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
Sidhant Kabra
Maker
πŸ“Œ

Hi Product Hunt Fam πŸ‘‹ - @kabra_sidhant, @shashij_gupta and @tarush_ here from Cekura AI.

Cekura lets you simulate, evaluate and monitor your Voice & Chat AI agents automatically.

Why did we build Cekura? πŸ’‘

Cekura was born out of our own frustration building voice agents for healthcare, where every change required hours of manual QA, yet critical failures still made it to production. We built the platform we wished existed: one that simulates conversations at scale, generates edge-case scenarios, and monitors real-world agent calls for failures.

Team Background πŸ‘₯

Shashij has published a paper on AI systems testing from his research at ETH Zurich and Google. Tarush has developed simulations for ultra-low latency trading, and I have led product and growth teams before, including a conversational AI company. All of us met at IIT Bombay and have been friends for the last 8 years.

Problem🚨: Making Conversational AI agents reliable is hard. Manually calling/chatting with your agents or listening through thousands of conversations is slow, error-prone and does not provide the required coverage.

Our Solution: At Cekura, we work closely with you at each step of the agent-building journey and help you improve and scale your agents 10 times faster

Key Features:

Testing:

  • Scenario Generation: Create varied test cases from agent descriptions automatically for comprehensive coverage.

  • Evaluation Metrics: Track custom and AI-generated metrics. Check for instruction following, tool calls, and conversational metrics (Interruptions, Latency, etc).

  • Prompt Recommendation: Get actionable insights to improve each of the metrics.

  • Custom Personas: Emulate diverse user types with varied accents, background noise, and conversational styles.

  • Production Call & Chat Simulation: Simulate production calls to ensure all the fixes have been incorporated.

Observability:

  • Conversational Analytics: Provides customer sentiment, interruptions, latency and call analytics: ringing duration, success rate, call volume trends, etc

  • Instruction Following: Identify instances where agents fail to follow instructions.

  • Drop-off Tracking: Analyzes when and why users abandon calls, highlighting areas of improvement.

  • Custom Metrics: Define unique metrics for personalized call analysis.

  • Alerting: Proactively notifies users of critical issues like latency spikes or missed functions.

Major Updates Since Last Product Hunt Launch:

  • Added Chat AI Testing and Observability

  • Automated Expected Outcome along with each generated scenario

  • Simulation of Production conversations

  • 'Instruction Following' and 'Hallucination' metric to automatically flag deviations from Agent description and Knowledge base respectively

Who is this for?

Anyone building Conversational AI agents. If you want to make your voice & chat AI agents reliable, book my calendar here πŸ—“οΈ or reach out to sidhant@cekura.aiπŸ“§.

Demo πŸŽ₯

You can check out our demo video here.

If you'd like to engage in a fun roleplay, you can talk with our agent here: You will act as a customer support representative and our agent will call you for a refund, order status, and product recommendation. After the call, we will give you an evaluation.

Please note: In reality, we generate hundreds of simulations automatically and provide detailed analytics on your AI agent's performance as demonstrated in the demo video.

Shoutout πŸ™Œ

Thanks @garrytan for hunting us. Also @svkpham and @rohanrecommends for helping us with the launch. πŸŽ‰

Monia Dohas

@kabra_sidhant  @shashij_gupta  @tarush_  @garrytan  @svkpham  @rohanrecommends Are your evaluations based on audio, text, or both?

Tarush Agarwal

@kabra_sidhant  @shashij_gupta  @garrytan  @svkpham  @rohanrecommends  @monia_dohas We break down the evaluations via metrics. We do use both text and audio. Some metrics (e.g., latency, interruptions, sentiment) run on audio, and some metrics which check for instruction following work on text.

Fenil Suchak

Congrats on the Launch!

How do you guys see reliability going beyond metrics but being reliable/contextual in domain specific questions and conversations?

Sidhant Kabra

@fenil_suchak1, you are right. Reliability extends beyond conversational metrics, such as latency and interruptions. Its giving the right answer at every step for company/domain-specific questions as well.

We typically visualize metrics into three types:

  • Conversational Metrics: applicable across customers across industries

  • Industry Specific Metrics: applicable across customers for a particular industry. Healthcare: HIPAA compliance, BFSI: PCI DSS compliance

  • Company specific Metrics: Following company specific SOPs

Shashij Gupta

@fenil_suchak1 i think with time we are seeing a lot of improvement in model reliability. Along with that people are using custom logics with asserts, thinking models and nlp logics to make it more reliable

Nimish Gahlot

Do you provide alerts for production calls?

Sidhant Kabra

Yes, @nimishg , we provide alerts for production calls over Slack and Gmail. You can also setup frequency of alerts as daily or as soon as the issue happens, e.g: latency spikes

Shashij Gupta

@nimishg yes you can get alerted whenever something critically wrong goes into production

Kunwar Raj

Absolutely love your product guys, best in the market!

Sidhant Kabra

Thanks a lot@kunwar_raj 

Shashij Gupta

@kunwar_raj thanks a lot

Ritesh Bansal

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

How does pricing workβ€”are plans usage‑based or seat‑based?

Do you support multichannel testingβ€”e.g., SMS or chatβ€”in addition to voice?

Shashij Gupta

@ritesh_bansal1 We do support chat along with voice. We have monthly subscription based plans

Tarush Agarwal

@ritesh_bansal1 the pricing is plan based where each plan gives you an amount of credits and these credits can be used for the different aspects.

Ashish Dogra

Do you support multichannel testingβ€”e.g., SMS or chatβ€”in addition to voice?

Shashij Gupta

@ashish_dogra Yes, we do support chat modality as well.

Sidhant Kabra

@ashish_dogra  @shashij_gupta We already have customers including some of the largest CCAS players running thousands of simulations for their digital (chat) agents

Roshan Rajak l byteio.Ιͺn

What’s the most impactful metric your current customers track that really moves the needle for improving their agents?

Tarush Agarwal

@truroshan the most important metric is Instruction Follow which is a very powerful AI Agent on our side.

Shashij Gupta

Here we goo :)

Aditya Lahiri

Best Voice AI Testing platform on the market with an impeccable team! Lets gooo!

Shashij Gupta
Sidhant Kabra

@aditya_lahiri  Thanks mate!

Sagar Kalsaria

Great Product Folks!!

What were the technical challenges you've solved while building Cekura?

Shashij Gupta

@sagar_kalsaria the major one is coverage of test cases. We need to ensure we are able to provide and cover all the cases which people are gonna see in prod. There is still a long way to go.

Harkirat Dhanoa

Congrats on the launch @shashij_gupta

Shashij Gupta
Harkirat Dhanoa

@shashij_gupta Can you share what technical challenges you ran into, while building Cekura?

Shashij Gupta

@harkiratdhanoa the major one is coverage of test cases. We need to ensure we are able to provide and cover all the cases which people are gonna see in prod.

Rishi Penmetcha

Great product, even better team. I did a thorough bakeoff of the options out there to improve dev velocity and stability for a voice agent, and Cekura had the most intuitive platform. But what really drove it home was their true customer obsession and top-notch service. They’ve been deep in the weeds with us and real thought partners in our voice agent journey.

Tarush Agarwal

@rishipenmetcha Thanks Rishi! Your feedback has been invaluable.

Shubham Pratap Singh

Congratulations on the launch πŸŽ‰

Sidhant Kabra
Shashij Gupta
Nikunj Agarwal

Congrats on the launch!!

Do you guys test GenAI bots or NLU bots as well?

Shashij Gupta

@nikunjagarwal321 yes, you can test nlu bots as well

Aditi Choubey

Do you support multichannel testingβ€”e.g., SMS or chatβ€”in addition to voice?

Shashij Gupta

@aditi_choubey1 yes we do support chat based testing

Anjali

Congrats on the launch! πŸš€

Shashij Gupta

@anjali19_ thanks

Alexandre Contador

Congrats team! This looks great!

Shashij Gupta
Tarush Goyal

Great stuff!

A question - how is data privacy / security handled for sensitive segments such as healthcare?

Shashij Gupta

@tarush_goyal We are HIPAA & SOC2 complaint. We have implemented industries best practices to secure the data.

Haz Hubble

congrats on the launch team, looks awesome!

Shashij Gupta

@hazhubble thanks

Om Dahale

Let's go! ❀️

Tarush Agarwal

@om_dahale Yess! Thanks for all the help