This is something we've been working on at Vaani AI @Vaani Developer Platform . We wanted to solve a simple but important problem: a caller shouldn't feel like they're starting a new conversation every time the system switches agents.
The challenge is that passing a summary isn't always enough. Small but important details can get lost, like a callback time, a promise made earlier, the caller's language preference, or the context behind a decision.
At Vaani, we've been working on making agent handoffs more seamless, so the next agent can pick up the conversation without making the caller repeat themselves or creating a disconnected experience.
But there's still an interesting design question here. How much context should move between agents? Should every agent have access to the full conversation, or should each handoff carry only the relevant context?
Hey Product Hunt 👋
I’m Chandra from Vaani, a small voice AI team in Bengaluru.
Voice AI started with great models and only later got applications, so putting an agent on a real phone line still means stitching together speech, an LLM, telephony, tools and retries. We built an internal tool to configure agents without all that glue. Founders, PMs and developers who saw it kept asking for access, so today we’re opening it up.
What you can do, no code:
Design the call flow, including how the agent handles objections, interruptions and edge cases
Give it actions: hold, schedule a callback, hand off to another agent or a human
Connect a knowledge base so it answers from your docs mid-call
Pick a number and go live
After every call, get structured data: extracted fields and a disposition, so you don’t have to read transcripts to know what happened
It also orchestrates multiple models and switches to a backup if one fails mid-call, so one bad response doesn’t wreck the conversation.
We started with languages where data is scarce, which is why “sounds local” matters so much to us. It’s built to work for your customers wherever they are.
What’s the first voice agent you’d build, and what would you expect to break it?
We’ll be in the comments all day.
Try out the platform first-hand at https://platform.vaani.dev/
Grab 1000 free credits by using the code PHL1000X
@chandrashekran_y I'd build a "call my notes" agent.
Call a number, ask what I decided about a project last week, get an answer from my docs without opening five tabs.
What I'd expect to break it: me switching between Hindi and English halfway through, then interrupting to correct a name. That's a pretty normal conversation, but a messy test case.
Also curious about the fallback: if the model switches mid-call, does the new one retain the full context, or does the caller have to repeat themselves?
@maybe_someone_20 We actually built this platform for curious techies like you,
Cant wait to see how your built goes, do share a feedback and love if posssible!
And reg. your question, absolutely, the agent context is preserved independant of the models at play
@chandrashekran_y gotcha, looking forward to that!
@chandrashekran_y How well does Vaani handle interruption and backgrounds noise during real phone conversation????
@amrita_prajapati2 haha, this is a classic problem buddy, more our agents naturally handle, but better, we hand out these control and control to the users, you can control exactly how the agents need to behave.
also, regarding handling background noises, we have build propriety modules that solves for these conditions., would for you to try out and let us know!
How well do you guys handle people switching between hindi, english and regional languages mid-convo, like we naturally do in India?
@nishank_koul haha, this is one of the first problem statements we started out with,
To be very frank, We treat language as a probability n not a setting, Vaani.dev tracks context across turns to predict switches and mixing patterns, or you can lock a languages by config when you need strict control.
Congratulations Vaani team on the launch. The product looks really promising. I want to know what all use case does the Vaani agent covers also what all integrations does Vaani currently provides.
@vishal_goswami7 Hey Vishal, thanks for the wishes!
We already have close to 150 prebuilt templates - across multiple usecases and languages, so go the templates sections > filter by industry (we have close to 10 of them), and find the best template for yourself!
And reg, the integrations, our platform support a lot of integrations, but you wanna make a custom integration., that's also very much possible!
Do try out these features and let us know how it went!
Can't wait to hear from you!
Very impressive. I created an account and played a little with it.
I've noticed that while Hindi is offered as a default language, all English agents come with only one accent. Are you planning to expand that to various accents?
@ilyasb Happy that you created an account and tried out the platform and you found it impressive!
Yes, we currently have these accents out if the box, also if you wanna explore more langues/ accents, try out the voices on Voice lab, also you can clone your voice!
We are also constantly improving our library with more n better voices.
Vanni works for the vernacular languages too?
@avirup_sarker Absolutely, Low resource languages is one of our biggest strengths, would love for you to try it and let us know how it goes!
Congrats on the launch! Love that every call ends with structured data, reading transcripts to figure out what happened is the worst part of voice agents.
@leo_kostetskyi Heyy, you pointed out the exact pain points that 1000s of builders face everyday, you dont have to go through this at all in our product, and better, you can configure what exact questions to record and store,
We wanna hand over all the control to our users.
@leo_kostetskyi thanks Leonid.
Plus, if you ever realize you need extra insights later, you can just add new fields anytime and it’ll automatically extract them for you!
The handoff to a person is the bit I'd spend time on. The caller shouldn't have to repeat the details they already gave the agent.
@oleksii_sekundant Absolutely, all agents prior to the call handover to the human agent will deliver a summary of all the key points of the calls.. This way the caller never have to repeat anyhing, the human agent can take over from where the agent left!