Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

A demo of a practical use case for Jev: routing customer inquiries on a live call center line Fun voice AI project built with LiveKit It's really incredible to see how quickly Jev can act on a live call and bring in real-time AI judgment on everything the caller says

rahat

17,052 subscribers

16,925 Aufrufe • vor 5 Tagen •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

24 Kommentare

Profilbild von rahat

rahatvor 5 Tagen

Would love your throughts @codeSTACKr I enjoyed your talk at Commit Your Code in dallas and thought of this when Jev released

Profilbild von Vishal Singh 🥑

Vishal Singh 🥑vor 5 Tagen

@livekit this is a great use case using jev + livekit 💙

Profilbild von rahat

rahatvor 5 Tagen

@livekit Thanks Vishal!

Profilbild von Ali

Alivor 5 Tagen

@livekit Beard lookin fresh

Profilbild von rahat

rahatvor 5 Tagen

@livekit Hahahahah hopefully the demo was good too

Profilbild von Sim Audience

Sim Audiencevor 5 Tagen

@livekit cool use case, added to community demos

Profilbild von rahat

rahatvor 5 Tagen

@livekit Thanks for the add!!

Profilbild von SushiKev

SushiKevvor 5 Tagen

@livekit Cool stuff!!!

Profilbild von rahat

rahatvor 5 Tagen

@livekit Appreciate you kev :)

Profilbild von 0xShikhar⚡️

0xShikhar⚡️vor 2 Tagen

@livekit build something on JEV last week, would love to know ur feedback 👀

Profilbild von rahat

rahatvor 2 Tagen

@livekit Just glanced and looks very cool! I will take a closer look later today

Profilbild von 0xShikhar⚡️

0xShikhar⚡️vor 2 Tagen

@livekit thanks man, appreciate it. keen to hear what you think.

Profilbild von Danny Thompson

Danny Thompsonvor 5 Tagen

@livekit This is exactly how I have been thinking about it! great stuff Rahat!

Profilbild von rahat

rahatvor 5 Tagen

@livekit Thanks Danny!

Profilbild von rahat

rahatvor 5 Tagen

Here's the demo code:

Profilbild von ahmad

ahmadvor 5 Tagen

@livekit Content Rahat back in the game

Profilbild von rahat

rahatvor 5 Tagen

@livekit we baaaaack

Profilbild von Spiroo

Spiroovor 5 Tagen

@livekit it is actualy impressive to see the frustration tracking move in real time during a call

Profilbild von Crypto Kɑrhen

Crypto Kɑrhenvor 5 Tagen

@livekit latency must be wild on a live call line though

Profilbild von rahat

rahatvor 5 Tagen

@livekit 200 ms ser the start of the video is a live demo the livekit/jev combo is crazy

Profilbild von Raza

Razavor 5 Tagen

@livekit Is this video recorded in Texas?

Profilbild von rahat

rahatvor 5 Tagen

@livekit Howdy

Profilbild von Carl D

Carl Dvor 5 Tagen

@livekit Now route all my spam calls to "waste their time for as long as possible"

Profilbild von rahat

rahatvor 5 Tagen

@livekit Ayyyy

Ähnliche Videos

We built a live multilingual, multi-person video call with Gemini 3.5 Live Translate on LiveKit. Everyone picks their language, speaks naturally, and hears each other in real time in their language of choice. Watch the demo and check out the open source repo:

We built a live multilingual, multi-person video call with Gemini 3.5 Live Translate on LiveKit. Everyone picks their language, speaks naturally, and hears each other in real time in their language of choice. Watch the demo and check out the open source repo:

LiveKit

21,636 Aufrufe • vor 3 Monaten

I got access to Jev. It's incredible. The horizon of what's possible just moved. LLM-era software had a real gap and project liks this was simply impossible. Introducing the first real-time AI-first calculator - no CPU load - instant responses - costs pennies - jev based

I got access to Jev. It's incredible. The horizon of what's possible just moved. LLM-era software had a real gap and project liks this was simply impossible. Introducing the first real-time AI-first calculator - no CPU load - instant responses - costs pennies - jev based

Dmitriy Kovalenko

226,474 Aufrufe • vor 12 Tagen

I was also looking into how we can integrate Jev into a real hardware and I built a custom firmware for my keyboard that predicts and highljghts the next key using Jev. Mostly real time. This is not a simple dummy 2kb model that lives in the board. In my project Jev gets context of the current active app on a screen so it can suggest actual vim commands completion! For real. And a real word endings or even phrases. lmao this experiments are getting out of hand this quite cool

I was also looking into how we can integrate Jev into a real hardware and I built a custom firmware for my keyboard that predicts and highljghts the next key using Jev. Mostly real time. This is not a simple dummy 2kb model that lives in the board. In my project Jev gets context of the current active app on a screen so it can suggest actual vim commands completion! For real. And a real word endings or even phrases. lmao this experiments are getting out of hand this quite cool

Dmitriy Kovalenko

56,086 Aufrufe • vor 11 Tagen

A real call of our AI making a reservation. Use bland today — live on our website. No special access needed.

A real call of our AI making a reservation. Use bland today — live on our website. No special access needed.

Bland

42,573 Aufrufe • vor 3 Jahren

10 Jev use cases a marketer can see: 1. Lead scoring - You get 100 new leads overnight. Jev can score which ones are most likely to buy. Sales gets the best ones first. 2. Email prioritization - Drop hundreds of emails into it. Jev can score priority, spam, category, and reply probability. 3. Support routing - A client reports a billing issue, another one has an API problem. Jev can instantly decide where each ticket should go. 4. Customer intent - A user visits pricing three times this week. Jev can score how likely they are to upgrade. 5. Marketplace matching - Someone explains exactly what service they need. Jev can score which provider is the closest match. 6. Lead qualification - A prospect fills out your website form. Jev can decide between sales, self-serve, or nurture. 7. Content clipping- Give it a 60-minute podcast transcript. Jev can score the moments most worth clipping. 8. Browser tasks - Tell an agent to find the right hotel. Jev can help choose the best one in 8 seconds. 9. Human vs AI routing - Jev can decide whether it goes to AI or a human. 10. Workflow decisions - Most workflows eventually hit the same question: What should happen next? That's probably the best place to use Jev.

10 Jev use cases a marketer can see: 1. Lead scoring - You get 100 new leads overnight. Jev can score which ones are most likely to buy. Sales gets the best ones first. 2. Email prioritization - Drop hundreds of emails into it. Jev can score priority, spam, category, and reply probability. 3. Support routing - A client reports a billing issue, another one has an API problem. Jev can instantly decide where each ticket should go. 4. Customer intent - A user visits pricing three times this week. Jev can score how likely they are to upgrade. 5. Marketplace matching - Someone explains exactly what service they need. Jev can score which provider is the closest match. 6. Lead qualification - A prospect fills out your website form. Jev can decide between sales, self-serve, or nurture. 7. Content clipping- Give it a 60-minute podcast transcript. Jev can score the moments most worth clipping. 8. Browser tasks - Tell an agent to find the right hotel. Jev can help choose the best one in 8 seconds. 9. Human vs AI routing - Jev can decide whether it goes to AI or a human. 10. Workflow decisions - Most workflows eventually hit the same question: What should happen next? That's probably the best place to use Jev.

Yum⋆₊˚

130,108 Aufrufe • vor 11 Tagen

Introducing Lemon Slice Live: the first real-time audio-video AI model Anyone can video chat with any character by just uploading a single photo. Every pixel on the screen is rendered at 25fps in real-time by a transformer model. Here’s how we built it + a live demo! 👇

Introducing Lemon Slice Live: the first real-time audio-video AI model Anyone can video chat with any character by just uploading a single photo. Every pixel on the screen is rendered at 25fps in real-time by a transformer model. Here’s how we built it + a live demo! 👇

LemonSlice

171,119 Aufrufe • vor 1 Jahr

Voice cloning is now available on LiveKit Inference. We’re launching with and Cartesia. Clone a voice once and use it across multiple TTS providers, with automatic fallback to the same voice if a provider fails mid-call. Free to create and available on all paid plans today.

Voice cloning is now available on LiveKit Inference. We’re launching with and Cartesia. Clone a voice once and use it across multiple TTS providers, with automatic fallback to the same voice if a provider fails mid-call. Free to create and available on all paid plans today.

LiveKit

11,443 Aufrufe • vor 4 Monaten

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!

sharing an easy way to test DJev (Diffusion Gemma Jev), the next evolution of the incredible jev concept and fully open sourced (model, code, api...) imagine jev but it also has: - native image-input support - native image as options!! - real-time video streaming input - as fast as jev (not with images, 600ms) - same price as jev, but can get even cheaper - using Diffusion Gemma adapted - we are seeing on-par performance but happy to have external validation! It is a research preview made for fun, so don't expect stability and the awesome scaling as jev team has delivered! this was a weekend project :) have fun!

David Villalón

42,739 Aufrufe • vor 11 Tagen

Introducing newsliquid-3.0-pro Building on the System One decision paradigm behind TypeSafe’s Jev TypeSafe AI , a specialist model purpose-built for real-time market news triage and conditional impact assessment.

Introducing newsliquid-3.0-pro Building on the System One decision paradigm behind TypeSafe’s Jev TypeSafe AI , a specialist model purpose-built for real-time market news triage and conditional impact assessment.

Newsliquid

28,283 Aufrufe • vor 6 Tagen

I've wanted this for ages and it's finally possible now with Jev by TypeSafe AI Imagine Mobbin, but it grabs fresh flows for whatever you’re looking for Browser use has always been to slow to pull this off properly. Jev + browser use are insanely quick now 🫪 I had a lot of fun tinkering on this yesterday

I've wanted this for ages and it's finally possible now with Jev by TypeSafe AI Imagine Mobbin, but it grabs fresh flows for whatever you’re looking for Browser use has always been to slow to pull this off properly. Jev + browser use are insanely quick now 🫪 I had a lot of fun tinkering on this yesterday

omar ✌️

50,029 Aufrufe • vor 12 Tagen

I built a browser extension with Jev TypeSafe AI that can hide/collapse posts on X based on natural language. It's so fast that it's not noticeable and insanely cheap...this must be the future of "ad blockers" and content firewalls.

I built a browser extension with Jev TypeSafe AI that can hide/collapse posts on X based on natural language. It's so fast that it's not noticeable and insanely cheap...this must be the future of "ad blockers" and content firewalls.

Marcel Pociot 🧪

85,778 Aufrufe • vor 13 Tagen

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build

this is f*cking gold 20 GitHub repos with 500K+ combined stars that will level up your JEV workflow AGENTS > jev-ultrafast: Jev picks every click and DOM target, a small LLM only types > hermes-jev-skills: routing, memory, compaction and skill picks in one pack > typesafe-computer-use: OCR reads your Mac screen, Jev picks the next click MEMORY > fast-jev-compaction: scores every tool call keep, truncate or drop instead of summarizing > jevmem: project memory for Claude Code, Cursor and Codex, updated every turn > jev-second-brain: your Obsidian vault, Jev judges which notes duplicate, revise or contradict SAFETY > jev-guard: a gate before every tool call, Jev scores the risk, you set allow, ask or deny TOOLS > skills: the official TypeSafe skill for Claude Code and Codex > system-one-adapter-python: dry-run your questions on an ordinary LLM before you burn a Jev key > jev-mcp: claim checks, screening and ranking as MCP tools > typesafe-mcp: plug Jev into any MCP client > json-render: Vercel's generative UI, where Jev picks the components OPEN MODELS > SemIf-OpenJev: semantic ifs from frozen open models kev: Jev-like models on Qwen that run on your MacBook > laya-mlx: the Laya decision engine on Apple silicon > clm: an open System One model with Choice, Noul and Score > jevlike: train your own Jev-like model TRADING > jev-trader: one buy or sell decision per Monad block START HERE > awesome-jev: the biggest map of everything built on Jev > awesome-jev-by-typesafe: use cases, patterns and starter code bookmark it before your next build

NO1ennn

18,445 Aufrufe • vor 2 Tagen

🚨 Big news: HighLevel received early alpha access to OpenAI's GPT-Live-1, and we’ve been putting it to the test in Voice AI. We analyzed 4+ million calls to small businesses. Only 47% were answered. That means more than half the time, that customer calls the next business on the list. That’s the problem we built Voice AI in HighLevel to solve. 🤖 Real conversations. 📅 Real bookings. 📞 No missed calls. Watch it handle a dental emergency, a same-day flower delivery and a customer switching to Spanish mid-call... all without missing a beat. The future of business communication isn’t just about AI that can talk. It’s about AI that can actually have the conversation.

🚨 Big news: HighLevel received early alpha access to OpenAI's GPT-Live-1, and we’ve been putting it to the test in Voice AI. We analyzed 4+ million calls to small businesses. Only 47% were answered. That means more than half the time, that customer calls the next business on the list. That’s the problem we built Voice AI in HighLevel to solve. 🤖 Real conversations. 📅 Real bookings. 📞 No missed calls. Watch it handle a dental emergency, a same-day flower delivery and a customer switching to Spanish mid-call... all without missing a beat. The future of business communication isn’t just about AI that can talk. It’s about AI that can actually have the conversation.

HighLevel

16,674 Aufrufe • vor 20 Tagen

Meet Orin! 🟠 Orin is a voice-enabled AI companion built for conversation. You open a chat, say what's on your mind, and get a thoughtful reply. If talking out loud is easier, you can start a voice call in the same thread. ElevenLabs powers Orin for real-time voice, OpenAI for text, and a layered prompt system across five personalities — Warm, Curious, Playful, Calm, and Direct. Spent the past couple of weeks building this from the ground up, and it's live now. Say hello at orin[.]chat, and star the repo on GitHub!

Meet Orin! 🟠 Orin is a voice-enabled AI companion built for conversation. You open a chat, say what's on your mind, and get a thoughtful reply. If talking out loud is easier, you can start a voice call in the same thread. ElevenLabs powers Orin for real-time voice, OpenAI for text, and a layered prompt system across five personalities — Warm, Curious, Playful, Calm, and Direct. Spent the past couple of weeks building this from the ground up, and it's live now. Say hello at orin[.]chat, and star the repo on GitHub!

victor

137,880 Aufrufe • vor 2 Monaten

Today I built this voice agent while on a call with it Introducing /this-needs-a-call - it's a slash command to start a phone call - grill or be grilled by the voice agent in realtime - your coding agent listens in on the call via MCP and works while you talk for hours

Today I built this voice agent while on a call with it Introducing /this-needs-a-call - it's a slash command to start a phone call - grill or be grilled by the voice agent in realtime - your coding agent listens in on the call via MCP and works while you talk for hours

jacob paris ▲

32,463 Aufrufe • vor 3 Monaten

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇

Everyone is talking about JEV. Almost nobody knows how to actually use it. These 10 GitHub repos fix that. 1. browser-use/jev-ultrafast (~16.6k⭐) Jev for browser agents: pick the next action without another expensive LLM call. 2. tamaratran/fast-jev-compaction (~6.5k⭐) Uses Jev to decide what context still matters and what can be dropped. 3. TheoLeeCJ/SemIf (~4k⭐) Open-source Jev-style decision making you can run locally. 4. jarrodwatts/jev-trader (~2.1k⭐) Real-time trading loop where Jev decides buy, sell or wait. 5. kerpopule/hermes-jev-skills (~670⭐) Jev routing, memory, compaction and skill selection for AI agents. 6. devagrawal09/jev-review (~570⭐) Code review powered by Jev decisions instead of one giant prompt. 7. thruwire/foreman (~520⭐) Jev as a supervisor for coding agents: continue, retry, verify or stop. 8. superagents-lab/jev-search (~400⭐) Jev decides where and how an agent should search. 9. droidrun/mobile-jev (~350⭐) Jev for Android agents choosing the next app action. 10. gargpratyush/jev-router (~340⭐) Routes agent tasks to the right model with Jev. After looking through these, the pattern is pretty clear: LLMs generate. Agents execute. JEV decides. That decision layer is what most agent stacks are still missing. Save this if you want to integrate Jev into your workflow👇

unicode

20,745 Aufrufe • vor 7 Tagen

It's Revia Demo Day! Let's see how Revia, our AI call assistant, can save the day. Calling government agencies with their endless menus and not-so-smart AI can be frustrating. Today, we'll see Revia book a DMV driving test, turning a frustrating task into a breeze! 🧵(🔊on)

It's Revia Demo Day! Let's see how Revia, our AI call assistant, can save the day. Calling government agencies with their endless menus and not-so-smart AI can be frustrating. Today, we'll see Revia book a DMV driving test, turning a frustrating task into a breeze! 🧵(🔊on)

Shaun.AGI

15,143 Aufrufe • vor 2 Jahren

The speed and cost is going to enable use cases that haven't been possible before. Here's a quick demo of live decisions of what slide to pull up as I'm speaking, powered by TypeSafe AI Jev. Also, sorry for the sniffling. I have a bit of a cold.

The speed and cost is going to enable use cases that haven't been possible before. Here's a quick demo of live decisions of what slide to pull up as I'm speaking, powered by TypeSafe AI Jev. Also, sorry for the sniffling. I have a bit of a cold.

Zain Hoda

59,968 Aufrufe • vor 13 Tagen

I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations. I hooked it up to web search, wikipedia, weather, todoist and home assistant. Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!

I built a chat bot with jev, no LLM at all! Responses are instant, no hallucinations. I hooked it up to web search, wikipedia, weather, todoist and home assistant. Jev decides what tool to call and what args to use based on the prompt. Instant answers cite sources as well!

CJ (Coding Garden)

114,643 Aufrufe • vor 13 Tagen

Gemini 3.1 Flash Live launched a few days ago, and it's a pretty incredible real-time model. We're getting very close to everyone having their own JARVIS assistant. A small demo of a Todoist voice assistant built with the new model.

Gemini 3.1 Flash Live launched a few days ago, and it's a pretty incredible real-time model. We're getting very close to everyone having their own JARVIS assistant. A small demo of a Todoist voice assistant built with the new model.

Amir Salihefendić

35,685 Aufrufe • vor 6 Monaten