Comcent
AI-ready voice infrastructure on your own SIP trunk
Start new thread

Comcent - AI-ready voice infrastructure on your own SIP trunk

by
•
Comcent is voice infrastructure for teams that run on calls. Connect your Twilio account (or any SIP provider) in a few clicks and your team takes calls in the browser, with call flows, queues, transfers and recordings. AI transcribes and summarises every call, scores sentiment and tracks the promises agents make, and AI voice bots can answer and hand over to a person. Every call can go to your own systems as a standard vCon. Unlimited users from $20/month, and the core is open source.

Add a comment

Replies

Best
Maker
📌
Hi Product Hunt! Phone calls are where customers tell you the most, and where most businesses learn the least. Comcent changes that. Your team takes calls right in the browser, and AI turns each conversation into a summary, the customer's mood and the promises made, ready the moment the call ends. Every call can also flow into your own systems as a standard vCon, and the core is open source. I've spent four years working in telephony and built Comcent because the tools I saw were patched together and hard to build on. I'd love your honest feedback: what would you want to know from your calls? Launch offer: $25 free credit with code PRODUCTHUNT.

we build voice agents at Dial so "the promises made" line jumped out at me. the thing I'd want from that feature isn't just the list, it's confidence that a promise got flagged as a promise in the first place. a committed-sounding line like "I'll have that shipped by Friday" is easy to catch, but a lot of real promises come out softer, "I'll look into it" or "should be fine" said in a tone that the customer absolutely heard as a commitment even though the words are hedged. does the extraction lean on phrasing patterns or is it trying to catch the implied commitment too, since the gap between those two is where the actual broken promises hide

Maker

 Thanks Gal, great question. We don't use phrase patterns. An LLM reads the full transcript and pulls out commitments from context, so a hedged line like "I'll look into it" can still be flagged when the conversation treats it as a promise. Your point on soft promises is pointing us in the right direction. We're adding these cases to our LLM evals and will keep growing that set as testing goes on, so the softer commitments get captured reliably.