Launching today
Elvin
Proactive AI that finds and finishes work before you ask
349 followers
Proactive AI that finds and finishes work before you ask
349 followers
Stop acting as the routing layer between AI and your actual work. Elvin is proactive AI that finds coordination work across your tools, handles the messy multi-step parts, and asks before taking action. It turns scattered context from messages, meetings, docs, and task tools into ready-to-approve drafts, follow-ups, updates, and next steps.
Elvin
Who decided that AI gets to do the fun stuff while we remain the routing layer for work?
Hello Product Hunt! We’re Ellie and Vinay, the cofounders of Elvin.
We are busy people, creating Elvin for busy people
We built Elvin because we’re all overloaded. So far, AI is making it worse, not better. Every AI-generated message or newsletter becomes someone else’s noise, and that person still has to process it. And getting AI to help meant stopping to write a pile of prompts first.
Somewhere along the way, AI grabbed all the big, interesting work, and we got left as the routing layer. Sorting, chasing, following up. That felt backward.
If AI is so smart, it should figure out how it can help you, not the other way around.
So we built Elvin: a proactive personal agent that works ahead of you. It reads across your email, chat, and calendar, identifies what needs to be done, and gets started. It's as powerful as it is proactive. It does the big jobs, building documents and graphics, not just drafting emails (though it does that too).
If you’ve seen OpenClaw, you know proactive AI is real and can figure out how to do real tasks. Elvin is that, minus the hardware, the tokens, and the command line.
How Elvin works
🔍 Elvin finds tasks in your email and other tools (or you can message Elvin)
📋 Elvin creates plans for how to get the work done for you
✅ You just say yes, and off to the races! (Or tweak the plan)
⚡ Turn on Elvin’s pre-built skills for your job role or build your own
Elvin is multiplayer
🤝 Connect with your teammates
🤖 Even add your AI Agent friends like AI Software Engineer @Devin by Cognition
Elvin’s origin story
We like making powerful tools that are usable by everyone.
Back in 2018, I (Ellie) joined Slack and was immediately overwhelmed by the number of new messages and channels. I wondered when AI would be able to help me find what was most important for me to read, and could it generate a todo list based on information coming in from all of your messages and apps. In 2018, AI was not up to the task.
In 2025, Vinay and I realized that the technology was there to build a product that could not only find your most important work but also get it done for you with self-writing AI Agents.
Elvin is available on iPhone, Android, and the web. Free while it’s in beta. No waitlist. Big thanks to @Voicepanel and @CodeAnt AI for making Elvin possible!
Thanks for having a look!
✨ Ellie and Vinay
One X Sensor
Have you guys considered the possibility of two Elvins collaborating when their users are working together while keeping each user's context completely separate?
For example, if User A and User B have an important planning meeting coming up, their Elvins could coordinate data gathering and preparation on both sides, with each user authorizing what they're willing to share and what actions to take. The goal would be to automate the groundwork on both ends and surface the best possible outcome for the meeting.
One Elvin could request data or trigger an action on the other side, which would then prompt the other user for approval before anything happens.
Elvin
@gabriel_archanjo Yes! Right there with you! Two Elvins working together is something we're really excited about and working towards! We think it could be super helpful to allow collaboration within one company or between two people at different companies.
We hope that would really help coordinate work across a team!
Love the idea of AI that works ahead of you rather than waiting to be asked. How does Elvin handle situations where it gets context wrong and takes the wrong next step — is there an easy way to course-correct?
Elvin
@doganakbulut Great question. We definitely have worked hard to make sure that Elvin doesn't perform any actions that the user wouldn't want. What we do for that so far is that we first allow Elvin to research the task and it can "read" in as many tools as it wants for free, and then it forms its plan which is presented to the user. The user can review the plan and approve it or request a change. We have also spent a lot of time building logic that prevents Elvin from going outside of its approved plan.
Nice idea. How does Elvin decide what counts as coordination work worth surfacing versus noise it should ignore?
Elvin
@dhiraj_patel5 Thank you! When we're looking at what work to surface, we look at what is most important to an individual user as well as logic that we've honed across multiple users. We plan to continue tuning it so that it will do the best possible job for each person on day one.
The proactive angle is compelling. Most AI tools still wait for a prompt, which keeps humans as the workflow router. How does Elvin decide when to start work on its own versus when to pause and ask for confirmation? That boundary feels like the difference between an assistant and a real work agent.
Elvin
@rahulbhavsar The question about how proactive to be is a really great one, and it's one that we've shifted as we've built and tuned the product. Here's the model that we're working with now. For novel tasks that you give Elvin or Elvin finds, we tell Elvin that it can "read" as many tools as you've given it access to, then it prepares a plan for how it will do the work. Then the user needs to approve the plan or request a change. Elvin then executes the task. If it runs into an issue in the execution and needs to request additional permissions (reading is still "free"), then it needs to come back to the user for another approval.
We also allow you to set up recurring skills (for example, reviewing all your meeting notes at the end of the day and compiling action items). Once those are set up, they run with the pre-approved plans!
It's also something we may continue to revisit.
How do you think it should work?
I like the idea that Elvin looks for the coordination work first instead of waiting for a perfect prompt. Emails, meetings, docs, and task tools are exactly where the messy “someone needs to follow up on this” work usually lives.
The approval step also feels important. For anything involving teammates, clients, or important decisions, I would want the agent to prepare the work, but not silently act without me.
Curious how Elvin decides what is worth surfacing. Does it learn from what users approve, ignore, or edit over time?
Elvin
@andrasczeizel Thank you for learning about Elvin! Yes, it does learn from what users approve and ignore - there is also a button on items that Elvin found where you can tell it that it identified an item you'd like it to skip in the future and it will learn from that. We're definitely tuning it over time so that it will get closer to perfect results for each user as soon as possible.
Lancepilot
Elvin
@odeth_negapatan1 Thank you! Yes, we are excited about a future where human minds and capacity are supported by AI, not overwhelmed by the noise it can generate. I would say that one of the most impactful surprises early on was on @workmonk 's account. He received an invitation to speak at a conference. Elvin offered to put together a speaker proposal. It looked in his personal context layer, talking about his specific technical experience, Granola meeting notes, Linear tickets, emails, and more, to come up with a meaningful and technically accurate speaker proposal. All he had to do was review the plan and say yes, and boom! A better speaker proposal than he thinks he would have generated on his own. Our minds were blown.