Upstream - The inbox designed for humans and agents

Finally, an inbox you'll look forward to. Agents sort your messages, draft your replies, and clear the grunt work behind the scenes, all in a client so well-crafted that email feels light, fast, fun.

Add a comment

Replies

Best

Been using Upstream for a few months now and I can’t imagine going back to Gmail. The UX is so much better, and the inbox splits have made managing my emails so much easier

 So glad you're enjoying Upstream 😄 we appreciate your support

thanks, I'm glad you love the UX :)

 so glad you’re enjoying it!

 inbox splits are indeed a game changer for inbox productivity! i'm glad you're enjoying it :)

 Love hearing this. The inbox splits are exactly meant to make email feel less like one giant pile. Thanks for using Upstream for so long.

Congrats to the entire team for the launch! It looks really cool. 👏

 We really appreciate your support! 🙏

thanks for your support Manou ❤️

 thanks Manou! We all appreciate it 😄

 Thank you so much! I hope you'll like as much as we do 😇

 thanks, appreciate it!

The right test for this category is not whether the draft sounds polished; it's whether the system makes handoff and review legible. For a small shop, knowing what the agent touched and what still needs a human is the difference between leverage and another inbox to supervise.

 The agents work for you and nothing gets sent without your approval. Every conversation with an AI drafted reply is clearly marked.

What are the biggest challenges that you are facing with message handoff/review?

Yes 100% ! It's one of the things that initially disappointed us about the way email clients have integrated AI, simply as an extra layer on top of the inbox. We wanted to do things differently by building an inbox where agents work alongside humans

The human-agent inbox idea is interesting because email is full of half-finished work, not just messages. The key question for me is trust: when Upstream drafts replies or tracks open loops, does it explain why something matters and what context it used from connected tools before a human acts?

 great question. Every time Upstream creates a reply or follow up you are able to see why it did so and the context it used from various tools.

Haha an image is worth a thousand words I guess.   did you have specific use cases in mind in which it's super important for you that the agent explains why he did this or that action?

 Yes. Three use cases come to mind: customer follow-ups, sales/prospecting replies, and internal commitments pulled from meeting notes or email threads. In each case, I’d want to know what context the agent used, why it thinks the action matters now, and whether anything is customer-facing before sending.

 do you think our UI above would help answer those questions? Where it shows which sources the agent pulled from to draft the response? Would you add anything?

Congrats on the launch Upstream team! It’s the only product where I find myself hitting « send » most of the time without changing anything in the AI’s draft. It’s so much faster than having to prompt Claude Code or Codex, wait for it to find the thread, analyze, draft and answer, then re-write half of it manually

 Thanks so much Thomas! Super happy that you're saving so much time with Upstream

thanks Thomas. I'm glad you like the product!

 thank you!

 Best signal we can get. Thanks!

 Sending drafts as is is the goal - thank you, Thomas! 🙏

   fully agree! so happy we nailed it!

After a few weeks, it's obvious that Upstream is the SuperHuman of the AI era - congrats to the team!

 Thanks so much Arthur 💪

Thank you so much for your words Arthur

 🙌🏾🙌🏾

 Thank you so much Arthur! It's heartwarming to be compared to Superhuman, a giant, which has been an inspiration for us.

   Huge compliment - thank you. That’s exactly the level we’re aiming for!

 That means a lot, Arthur - thank you! 🙏

Congrats on the launch guys!

 Thanks a lot!

Thanks so much Quentin! :)

 thanks 😄

 Thank you so much!

Can't wait to try it!!!

 We can't wait either!

 can't wait to get your feedback :)

 let us know what you think!

 please share your thoughts later :)

 Thanks, Damien! Hope you love it 🙌

Best team, best product!

 Thanks a lot 🙌 🙌

Haha ! Thanks so much

 we appreciate your support!

 thanks man, really appreciate this!

 Thank you so much Pierre Eliott!

Wonderful product !
Once you try it, you keep it forever !

 Thanks so much Romàn! That's the goal 😄

thanks Roman. We are on a mission to make email fun again :)

 💪🏾💪🏾

 Thank you so much Roman! i'm so happy you liked it!

 ❤️

First
Previous
•••
789
•••
Next