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

Great product! I tested it and I'm pleasantly surprised by its effectiveness! It manages my emails very well, with highly relevant suggested replies that save me time—just reread and send! I haven't tested the collaborative aspect with my team yet, but the promise is there: working together on emails to provide the best possible responses, all while staying aligned with everyone, and all powered by AI. I highly recommend it!

 Thanks a ton Johan! We really appreciate it. Let us know if there are any features that would make things easier.

So glad to have you as part of our early users Johan. Thanks for the support ❤️

 we love that you’re finding so much value already!

 thank you - great to hear the replies feel relevant

 So glad it's saving you time, Johan - thank you! 🙏

Great product. Much better than any other inbox app I’ve tried!

 🙏 Thanks Andrew!

 love hearing that Andrew!

 Thanks Andrew, appreciate it! What's your favorite feature in Upstream?

 Appreciate it. We’re trying to make email feel like a real upgrade, not just another inbox.

 Thanks so much, Andrew! 🙏

This looks great, but I'm just concerned about privacy... especially when dealing with internal emails containing confidential information. I have safeguards matching the sensitivity of the information, but having an AI agent reading and classifying my emails may be a risk factor. Anything you can suggest here?

Overall, great product nonetheless!

thanks for the comment. Are you concerned about your data being read by LLMs, or more specifically about agents making mistakes and your data being leaked ? If it is the latter, then all actions in Upstream need to be approved before they get executed. For instance, agents cannot send emails without your permission. You always have to click Send

  curious if that answered your question!?

Total game changer. Congrats team for the launch!

 Thanks Adrien!

Thanks Adrien ❤️

 thanks so much!

 thanks a lot!

 Thank you so much Adrien!

Simplicity in answering my emails that makes me almost enjoy answering them 👌

 the more we can make email more joyful and less anxiety-inducing, the better 🙂

we are on a mission to make email fun again 🚀🚀🚀

 love that!

 Why almost? 😂 What could we improve to make it even more fun? 😁

 love to heart this!

The open-loops part is the bit that stands out to me. Drafting replies is useful, but remembering what needs a follow-up is where email quietly taxes people every day. Curious whether those reminders are purely email-thread based or can pull from Calendar/Granola context too.

 We create follow ups on email threads. We also create follow up emails after each Granola meeting, with a summary, action items and recipients added.

What other types of follow ups do you have in mind?

 Before generating a follow-up in a given conversation, we also check other conversations to see whether you actually received a reply on the topic before following up. Also, I’m curious to learn what use cases you have in mind for Calendar.

My new favourite email client. Insane how many times I’ve simply hit ‘send’ on an auto reply!

 Love hearing that Antoine! Thanks for your support

I love to hear that ❤️

 I love that we nailed your voice!

 There's nothing better than just clicking send on an auto draft 😌 If there was one thing you could change in upstream, what would it be?

 Love to hear it!

How much time can agents save on emails daily?

 It all depends on your email volume, the types of inbound message you receive, and how often you typically reply to messages.

What are you most common email use cases?

how much do you want to save? 😁

   Jon "aka" the agent automation king. This guy would automate his breakfast if he could

 It depends on your inbox, but the main savings come from having drafts, triage, and follow-ups ready without prompting from scratch

Congrats on the launch!

 Thanks Raphaël!

Thanks Raphael

 thanks a ton!

 thank you so much!

The human + agent inbox model is interesting - most tools treat agents as a bolt-on to an existing workflow, and it creates friction. Building the inbox around the assumption that agents will be first-class participants from day one is a different design choice. What's the biggest behavioural change you've seen in users when they start treating the AI as a teammate rather than a tool?

Very good question Lava! I'd say that the biggest change is that people start delegating much earlier. Instead of opening a thread, reading everything, thinking for a few minutes and then asking AI for help, they immediately pull an agent into the conversation and work from there

I would add that people stop complaining about their inbox all the time and actually have a different relationship with it!

Yeah, that's a very good point indeed  

 100% agree with this

 I just want to jump on one thing:

most tools treat agents as a bolt-on to an existing workflow, and it creates friction.

I couldn't agree more. Putting AI where it doesn't belong is such a bad experience. that's why we took our time before integrating it. We really wanted to add AI where it made a difference, and was actually useful to out users.

First
Previous
•••
456
•••
Next