Impressive demo, just wish I didn't have to request a demo and could just sign up. Request a demo button also does nothing other than change the text on success - not sure if it even went through...
I got the demo request:) Let me reply to you
Launch HN: Leaping (YC W25) – Self-Improving Voice AI
11–20 of 44 posts
Re: Launch HN: Leaping (YC W25) – Self-Improving Voice AI
#12congrats! Some time ago we were giving client intake in legal a try with a voice AI product, but we never were able to get the success rate higher than really low numbers (especially with sensitive use cases like legal where people will reject the call instantly if it's a bot). Have you guys seen use cases like this? What ranges of success rates/engagement times have you seen?
Why do you think it didn't work out in legal? We currently don't focus on that domain.
In general, we currently have really high success rates with relatively constrained use cases, such as lead qualification and well scoped customer service use cases (e.g., appointment booking, travel cancellation).
In general, voice AI is hard because WYSIWYG (there is no human in the loop between what the bot is saying and what the person on the other side gets to hear). Not sure about legal, but for more complex use cases (e.g., product refunds in retail), there are many permutations in how two different customers might frame the same issue and so it might be harder to accurately instruct the AI agent in a way to guarantee high automation results (given plentitude of edge cases).
It is our belief therefore that voice AI works the best, when the bot is leading the conversation and it is always very clear what the next steps are...
Re: Launch HN: Leaping (YC W25) – Self-Improving Voice AI
#13Have you tried your solution in noisy environments? Like a call to a person in a restaurant.
Re: Launch HN: Leaping (YC W25) – Self-Improving Voice AI
#14Your demo is nice, but why don't you show a call? That would be a lot more convincing...
Re: Launch HN: Leaping (YC W25) – Self-Improving Voice AI
#15congrats! Some time ago we were giving client intake in legal a try with a voice AI product, but we never were able to get the success rate higher than really low numbers (especially with sensitive use cases like legal where people will reject the call instantly if it's a bot). Have you guys seen use cases like this? What ranges of success rates/engagement times have you seen?
Why do you think it didn't work out in legal? We currently don't focus on that domain. In general, we currently have really high success rates with relatively constrained use cases, such as lead qualification and well scoped customer service use cases (e.g., appointment booking, travel cancellation). In general, voice AI is hard because WYSIWYG (there is no human in the loop between what the bot is saying and what th…
I think the problem relates to the core value proposition of automating an intake department with voice AI. The best voice AI customer is in an industry in which there is a clear increase in value that comes with the ability to handle a larger mass of calls. This was not the case in the legal world, when one missed client might be a loss of millions (and many firms would live off of Therefore I think the verticals of customer service and lead pre-qualification make a lot more sense. Since you guys have the numbers, I am curious to learn more about the way you define constraints for the bot and how often calls in these verticals deviate from these constraints.
I'm also curious about your opinions/if you've seen any successful use cases where the bot has to be a bit more "creative" to either string together information given to it or make reasonable extrapolations beyond the information it has.
Re: Launch HN: Leaping (YC W25) – Self-Improving Voice AI
#16Congrats on the launch! I work in this space, and fwiw I strongly agree with the idea of A/B testing + continuous improvement. I have found that it is relatively easy to setup A/B tests, much harder for stakeholders to draw the right conclusions.
Re: Launch HN: Leaping (YC W25) – Self-Improving Voice AI
#17what does the feedback loop look like to your agents - wonder how hard it will be to generalize metrics across these agents!
Re: Launch HN: Leaping (YC W25) – Self-Improving Voice AI
#18Your demo is nice, but why don't you show a call? That would be a lot more convincing...
Only for the data privacy reasons
Re: Launch HN: Leaping (YC W25) – Self-Improving Voice AI
#19Have you tried your solution in noisy environments? Like a call to a person in a restaurant.
Noisy is ok, but it doesn't work that well when there are multiple clear speakers and not much noise. We are planning to add speaker diarization to address this.
Re: Launch HN: Leaping (YC W25) – Self-Improving Voice AI
#20what does the feedback loop look like to your agents - wonder how hard it will be to generalize metrics across these agents!
feedback is generated based on evals.
example:
eval: function foo wasn't triggered even though [...]
feedback (exaggerated): 1. change stage prompt 2. change function description 3. add extra instructions to the end of the context
metrics are easy to generalize (e.g. call transfer rate), but baseline is different for each agent, so we're interpreting only the changes, not the absolute values (in the context of self-improvement).