返回列表
AI 产品发布 · 智能体基础设施

AGI 已至——Airtable 发布 Hyperagent 智能体平台

Airtable 推出 Hyperagent——一个为 AI 智能体提供完整计算环境(浏览器、shell、文件系统)+ 技能学习 + 一键部署到 Slack 的企业级智能体平台,定位"AGI 时代的操作系统"。
打开原文 ↗

2026-02-20 原文链接 ↗
阅读简报
双语对照
完整翻译
原文
讨论归档

核心观点

1. 完整计算环境是智能体的下一个标配:Hyperagent 给每个会话配备持久化文件系统、真实浏览器、代码执行、多模态生成能力,让智能体能创造性地串联工具链,而非走固定流程。 2. 技能学习 = 领域知识复利:用一次会话教会智能体某个领域方法论(如VC 评估框架),之后全组织复用,且每次运行自动改进——这是从"通用 AI"到"你的AI"的关键跳跃。 3. 一键部署到 Slack,智能体变同事:不是被动等 @mention 的 bot,而是跟随对话、理解上下文、主动行动的"智能同事",降低了组织内AI 落地的最后一公里摩擦。 4. 指挥中心做舰队管理:评估量表、成本追踪、A/B 测试模型配置——把智能体运营从"手工调试"拉到"系统化管理"层面。 5. 直接对标OpenClaw:文章明确说"把它想成 OpenClaw,但云端化且安全",说明这个赛道正在从开发者工具走向企业 SaaS。

跟我们的关联

  • 智能体架构参考:Hyperagent 的"完整计算环境 + 技能学习 + 部署到IM"模式,跟 Neta 未来可能做的 AI 社交助手方向高度相关——用户教会 AI 自己的社交偏好/风格,然后 AI 在聊天场景中主动辅助。
  • 技能复利思路可借鉴:Neta 的 AI 如果能"学会"用户的表达习惯、社交圈特征,每次交互都更懂用户,这就是社交产品版的"技能学习"。
  • 海外竞品动态:Airtable 从表格工具转型智能体平台,说明 AI-native 产品正在重塑企业工具格局,Neta 做海外增长时需要关注这类平台级玩家是否会切入社交场景。

讨论引子

1. Hyperagent 的"技能学习"本质是把组织知识编码进智能体——如果Neta 的 AI 能"学会"每个用户的社交风格和偏好,产品形态会怎么变? 2. "一键部署到 Slack"让智能体成为团队同事——Neta 有没有可能让用户"一键部署"一个 AI 分身到群聊里,代替自己社交? 3. 智能体平台都在抢"AGI 时代的操作系统"定位,社交产品在这个格局里是基础设施、应用层、还是数据层?

过去几个月,作为一名构建者,我每周亲自烧掉数十亿个 token。今天,我很兴奋地宣布 Airtable 推出的 Hyperagent。

Hyperagent 为智能体提供完整的计算环境——真实的浏览器、shell、文件系统——并配备强大工具,如图像与视频生成、地图、数据仓库访问,以及数百个企业级集成。把它想成 OpenClaw,但从一开始就安全且云端化——技能学习会随时间复利增长,一键部署到 Slack,还有一个指挥中心,用来规模化管理你整支智能体舰队。

具备完整计算环境与强大工具的最先进智能体

Hyperagent 的设计旨在充分释放最强前沿模型的能力;每次 Hyperagent 会话都会获得一个完整计算环境:持久化文件系统、真实浏览器、代码执行、图像/视频/音频生成、数据仓库集成 + 数百个其他连接器,以及把任何新 API 学成技能的能力。以室内设计为例,Hyperagent 可以上网浏览寻找房源照片,抓取外立面的 Google Street View 影像,然后将这些真实照片作为种子,用 Nano Banana Pro 生成重新构想的房间,并用 Veo 3 生成看房漫游视频——再把这一切汇总成一个带自定义 URL、可直接交付客户的提案网站。没有脆弱的固定流程——它会创造性地把工具拼接起来,让每一步的输出成为下一步的输入。

用技能学习解锁领域专长

花一个会话教会智能体你们风投机构如何评估初创公司——拐点信号、创始人特质、以及你如何判断技术护城河是会复利增长还是会被商品化。之后任何合伙人只要说“梳理一下对这家公司的看法”,得到的就是你们机构的投资主张,而不是一套通用模板。技能可以是 API 集成、领域方法论或运营框架——并且每次运行都会变得更好。

一键部署,成为全组织的智能同事

任何工作流程都可以打包成一个可复用的智能体——自定义提示词、明确的工具、附加的技能、模型选择以及调用设置。然后一键把你的智能体部署到 Slack。它们不是那种等着被 @mentioned 的机器人——它们会跟随对话、理解上下文,并在相关时机采取行动。

现在任何同事只要说“这套房刚刚上市”,每一次都能获得同样高质量的输出,并且遵循最佳实践步骤。

指挥中心:统筹、优化并持续改进你的整支舰队

全组织部署的每个智能体,都集中在一处。用评估量表定义一次成功运行应当是什么样。跟踪长期表现。成本追踪。自动建议改进。对配置做 A/B 测试——通过更换模型来优化成本或质量。

这是一套拥有完成真实工作所需工具箱、并且每次运行都会进步的智能体系统。AGI 时代的操作系统。

我们正在为早期用户开通使用——hyperagent.com。关于我们为什么打造它的完整故事:https://howietl.substack.com/p/agi-is-here-now-harness-it

链接:http://x.com/i/article/2024601345890930688

I've been personally burning through billions of tokens a week for the past few months as a builder. Today, I'm excited to announce Hyperagent, by Airtable.

Hyperagent gives agents a full computing environment — real browser, shell, filesystem — along with powerful tools like image and video generation, mapping, data warehouse access, and hundreds of enterprise integrations. Think OpenClaw, but secure and cloud-based from the get-go — with skill learning that compounds over time, one-click deployment into Slack, and a command center to manage your entire fleet of agents at scale.

State-of-the-art agents with a full computing environment and powerful tools

Built to fully leverage the best frontier models, every Hyperagent session gets a full computing environment with persistent filesystem, a real browser, code execution, image/video/audio generation, data warehouse integrations + hundreds of other connectors, and the ability to learn any new API as a skill. For an interior design use case, Hyperagent can browse the web to find listing photos, pull Google Street View imagery of the exterior, then uses those actual photos as seeds to generate reimagined rooms with Nano Banana Pro and walkthrough videos with Veo 3 — and compile it all into a client-ready proposal website with a custom URL. No brittle sequence — it pieces together tools creatively, each output becoming the input to the next.

Unlock domain expertise with skill learning

Spend a session teaching the agent how your VC firm evaluates startups — the inflection signals, the founder qualities, how you assess whether a technical moat compounds or gets commoditized. Now any partner says "pull together a view on this company" and gets your firm's thesis, not a generic template. Skills can be API integrations, domain methodologies, or operational frameworks — and they improve with every run.

One click to deploy as intelligent coworkers for your entire org

Any workflow can be packaged into a reusable agent — custom prompt, defined tools, attached skills, model selection, and invocation settings. Then deploy your agents into Slack with one click. These aren't bots that wait to be @mentioned — they follow conversations, understand context, and act when relevant.

Now any teammate can say "this house just hit the market" and get the same high-quality output, following the best-practice steps, every time.

A command center to oversee, optimize, and continuously improve your entire fleet

Every agent deployed across the org, in one place. Eval rubrics that define what a successful run looks like. Performance over time. Cost tracking. Auto-suggested improvements. A/B test configurations — swap models to optimize for cost or quality.

This is a system of agents that have the toolkit to do real work and get better with every run. The operating system for the age of AGI.

We're onboarding early users now — hyperagent.com. The full story on why we built it: https://howietl.substack.com/p/agi-is-here-now-harness-it

Link: http://x.com/i/article/2024601345890930688

过去几个月,作为一名构建者,我每周亲自烧掉数十亿个 token。今天,我很兴奋地宣布 Airtable 推出的 Hyperagent。

Hyperagent 为智能体提供完整的计算环境——真实的浏览器、shell、文件系统——并配备强大工具,如图像与视频生成、地图、数据仓库访问,以及数百个企业级集成。把它想成 OpenClaw,但从一开始就安全且云端化——技能学习会随时间复利增长,一键部署到 Slack,还有一个指挥中心,用来规模化管理你整支智能体舰队。

具备完整计算环境与强大工具的最先进智能体

Hyperagent 的设计旨在充分释放最强前沿模型的能力;每次 Hyperagent 会话都会获得一个完整计算环境:持久化文件系统、真实浏览器、代码执行、图像/视频/音频生成、数据仓库集成 + 数百个其他连接器,以及把任何新 API 学成技能的能力。以室内设计为例,Hyperagent 可以上网浏览寻找房源照片,抓取外立面的 Google Street View 影像,然后将这些真实照片作为种子,用 Nano Banana Pro 生成重新构想的房间,并用 Veo 3 生成看房漫游视频——再把这一切汇总成一个带自定义 URL、可直接交付客户的提案网站。没有脆弱的固定流程——它会创造性地把工具拼接起来,让每一步的输出成为下一步的输入。

用技能学习解锁领域专长

花一个会话教会智能体你们风投机构如何评估初创公司——拐点信号、创始人特质、以及你如何判断技术护城河是会复利增长还是会被商品化。之后任何合伙人只要说“梳理一下对这家公司的看法”,得到的就是你们机构的投资主张,而不是一套通用模板。技能可以是 API 集成、领域方法论或运营框架——并且每次运行都会变得更好。

一键部署,成为全组织的智能同事

任何工作流程都可以打包成一个可复用的智能体——自定义提示词、明确的工具、附加的技能、模型选择以及调用设置。然后一键把你的智能体部署到 Slack。它们不是那种等着被 @mentioned 的机器人——它们会跟随对话、理解上下文,并在相关时机采取行动。

现在任何同事只要说“这套房刚刚上市”,每一次都能获得同样高质量的输出,并且遵循最佳实践步骤。

指挥中心:统筹、优化并持续改进你的整支舰队

全组织部署的每个智能体,都集中在一处。用评估量表定义一次成功运行应当是什么样。跟踪长期表现。成本追踪。自动建议改进。对配置做 A/B 测试——通过更换模型来优化成本或质量。

这是一套拥有完成真实工作所需工具箱、并且每次运行都会进步的智能体系统。AGI 时代的操作系统。

我们正在为早期用户开通使用——hyperagent.com。关于我们为什么打造它的完整故事:https://howietl.substack.com/p/agi-is-here-now-harness-it

链接:http://x.com/i/article/2024601345890930688

相关笔记

I've been personally burning through billions of tokens a week for the past few months as a builder. Today, I'm excited to announce Hyperagent, by Airtable.

Hyperagent gives agents a full computing environment — real browser, shell, filesystem — along with powerful tools like image and video generation, mapping, data warehouse access, and hundreds of enterprise integrations. Think OpenClaw, but secure and cloud-based from the get-go — with skill learning that compounds over time, one-click deployment into Slack, and a command center to manage your entire fleet of agents at scale.

State-of-the-art agents with a full computing environment and powerful tools

Built to fully leverage the best frontier models, every Hyperagent session gets a full computing environment with persistent filesystem, a real browser, code execution, image/video/audio generation, data warehouse integrations + hundreds of other connectors, and the ability to learn any new API as a skill. For an interior design use case, Hyperagent can browse the web to find listing photos, pull Google Street View imagery of the exterior, then uses those actual photos as seeds to generate reimagined rooms with Nano Banana Pro and walkthrough videos with Veo 3 — and compile it all into a client-ready proposal website with a custom URL. No brittle sequence — it pieces together tools creatively, each output becoming the input to the next.

Unlock domain expertise with skill learning

Spend a session teaching the agent how your VC firm evaluates startups — the inflection signals, the founder qualities, how you assess whether a technical moat compounds or gets commoditized. Now any partner says "pull together a view on this company" and gets your firm's thesis, not a generic template. Skills can be API integrations, domain methodologies, or operational frameworks — and they improve with every run.

One click to deploy as intelligent coworkers for your entire org

Any workflow can be packaged into a reusable agent — custom prompt, defined tools, attached skills, model selection, and invocation settings. Then deploy your agents into Slack with one click. These aren't bots that wait to be @mentioned — they follow conversations, understand context, and act when relevant.

Now any teammate can say "this house just hit the market" and get the same high-quality output, following the best-practice steps, every time.

A command center to oversee, optimize, and continuously improve your entire fleet

Every agent deployed across the org, in one place. Eval rubrics that define what a successful run looks like. Performance over time. Cost tracking. Auto-suggested improvements. A/B test configurations — swap models to optimize for cost or quality.

This is a system of agents that have the toolkit to do real work and get better with every run. The operating system for the age of AGI.

We're onboarding early users now — hyperagent.com. The full story on why we built it: https://howietl.substack.com/p/agi-is-here-now-harness-it

Link: http://x.com/i/article/2024601345890930688

📋 讨论归档

讨论进行中…