Garry Tan

Cekura - Launch reliable voice & chat AI agents 10x faster

Cekura is an end-to-end QA for Voice & Chat AI Agents. Cekura helps Conversational AI companies with pre-production testing and simulation as well as monitoring of production calls to ensure quality and reliability at every stage of development

Add a comment

Replies

Best
Raghavendra Devadiga

Which voice/telephony platforms and protocols does Cekura plug into out of the box (Twilio, SIP, WebRTC, etc.)?

Tarush Agarwal

@raghavendra_devadiga4 We do support Twilio, SAP, and WebRTC out of the box. We also support chat-based integrations via websockets.

Erliza. P

🗣️⚡ Cekura’s back with launch #2! Spin up reliable voice & chat AI agents 10x faster — speed meets stability, just how we like it 🛠️🤖

Erliza. P

🎙️⚡ Cekura’s back with launch #2! Build & launch voice + chat AI agents 10x faster — speed, scale, and stability in one smart stack 🤖📈

Rohan Abhishek Srikakulapu

Congratulations on the launch!

What are some of the metrics used, especially for the quality of Conversational AI agents?

Sidhant Kabra

@rohan_abhishek Some of the common metrics we measure are latency, interruption handling, context awareness, agent repetition, etc

Abby  G

Congratulations, my brother @shashij_gupta & TEAM on launching your product! That’s an incredible achievement. I’ve been curious - can Cekura detect and score tool calls (function calls) inside a conversation? Would love to learn more about its capabilities!.

Sidhant Kabra

Thanks @abby_3. Yes, we do test for tool calls and highlight different failure modes associated with it (correctly triggered, incorrectly triggered, incorrectly not triggered)

Kesav Kosana

Congrats! One of the fastest improving products I've seen this year :)

Sidhant Kabra
Jimmy E. Chan

Congrats on the launch!!

Sidhant Kabra

thanks@jimmyechan  for the support

Alfredo Diaz

Congrats on the launch, go Cekura!!

Exactly what the next generation of apps need

Sidhant Kabra

thanks@fredo 

Shantanu
Pinku Mallick

Hi guys, congratulations for this incredible work. I have some questions -

How does pricing work—are plans usage‑based or seat‑based?

Do you support multichannel testing—e.g., SMS or chat—in addition to voice?