Launching today
Upstream
The inbox designed for humans and agents
289 followers
The inbox designed for humans and agents
289 followers
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.
Been using Upstream in beta and the drafts genuinely sound like me, not like AI assisted. The reply’s already waiting when I open a thread. Congrats!
Upstream
@gregoireboutin We love nailing your voice, thanks for being an early supporter!
Daily driver here. Dictation mode lets me just talk and it writes. And "needs reply" is brilliant: the draft is already there waiting, so I'm never staring at a blank page, but I stay in control of what actually sends. Rare to find AI email that assists without taking over. Congrats to the team.
Upstream
@benjamin_lalanne1 We appreciate that Benjamin! Also there are quite a few of us in the office that use dictation too 🗣️🗣️🗣️
I’ve been using Upstream and what really stands out is how natural the drafts feel — they actually sound like me, not like a generic AI reply. Opening a thread and already having a solid response waiting there saves a surprising amount of time. The follow-up nudges are also genuinely useful for keeping important conversations from slipping through the cracks. Congrats on the launch — this is one of the few AI email tools that feels built for real daily use.
Upstream
@greg_lpz Thanks so much Grégoire!! Are there any features that would help make AI replies even better for you?
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!
Upstream
@johan_p_ Thanks a ton Johan! We really appreciate it. Let us know if there are any features that would make things easier.
Where do you guys draw the autonomy line on triage vs sending? Those two might fail completely differently IMO. Anyways, great work!
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!
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?