AI-Powered Categorization Launched by Superhuman to Combat Inbox Spam
It's been over two years since ChatGPT made a splash, and it seems like every email app jumped on the AI bandwagon, adding features like AI-powered writing, summaries, and search to help you navigate your inbox faster. Now, Superhuman is tackling one of the biggest headaches in email management: categorization.
Remember Google's Inbox? It tried to sort emails into categories but got the axe in 2019. Since then, other email clients, including Gmail, have taken a crack at it, but the results have been hit or miss.
Enter Superhuman's new Auto Label feature. It automatically slaps labels like marketing, pitch, social, and news on your emails. And if those don't cut it, you can create your own custom labels with a prompt. Superhuman's all about speed, so you can even auto-archive emails under certain labels if you don't need to see them.
Rahul Vohra, Superhuman's CEO, told TechCrunch that their customers were drowning in cold marketing and spam emails. "Why isn't Superhuman filtering these out?" they asked. Initially, Superhuman relied on Gmail and Outlook's spam filters, but that wasn't cutting it. So, they decided to take control with their own classification system.
One hiccup with the auto labels at launch is that you can't tweak the prompts for creating categories. If a prompt isn't working and missing emails you thought would be categorized, you'll have to come up with a new one.
The app also lets you set up a Split Inbox based on your filters, like emails with specific subjects or from certain domains. Now, you can also use your custom labels to create a new Split Inbox.
Superhuman's also sprucing up its reminder feature. You could already snooze emails, but now, if you reply to an email expecting a response, it'll pop back up after a set time if you don't hear back. You can tweak this in the settings. Plus, there's an AI-powered auto-draft feature that crafts a follow-up in your style, keeping the conversation's context and your tone in mind. It's like a polite nudge to the recipient.

Image Credits:Superhuman Vohra shared with TechCrunch that Superhuman's next move is to tap into different knowledge bases that represent you, like your website and personal wiki. They already peek at your schedule through your calendar.
With all this info, Superhuman's AI could soon auto-draft replies to emails that need a response and even send some automatically if you're okay with it. For instance, it might reply to a meeting request with a suggested time slot.
Superhuman's also eyeing IFTTT-style (IF This Then That) workflows with prompts. Say you get a recruiting email; you could set up an AI-generated reply template and forward it to the recruiting department if it meets certain criteria.

Image Credits:Superhuman While an email client automatically replying to emails might be a ways off, sorting emails into categories is a pain point that could be solved right now. And the new label feature sounds promising—as long as it gets the categorization right.
Related article
Anthropic's experimental AI Claude completes negotiations and transactions in e-commerce test
As artificial intelligence advances rapidly, Anthropic quietly rolled out an internal experiment called "Project Deal" last Friday, showcasing AI's potential in e-commerce. The experiment had its AI model Claude autonomously handle buying, selling, a
DeepSeek Code poised for launch
As AI technology accelerates, DeepSeek is at a thrilling juncture. The AI company recently revealed it has secured over 70 billion yuan in funding. Leadership has emphasized a commitment to groundbreaking AI research over immediate commercial gains.
Musk’s Grok: 1.5 Trillion Parameters and Cursor Code Absorption—Game Changer or Bluff?
Elon Musk is finally making a move.In the AI programming race, OpenAI and Anthropic are accelerating, while xAI appears to be lagging. Musk has often stated his aim to rival Claude, yet despite multiple updates to the Grok4.X series, the results look
Related Special Topic Recommendations
Comments (53)
0/500
수퍼휴먼의 'AI 분류' 기능이 출시되었군요! 이메일 폴더 정리 지옥에서 벗어날 수 있을 것 같아요 ㅠㅜ 저처럼 하루 수백 통의 이메일에 시달리는 사람에게 참고 싶은 기능인데, AI가 카테고리를 얼마나 정확하게 나눌 수 있을지 궁금하네요. 혹시 시장의 다른 이메일 앱들보다 앞서나가는 전략일까요? 경쟁이 점점 치열해지는 것 같아요 🤔
Superhuman's AI categorization sounds like a game-changer! My inbox is a warzone of spam and promos, so auto-labeling could really save my sanity. Excited to try this out and see if it actually sorts my mess as promised. 🤞
C'est incroyable comment Superhuman utilise l'IA pour nettoyer nos boîtes mail ! 😊 Fini le spam qui nous noie, avec leurs étiquettes auto, on dirait un assistant personnel qui trie tout. Mais bon, est-ce que ça va vraiment comprendre mes priorités bizarres ?
スーパーヒューマンのAIカテゴリ分け、最高です!スパムメールをしっかり分類してくれるので、受信箱がすっきり。ただ、重要なメールまでスパム扱いすることがあるので、注意が必要です。でも、時間の節約には大いに役立ちます!😊
La categorización por IA de Superhuman es un salvavidas para mi bandeja de entrada. ¡Clasifica el spam tan bien que casi no veo correo basura ahora! Solo desearía que también capturara esos correos de phishing astutos. En general, ha hecho que mi vida de correo electrónico sea mucho más fácil. 😊
It's been over two years since ChatGPT made a splash, and it seems like every email app jumped on the AI bandwagon, adding features like AI-powered writing, summaries, and search to help you navigate your inbox faster. Now, Superhuman is tackling one of the biggest headaches in email management: categorization.
Remember Google's Inbox? It tried to sort emails into categories but got the axe in 2019. Since then, other email clients, including Gmail, have taken a crack at it, but the results have been hit or miss.
Enter Superhuman's new Auto Label feature. It automatically slaps labels like marketing, pitch, social, and news on your emails. And if those don't cut it, you can create your own custom labels with a prompt. Superhuman's all about speed, so you can even auto-archive emails under certain labels if you don't need to see them.
Rahul Vohra, Superhuman's CEO, told TechCrunch that their customers were drowning in cold marketing and spam emails. "Why isn't Superhuman filtering these out?" they asked. Initially, Superhuman relied on Gmail and Outlook's spam filters, but that wasn't cutting it. So, they decided to take control with their own classification system.
One hiccup with the auto labels at launch is that you can't tweak the prompts for creating categories. If a prompt isn't working and missing emails you thought would be categorized, you'll have to come up with a new one.
The app also lets you set up a Split Inbox based on your filters, like emails with specific subjects or from certain domains. Now, you can also use your custom labels to create a new Split Inbox.
Superhuman's also sprucing up its reminder feature. You could already snooze emails, but now, if you reply to an email expecting a response, it'll pop back up after a set time if you don't hear back. You can tweak this in the settings. Plus, there's an AI-powered auto-draft feature that crafts a follow-up in your style, keeping the conversation's context and your tone in mind. It's like a polite nudge to the recipient.

With all this info, Superhuman's AI could soon auto-draft replies to emails that need a response and even send some automatically if you're okay with it. For instance, it might reply to a meeting request with a suggested time slot.
Superhuman's also eyeing IFTTT-style (IF This Then That) workflows with prompts. Say you get a recruiting email; you could set up an AI-generated reply template and forward it to the recruiting department if it meets certain criteria.

Anthropic's experimental AI Claude completes negotiations and transactions in e-commerce test
As artificial intelligence advances rapidly, Anthropic quietly rolled out an internal experiment called "Project Deal" last Friday, showcasing AI's potential in e-commerce. The experiment had its AI model Claude autonomously handle buying, selling, a
DeepSeek Code poised for launch
As AI technology accelerates, DeepSeek is at a thrilling juncture. The AI company recently revealed it has secured over 70 billion yuan in funding. Leadership has emphasized a commitment to groundbreaking AI research over immediate commercial gains.
Musk’s Grok: 1.5 Trillion Parameters and Cursor Code Absorption—Game Changer or Bluff?
Elon Musk is finally making a move.In the AI programming race, OpenAI and Anthropic are accelerating, while xAI appears to be lagging. Musk has often stated his aim to rival Claude, yet despite multiple updates to the Grok4.X series, the results look
수퍼휴먼의 'AI 분류' 기능이 출시되었군요! 이메일 폴더 정리 지옥에서 벗어날 수 있을 것 같아요 ㅠㅜ 저처럼 하루 수백 통의 이메일에 시달리는 사람에게 참고 싶은 기능인데, AI가 카테고리를 얼마나 정확하게 나눌 수 있을지 궁금하네요. 혹시 시장의 다른 이메일 앱들보다 앞서나가는 전략일까요? 경쟁이 점점 치열해지는 것 같아요 🤔
Superhuman's AI categorization sounds like a game-changer! My inbox is a warzone of spam and promos, so auto-labeling could really save my sanity. Excited to try this out and see if it actually sorts my mess as promised. 🤞
C'est incroyable comment Superhuman utilise l'IA pour nettoyer nos boîtes mail ! 😊 Fini le spam qui nous noie, avec leurs étiquettes auto, on dirait un assistant personnel qui trie tout. Mais bon, est-ce que ça va vraiment comprendre mes priorités bizarres ?
スーパーヒューマンのAIカテゴリ分け、最高です!スパムメールをしっかり分類してくれるので、受信箱がすっきり。ただ、重要なメールまでスパム扱いすることがあるので、注意が必要です。でも、時間の節約には大いに役立ちます!😊
La categorización por IA de Superhuman es un salvavidas para mi bandeja de entrada. ¡Clasifica el spam tan bien que casi no veo correo basura ahora! Solo desearía que también capturara esos correos de phishing astutos. En general, ha hecho que mi vida de correo electrónico sea mucho más fácil. 😊





Home






