[HN Gopher] Launch HN: Leaping (YC W25) - Self-Improving Voice AI
___________________________________________________________________
Launch HN: Leaping (YC W25) - Self-Improving Voice AI
Hey HN, I'm Arkadiy from Leaping AI (https://leapingai.com).
Leaping lets you build voice AI agents in a multi-stage, graph-like
format that makes testing and improvement much easier. By
evaluating each stage of a call, we can trace errors and
regressions to a particular stage. Then we autonomously vary the
prompt for that stage and A/B test it, allowing agents to self-
improve over time. You can talk to one of our bots directly at
https://leapingai.com, and there's a demo video at
https://www.youtube.com/watch?v=xSajXYJmxW4. Large companies are
understandably reluctant to have AI start picking up their phone
calls--the technology kind of works, but often not very well. If
they do take the plunge, they often end up spending months tuning
the prompts for just one use-case, and sometimes never even end up
releasing the voice bot. The problem is two-sided: it's non-
trivial to specify the exact way a bot should behave using plain
language, and it's tedious to ensure the LLM always follows your
instructions the way you intended them. Existing voice AI
solutions are a pain to set up for complex use cases. They require
months of prompting all edge cases before going live, and then
months of monitoring and improving prompting afterwards. We do that
better than human prompters, and much faster, by running a
continuous analysis + testing loop. Our tech is roughly divided
into three subcomponents: core library, voice server, and self-
improvement logic. Core library models and executes the multi-stage
(think n8n-style) voice agents. For the voice server we are using
the ol' reliable cascading way of STT->LLM->TTS. We tried out the
voice-to-voice models, and although they felt really great to talk
to, function-calling performance was expectedly much worse, so we
are still waiting for them to get better. The self-improvement
works by first taking conversation metrics and evaluation results
to produce 'feedback', i.e. specific ideas how the voice agent
setup could be improved. After enough feedback is collected, we
trigger a run of a specialized self-improvement agent. It is a
cursor-style AI with access to various tools that changes the main
voice agent. It can rewrite prompts, configure a stage to use a
summarized conversation instead of a full one, and more. Each
iteration produces a new snapshot of the agent, enabling us to
route a small part of the traffic to it and promote it to
production if things look ok. This loop can be set to run without
any human involvement, thus making agents self-improve. Leaping is
use-case agnostic, but we currently focus on inbound customer
support (travel, retail, real estate, etc.) and lead pre-
qualification (medicare, home services, performance marketing)
since we have a lot of success stories there. We started out in
Germany since that's where we were in university, but initially
growth was challenging. We decided to target enterprise customers
right away and they showed reluctance to adopt voice AI as the
front-door 'face' of their company. Additionally, for an enterprise
with thousands of calls daily, it is infeasible to monitor all the
calls and tune agents manually. To address their very valid
concerns, we put all effort into reliability--and still haven't
gotten around to offering self-serve access, which is one reason we
don't have fixed pricing yet. (Also, with some clients we have
outcome-based pricing, i.e. you pay nothing for calls that didn't
convert a lead, only the ones that did.) Things picked up momentum
ever since we got into YC and moved to the US, but the cautious
sentiment is also present here if you try to sell to big
enterprises. We believe that doing evals, simulation, and A/B
testing really really well is our competitive edge and what will
enable us to solve large, sensitive use cases. We'd love to hear
your thoughts and feedback!
Author : akyshnik
Score : 69 points
Date : 2025-07-10 17:42 UTC (1 days ago)
| shahahmed wrote:
| congrats on launching! how are ya'll managing evals?
| kevinwu2981 wrote:
| Thanks! We provide eval templates that can be applied on
| specific stages or the whole conversation. Users can specify
| their own evals that can be as granular as they'd like. We're
| also working on conversation simulation feature that lets users
| quickly iterate on evals via simulating previous real
| conversations and seeing if the eval output aligns with human
| judgement.
|
| P.S. Arkadiy is locked out of his HN account due to the anti-
| procrastination settings. HN team, can you plz help? :)
| koakuma-chan wrote:
| How do you compare to livekit? I don't see any docs on your
| website.
| kevinwu2981 wrote:
| Livekit started as an infra for real-time audio/video
| applications. We are actually using them for WebRTC. They
| recently started growing into the voice AI space, but are still
| more of an infra solution, while we are an end-to-end platform.
|
| What sets us apart is multi-stage conversation modeling, out-
| of-the-box evals, and self-improvement!
| triyambakam wrote:
| Is this comparable to VAPI?
| kevinwu2981 wrote:
| Comparable in some aspects. Their focus is dev-tooling, while
| we are a mid-market and enterprise solution, geared towards
| enabling non-technical users at those companies, by using our
| tools, to easily create voice AI agents for customer service,
| lead qualification and ops use cases
| hajrice wrote:
| 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...
| kevinwu2981 wrote:
| I got the demo request:) Let me reply to you
| isabelleilyia wrote:
| congrats! 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?
| kevinwu2981 wrote:
| 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...
| isabelleilyia wrote:
| 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 < 10 successful cases a
| year).
|
| 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.
| kevinwu2981 wrote:
| We see the main value prop of voice AI to be to enable
| higher volumes of calls in a cost-efficient manner. It is
| clear that there is a slight trade-off on quality, because
| humans will do a better job in "high-stakes" calls and
| where creativity is more required.
|
| It thus makes sense why it might not work for legal, since
| every call there might be high stakes.
|
| Having the bot be "creative" is actually an interesting
| proposition. We currently do not focus on it, since the
| majority of our customers want the bot to be predictable
| and not hallucinate.
| lostmsu wrote:
| Have you tried your solution in noisy environments? Like a call
| to a person in a restaurant.
| akyshnik wrote:
| 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.
| joelthelion wrote:
| Your demo is nice, but why don't you show a call? That would be a
| lot more convincing...
| akyshnik wrote:
| Only for the data privacy reasons
| xp84 wrote:
| Weird, because it seems like the demo video is pretend data
| anyway ("Mr. Smith", etc). I agree, I would like to see a
| more fully-baked demo where you connect it to a testing CRM
| and a toy order api and get it to answer several customer
| queries using live information.
| akyshnik wrote:
| Ah, I misunderstood the question. Let me see if we can get
| something up.
| ajeet wrote:
| Congrats 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.
| kevinwu2981 wrote:
| Also every stakeholder might value different things: call
| deflection rate, CSAT, number of bookings, etc. Important to
| align expectations upfront
| vinodhkps wrote:
| what does the feedback loop look like to your agents - wonder how
| hard it will be to generalize metrics across these agents!
| akyshnik wrote:
| 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).
| costcopizza wrote:
| Very impressive! How many jobs do you estimate this could
| displace?
| akyshnik wrote:
| It's a huge industry, so a lot. Job is really stressful and has
| a lot of employee churn, so it's not really something I feel
| bad about. Pressing elevator buttons was a job too back then
| lostmsu wrote:
| What framework did you use for flow building?
| kevinwu2981 wrote:
| We are using Vercel
| ljclifford wrote:
| Super awesome demo! The contact center market, including inbound
| customer support, is incredibly ripe for disruption, and I'm sure
| you guys will be on the forefront of that.
|
| Kinda funny how many amazing CX companies start in Germany!
|
| I'm the CEO & founder of Rime, so I've been following your
| progress with real interest. Feel free to reach out and I'd love
| to explore ways we might collaborate. Until then, wishing you
| tons of success on this big milestone!
| kevinwu2981 wrote:
| The German call center market is very large, established and
| well-organised. Also pricing power here is often higher,
| because you cannot outsource call center work to outside
| Germany (because no one speaks German).
| cootsnuck wrote:
| How well does this scale? Like how many simultaneous calls can a
| single voice agent handle through your platform?
| kevinwu2981 wrote:
| It is very scalable. We currently handle >100k calls per day on
| our platform.
| AndrewKemendo wrote:
| I want this as an option to handle all my personal calls
|
| I built a skeleton of an iOS app that managed my calls such that
| I could choose to answer, decline or send to my chat bot
|
| So it gets real data from all my regular calls and in my state (1
| party consent) I don't need anyone's permission to record every
| call. So that data kicks off a fine tuning running that can run
| overnight or locally to improve my personal model
|
| My plan was to use whisper and a local model with my voice clone
| and it would talk with everyone I didn't want to eventually to
| the point where I don't ever talk with any person I don't want to
|
| I would pay you for a local way to do that, however I'd NEVER
| give you that data - but I'm sure plenty of people would
| kevinwu2981 wrote:
| Interesting and seems like a great use case. We currently focus
| on working with businesses though:/
| mandeepj wrote:
| > Existing voice AI solutions are a pain to set up for complex
| use cases. They require months of prompting all edge cases before
| going live, and then months of monitoring and improving prompting
| afterwards
|
| I wonder why! Most (or all) of customer support calls are
| recorded. Have you tried (or proposed) to train on that corpus on
| your Customers premises? You can do multiple evals in that
| setting - replay user calls into corpus trained ai agent vs
| generic ai agent and see the difference. Agents can be run on a
| 24x7 self-test, analysis, adjustment, and reporting loop.
| Continuously run that loop and compare the prompts of your ai
| agent vs human operators.
|
| Edit: Grammar
| kevinwu2981 wrote:
| This is on the roadmap. We haven't yet been able to execute on
| this, since we are still laying the foundations, but this is a
| great idea!!
| ookblah wrote:
| the demo is pretty impressive ngl. knowing it's a bot though
| makes you want to phrase your questions a certain way, so i tried
| to just pretend like i was talking to an actual support person.
|
| i always feel with these bots its like way too "polished" in the
| responses or how it speak. maybe that's a good thing and we are
| just so used to hearing someone speaking more casually be less
| well spoken lol. it makes it feels inauthentic, but perhaps that
| will change over time.
| kevinwu2981 wrote:
| Essentially you are currently optimizing for the majority.
| Looking forward to how that develops over time as conversations
| get more personalized
| froh42 wrote:
| It's too funny. I tried the voice chat and it was the typical
| frustrating shit, misunderstanding words, then slowly answering
| to them - "das Ding" it understood as "Singen" etc. You could
| film a comedy with that, but a company that owns something like
| it - I'd never call them.
| kevinwu2981 wrote:
| It seems you tried the English demo. Wondering was the website
| in English or German for you?
| devonsolomon wrote:
| The problem is... When (if) we pick up the phone today it's
| because we want to speak to a human.
|
| Most people, avoid phone calls if possible.
|
| If I get a call and it's an AI, I, like everybody else, is
| putting down.
|
| If I'm picking up the phone to call a company, it's because I
| can't achieve what I want to on their website.
|
| These AI phone calls are as or more limited than the website.
|
| There is a use-case for voice AI - most of these demoes really
| miss the mark with "we're going to replace your call center".
|
| If founders had any idea how much performance matters in a call
| center, and how hard it is to achieve, they'd focus on a use case
| better served by voice AI.
___________________________________________________________________
(page generated 2025-07-11 23:02 UTC)