Elvin
Proactive AI that finds and finishes work before you ask
368 followers
Proactive AI that finds and finishes work before you ask
368 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.
Free
Launch Team / Built With
Render: Get up to $100K in startup creditsThe fastest way to launch and scale your startup in the cloud
Promoted
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
@ellie_powers This is exactly the kind of friction-reducing tool teams need. I'm curious about how you handle context retention across different project types—does it learn task patterns from user behavior over time, or is it more reactive to explicit task structures? For freelancers juggling multiple client projects with different workflows, that distinction could be game-changing.
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.
@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!
Congrats on the launch! Read through Ellie's answers on the approve-the-plan model — really thoughtful, and the "reading is free, approve before acting" split is the right shape.
The one edge I'd be curious about is the recurring pre-approved skills. Per-task approval is well covered here — but once a recurring skill runs on a pre-approved plan, that's where the autonomy quietly lives, and the risk isn't the plan, it's drift:
the context shifts underneath a plan that was approved weeks ago, and it keeps executing confidently against the old
assumption. Do the recurring skills re-check themselves against current context before each run, or flag when what they're
about to do diverges from the original approved intent? That's usually where "set and forget" automations end up burning
someone.
Either way, flipping AI from routing-layer to proactive is the right direction — nicely done. 👏
@syed_noor4 Thank you, Syed! Even though the plan is pre-approved in skills, our orchestration layer re-evaluates it during the planning phase. This is then highlighted in the final output generated.
@harini_mukesh We've heard about less of a feeling that things are slipping through the cracks and a greater feeling of leverage.
The proactive part is exactly what I'd want and also what I'd be most nervous about. How much does it act on its own versus check with me first?
@suzychase This has been a huge thing that we've given a lot of thought to. Here's the model that we have so far. We allow Elvin to read in all the data sources that you have connected for free while it's researching and putting together a plan. Before it executes its plan, you have to review it and click Approve. If you don't like anything about the plan, you can request a correction. Elvin will show you in advance which data sources it will change, and if, during execution, it finds it needs additional permissions, it has to go back to the user to request them.
@suzychase it always comes up with a plan that you approve. The proactive part removes the need to prompt, find tasks or create agents. Elvin does that for you.
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?
@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?
@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.