 Claude/Codex 进行交付,我们非常愿意亲自为你们进行 onboarding。尤其是如果你们上周已经下意识地问过“客户到底想要什么?”或“X 进展得怎么样了?”的话。首批注册的 10 个团队可免费使用 Praxos 6 个月。发邮件至 lucas@praxos.ai 即可开始!

译文由上游机器翻译生成,可能有误;判断请以英文原文为准。

英文原文(来源本站未改写)

Hey HN!What does a regular workflow at a startup look like?Probably like this: > One founder talks to customers > Another founder builds > A customer asks for something.The first founder explains it to the second.The second founder explains it to Claude > Two weeks any one of the founders asks one of the following questions: \ Why are we building it this way?\ What happened here?\ What did we promise ACME we’d do?\ How far along are we on X?> Then you scream on the inside because you have to figure out what happened...Before agents, the person who did one part of the work usually held a mental map.They could share the context with other people.Increasingly, they can’t.

Small teams can run far more work in parallel than ever before thanks to AI, but someone now has to connect all that context manually.The reasoning behind one product change might now be scattered across a customer call, two emails, a Slack thread, and four Claude conversations.Praxos is a team messaging app.It has channels, groups and threads like you’d expect.However, places where work happens—Github, harnesses, email, calls—get linked and converted into a living record of your company.This means everyone is always up to date with the latest developments.Agents can join conversations and inherit the same context humans do.Here are examples we’ve seen in production: You talk to a customer.

Later, when an engineer or coding agent works on the feature, your conversation and the customer’s information are already in context.A new engineer picks up an existing project.They have immediate access to info about who worked on what part of the code base, the deltas across changes, and a granular view of their conversations with coding agents.There’s no need to interrogate the CTO.Three weeks later, someone asks why the engineer made a certain decision about the feature.Praxos fetches the engineer’s convos, the original feature request and call logs between the founder and the engineer.Then it contextualizes the work.We’re early, but the core product already works and is in use.

You get messaging, search, memory and connectors.You can bring your own agents, use ours, or both.A desktop app is going live next week.We’re building native calls and mobile apps, so that all the communications that go into a company’s history can happen on Praxos.If you’re a 2 to 10 person team where one person is spending all day with customers while the rest of the team is shipping with Claude/Codex, we’d love to personally onboard you.Especially if you’ve already caught yourself asking “what did the customer want?” or “what’s going on with X?” last week.The first 10 teams to sign up get Praxos for free for 6 months.Email lucas@praxos.ai to get started!

出处https://praxos.ai抓取日期 · 采集源 Hacker News

03 / EVIDENCE GAPS

这条还缺什么证据?

下面每条都由本条已有字段推出(等级、理由、商业模式、来源次数、是否演示), 本站不生成推测性结论;通用验证方法放在方法论页。

  • 可核验的收入或付费证据查官网定价页与付费口径;第三方数据源(如 GetLatka)只作旁证,需标注来源与时点。
  • 商业模式未定确认按席位/按用量/授权还是开源托管版收费;开源项目另查 LICENSE 与是否存在付费版。
  • 只有单一来源找一手站点或其他渠道是否重复出现同一产品;社区热帖数量不等于商业进展。

通用验证清单(谁有这个问题/谁愿意付费/一个人能交付哪一小步)见我们的筛选方法

04 / SIGNAL HISTORY

发现时间线