Viewing profile — sumanyusharma

Congratulations on the launch. Few qs: How do your agents decide a suspected issue is a validated vulnerability, and what measured false-positive/false-negative rates can you share…

How is this different from Integuru? They posted a few weeks back here: https://news.ycombinator.com/item?id=41983409

Appreciate the info; I'll double-check Fidelity again!

I'm actually pretty interested in what you're building. Sure, Vanguard and Fidelity are well-established giants, but they've barely moved beyond standard ETFs for decades. Having t…

No plans for acquisition :) Building product, talking to customers and making something people want!

We're focused on end-to-end evals focused on function-call accuracy, style, tone & latency of the conversations between our sims and your voice agent. Less focused on pure TTS eval…

Pipecat looks awesome! I'll run the examples over the weekend and try to see what the integration hooks need to look like: https://github.com/pipecat-ai/pipecat/tree/main/examples …

Likely outsourced call centers since call complexity is low to medium. We also expect rapid adoption in industries like customer service, healthcare, and retail, where 24/7 availab…

Should be fixed now; could you try again please?

We forgot to enable non-US numbers in our config for the demo. (oops) We're working on a fix right now!

I am curious - how was the team solving this at Kea?

I use Superwhisper (no affiliation, just a happy user), which runs a local Whisper model, to create most of my email drafts and post-meeting notes. I find Whisper more accurate tha…

I'm curious to learn more about what's blocking the widespread adoption of the LLM capabilities. Lack of knowledge, reliability, or something else?

This tracks. Text evals to test core logic and voice evals for overall end-to-end performance!

It's a bit of a catch-22. Making current voice agents reliable is incredibly time-consuming and complex. This challenge has kept many teams from pushing their agents into productio…

Our customers, who build voice agents, are often asked by their customers to make their voice agents more human-like and flexible. Their clients — businesses like pest control and …

Bolna looks awesome! We've considered going open-source, but we're not sure how to effectively manage a community. I'll reach out async!

Absolutely agree that creating effective evals requires domain expertise. Right now, we're co-building evals with customers, but we're identifying which aspects can be productized.…

Yes! We're aiming to build a tool that both engineers and non-engineers love. We've discovered that it's often faster for non-technical domain experts to iterate on prompts in a st…

I wonder if a more optimistic version of this could be used to train humans and improve their skills. I'm thinking along the lines of LeetCode / Project Euler, but more dynamic and…

Yes! Drive-through customers can be very impatient. We tried to make the demo persona maximally annoying. Testing for edge cases is especially important because getting an order wr…

Nice! What's the use case your agent solves for? I'm happy to spin up some scenarios that are more relevant for you instead of our stock demo personas :) Feel free to email me at s…

Yup, we named it after Richard Hamming. His essay 'you and your research' was deeply influential during my undergrad; I re-read it every quarter. Our current product draws inspirat…