Asmi calls you every morning. You talk - it handles the day. It calls services (dentist, salon, plumber, bank, insurance) or people (friends, colleagues) to coordinate, book or resolve things. Updates you on iMessage or WhatsApp when done. It can navigate IVRS, wait on hold and handle complex conversations well.
It started with a phone call from a close friend from my PhD days.
After a little chit-chat and a lot of catch-up, he asked me if I wanted to build something that actually helps people. Not in a vague, hand-wavy way but genuinely does the things you don't want to do yourself, and helps you do the things you actually care about, better.
The outbound call thesis is interesting - handling the messy phone-mediated workflows is genuinely the hard part of agent execution. One compliance layer worth building in now: Article 50(1) of the EU AI Act requires voice AI agents interacting with people in the EU to identify themselves as AI at the start of the call. For an agent calling a dentist's receptionist on behalf of a user, the opening line needs to be something like: "Hi, I'm an AI assistant calling on behalf of [user name] to [purpose]." That's also good caller experience - businesses responding to calls appreciate knowing what they're talking to. This obligation sits with whoever deploys the agent (Asmi), not just the underlying model provider. The August 2 deadline is 48 days out. If EU expansion is on the roadmap, building the disclosure into the call-start template now is much easier than retrofitting it later.
The clinic's website is broken. The second number rings forever. The third transferred me to a voicemail from 2019. I've been at this for 45 minutes. The appointment itself takes 20.
No reviews yetBe the first to leave a review for Asmi AI
This is the kind of AI I’d actually use because the task finishes outside the app. Curious how you handle guardrails like max budget, preferred times, or asking before it confirms something?
To keep you in control, Asmi smartly analyzes the task context and always asks for your confirmation and preferences—like a max budget—before initiating anything.
If an unexpected detail ever slips through the cracks, it immediately reverts to you to gather that information and wrap up the task to completion.
I had Claude, ChatGPT, Gemini open in three tabs. All brilliant. None of them would pick up the phone." that line alone sells the whole product. the IVR navigation and waiting on hold part is the real value because that's where everyone's time actually goes. not the conversation itself but the 20 minutes of hold music before it even starts. curious how it handles callbacks when the service asks to call back later
@tina_chhabra Thanks Tina. Whenever Asmi comes across a missed call or voicemail situation, either it can automatically recall in next few minutes or users can explicitly decide when Asmi should call back. Asmi is trained to handle all these task loops efficiently!
Report
Support for wide range of tasks, 50 lanuages and on top of that it's free? Wow, how come it's not the product of the day today? ;) Sounds super handy. I do wonder though how it would work in real life if i want to make a doctor appointment - will real people a the medical center for example even talk to AI?
Let me show this to you with an example. In the case you mentioned, Asmi will call the reception saying it's calling on behalf of Alexander to book an appointment for Saturday, 2pm. Given how human like and natural the experience is - most of the people/businesses are totally fine talking to an assistant That has been our experience.
Report
This sounds pretty cool but I’d be a little hesitant to give AI responsibility like that, especially for something like “fighting a charge with a bank”. How do you make sure it doesn’t book something wrong or spend money in the wrong place?
@montverde Hi Luke - great question! The case you highlighted, if Asmi needs to fight a chargeback, you just need to pass on the relevant info via text, a screenshot or a quick call . It will quote the same facts to the bank and resolve the issue. It does not need your personal card information or any access to your financial accounts. It is built to resolve issues with the information you choose to share with it. Hope it clarifies your doubt.
Report
@rishi_raj okay that makes more sense. That means it likely won’t hallucinate at the wrong time it sounds like. I appreciate it!
@mehulmishra6 Hi Mehul - Asmi does not take access to your contacts for privacy reasons. If you do share contact card or contact number over chat, it should be able to read contacts and also save them for future reference.
Report
Really exciting vision especially the ability to wait on hold and manage complex conversations without constant supervision. How do users typically build trust in Asmi before letting it make calls on their behalf?
Typically, people talk to Asmi over a call for the first time, give it one or two tasks, mostly making it call their personal contacts like their friends, family, or colleagues. Asmi accomplishes the first task, and we also have a flow where Asmi can send you the audio recording after a task is successfully completed. That's what creates more trust among people, and then they start using it every day for other tasks also.
Report
Interesting approach!!
What has been the biggest challenge in making the AI feel context aware rather than generic?
When users start using Asmi on day one, we don't ask for any integration or access to any of their personal apps. Asmi calls them every morning, and users share their personal chores to be done that day. That's how Asmi gets context on users each day, and it compounds over time.
To answer your question directly, the biggest challenge in this was that we were thinking we can directly integrate with users' email and calendar to pull up context, but then majority people are not comfortable sharing access to their private data on day one. That's where we created this experience where we don't ask them to integrate anything. It's frictionless and privacy-first. Whatever they want to share, they share, and we keep building this context and show them the value. On day 15 or day 30, users get really comfortable integrating more tools, and that helps them share the context easily, and Asmi becomes more high-agency and autonomous over time.
Report
@rishi_raj Thanks for the detailed response…
The “earn trust first, integrate later” approach is a thoughtful design choice 👍
@rishi_raj@harini_mukesh If you truly believe in the core thesis and the high baseline utility of the product, you can let that do the talking. That's how it is with Asmi. We trust you'll love it with or without integrations, so we can focus on providing you the best experience first.
Report
@sibi_asmi Cool I will give it a try and share my experience after a week
This is the kind of AI I’d actually use because the task finishes outside the app. Curious how you handle guardrails like max budget, preferred times, or asking before it confirms something?
@farrukh_butt1 Thanks Farrukh!
To keep you in control, Asmi smartly analyzes the task context and always asks for your confirmation and preferences—like a max budget—before initiating anything.
If an unexpected detail ever slips through the cracks, it immediately reverts to you to gather that information and wrap up the task to completion.
I had Claude, ChatGPT, Gemini open in three tabs. All brilliant. None of them would pick up the phone." that line alone sells the whole product. the IVR navigation and waiting on hold part is the real value because that's where everyone's time actually goes. not the conversation itself but the 20 minutes of hold music before it even starts. curious how it handles callbacks when the service asks to call back later
@tina_chhabra Thanks Tina. Whenever Asmi comes across a missed call or voicemail situation, either it can automatically recall in next few minutes or users can explicitly decide when Asmi should call back. Asmi is trained to handle all these task loops efficiently!
Support for wide range of tasks, 50 lanuages and on top of that it's free? Wow, how come it's not the product of the day today? ;) Sounds super handy. I do wonder though how it would work in real life if i want to make a doctor appointment - will real people a the medical center for example even talk to AI?
@alex_sh78 Thank you, Alexandr!
Let me show this to you with an example. In the case you mentioned, Asmi will call the reception saying it's calling on behalf of Alexander to book an appointment for Saturday, 2pm. Given how human like and natural the experience is - most of the people/businesses are totally fine talking to an assistant That has been our experience.
@montverde Hi Luke - great question! The case you highlighted, if Asmi needs to fight a chargeback, you just need to pass on the relevant info via text, a screenshot or a quick call . It will quote the same facts to the bank and resolve the issue. It does not need your personal card information or any access to your financial accounts. It is built to resolve issues with the information you choose to share with it. Hope it clarifies your doubt.
@montverde That's absolutely right :)
I tried posting addresses on the chat as well. . Its not able to parse contact addresses when posted on the chat either. That part needs work .
@mehulmishra6 Hi Mehul - Asmi does not take access to your contacts for privacy reasons. If you do share contact card or contact number over chat, it should be able to read contacts and also save them for future reference.
Really exciting vision especially the ability to wait on hold and manage complex conversations without constant supervision. How do users typically build trust in Asmi before letting it make calls on their behalf?
@iamwilliammills Thanks, Williams. Great question.
Typically, people talk to Asmi over a call for the first time, give it one or two tasks, mostly making it call their personal contacts like their friends, family, or colleagues. Asmi accomplishes the first task, and we also have a flow where Asmi can send you the audio recording after a task is successfully completed. That's what creates more trust among people, and then they start using it every day for other tasks also.
@harini_mukesh Thanks Harini. Great question.
When users start using Asmi on day one, we don't ask for any integration or access to any of their personal apps. Asmi calls them every morning, and users share their personal chores to be done that day. That's how Asmi gets context on users each day, and it compounds over time.
To answer your question directly, the biggest challenge in this was that we were thinking we can directly integrate with users' email and calendar to pull up context, but then majority people are not comfortable sharing access to their private data on day one. That's where we created this experience where we don't ask them to integrate anything. It's frictionless and privacy-first. Whatever they want to share, they share, and we keep building this context and show them the value. On day 15 or day 30, users get really comfortable integrating more tools, and that helps them share the context easily, and Asmi becomes more high-agency and autonomous over time.
@rishi_raj @harini_mukesh If you truly believe in the core thesis and the high baseline utility of the product, you can let that do the talking. That's how it is with Asmi. We trust you'll love it with or without integrations, so we can focus on providing you the best experience first.
@harini_mukesh Looking forward to it!