When you call customers, the first thing you often hear is a call screener, voicemail, an automated menu, or a "number switched off" message. In our own test of about 2,700 real calls, that was nearly 18%.
An agent who doesn't notice starts talking to a machine, wasting money and sounding silly.
Now it recognises what it is talking to and reacts:
- Call screener: introduces itself, then waits for the person.
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.
How does it deal with people interrupting the agent, or speaking before it is done with its response?
@manik_singhal1 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 and calibrate it based on the use case!
@chandrashekran_y That makes sense! It is always helpful to be in control of these scenarios, particularly as the style of conversation varies based on use case. Will give it a try!
@manik_singhal1 yupp, absolutely!
you got it all at your finger tips!
@Vaani Developer Platform is the easiest platform for building voice agents!
@daksh_goel glad that you liked vaani dev platform. Pretty excited for what you build next with Vaani
we already run our reasoning in a langgraph pipeline. can vaani handle just the voice and telephony around it?
@heeraa_ananthan Yeah absolutely, its a modular platform, you can bring your own models, plug it in and get going with all your use cases!
@heeraa_ananthan @chandrashekran_y How about node based pipeline? What are the type of models you guys support
Congrats on the launch, Chandra! Starting with languages where data is scarce really resonates. We just localized our app into 14 languages and learned how different "translated" and "sounds local" are.
To your question: the first agent I'd build is a Turkish booking assistant for a small café or studio. What I'd expect to break it: people switching between Turkish and English mid-sentence ("rezervasyonu cancel edebilir miyiz?"), and Turkish suffixes stacking onto names and dates. Curious how it handles code-switching like that.
Fellow maker launching today, good luck to the whole team! 🚀
@erenasiroglu Hey Eren, the use case of Turkish booking assistant for a small café or studio is the perfect case we have tested our platform against, do try it and let us know how it went, can wait to hear back from you, also share the platform amongst your connections for them to check it out, its many months of efforts we have put into this product!