Upstream - The inbox designed for humans and agents
by•
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.
Replies
Congrats on the launch @jontiret!
Thank you@abhishek_kankani !!
@jontiret @abhishek_kankani thanks so much!
Thank you so much for the support @abhishek_kankani :)
@jontiret @abhishek_kankani thx!
@jontiret @abhishek_kankani Thank you so much!
Amazing product! We've been using it and love the agentic features
@nikolay_rodionov love hearing this!
Thanks Nikolay! Curious what part you like the most?
Thanks so much@nikolay_rodionov
I'm glad you liked them.
@nikolay_rodionov thanks! Happy to hear you like it
@nikolay_rodionov I'm so happy to hear you like it :D
Is Outlook on the roadmap?
@nicole_harrison yes! Hoping to do it as soon as possible
That's going to be interesting to implement Outlook :)
@jontiret Oh boy we're in for a ride 🔥
You can still try with your Gmail account if you have a personal one
This is a great product but I encourage you to embrace an open source strategy like paperclip.ing, it is more scalable and builds more trust
Thanks @mikestaub ! Out of curiosity, what part do you think benefits the most from being open source: is it the customization, the trust/transparency, something else?
@jontiret trust and transparency is #1, but customization is #2. If you go open source you can create an extension ecosystem and go for a real platform play like VSCode or Slack
That’s an interesting way to think about it. The platform angle wasn’t the first thing that came to mind, but VS Code is definitely a compelling example. Thanks for sharing your perspective! 🙏 🙏
@mikestaub thanks for sharing your thoughts, building trust is core
@mikestaub @amperisk ➕
Thanks @mikestaub , would you use it if it was open source? Would you want to host it yourself or use a hosted version?
Congratulations for the launch! 🚀
Thank you Maxence! It’s been a fun week 🚀
Thanks Maxence, really appreciate it!
@lerigner thanks so much!!
@lerigner thanks, appreciated!
@lerigner Thank you so much Maxence
congrats on the launch @louislecat and team! looks great
@louislecat @deepkkapur thanks so much Deep!
Thanks so much for the support @deepkkapur ! Looking forward to your feedback
@louislecat @deepkkapur thanks a lot!
@louislecat @deepkkapur Thank you so much Deep!
I kept using the product and I love it!🥰
@delphy_rodriguez so happy to hear that Delphy!
@delphy_rodriguez thank you!! Any feedback on your experience so far?
It means a lot coming from you@delphy_rodriguez :)
@delphy_rodriguez Love hearing this, Delphy! 🥰 Thank you so much for the support.
Curious about two things - how does Upstream actually learn to sound like me? does it analyse my existing email history or is there a setup process where i train it manually? and when the agent hits an email its genuinely unsure about what happen, does it flag it, skip it or takes its best guess ?
@pradyumna6 Great questions! Yes, we learn from your existing email history to build a writing profile, including how you naturally write to different people.
When the agent isn’t sure, it’ll often make that uncertainty obvious rather than pretending it knows everything. Sometimes that means making its best guess, sometimes leaving placeholders for you.
Would love for you to give it a try and let us know what you think. I’m especially curious how often you end up tweaking the drafts versus sending them almost as-is.
Really like the focus on inbox triage rather than just AI writing. Knowing what actually needs attention is probably the biggest email problem today. Congrats on the launch!
@anuhas_ranasinghe Thank you so much Anuhas!
@anuhas_ranasinghe thanks so much!
@anuhas_ranasinghe thanks! We’ve found that deciding what deserves attention is indeed often harder than writing the reply itself :)
the "bet on the tool everyone uses" call is the right one. every "kill email" startup eventually shipped a thing 10 people use. the people drowning in 200 emails a day don't need a new protocol. they need the inbox they have to behave differently.
real question for the team: how do you handle the trust gap when an agent drafts a reply? specifically the moment a user has to choose between "send the draft" and "rewrite it because the agent missed nuance i never spelled out." that's where every AI email tool i've tried lost me. the cost of correcting the agent eventually exceeded the cost of writing from scratch.
if upstream's solved that ratio, that's the only thing that matters.