Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

𝜃 ZeroEval helps you build reliable AI agents through evaluations that learn from their mistakes and get better over time. Congrats on the launch, seb and xtamales!

ycombinator's profile picture

Y Combinator

1,655,546 subscribers

23,938 görüntüleme • 1 yıl önce •via X (Twitter)

Bilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

15 Yorum

seb profil fotoğrafı
seb1 yıl önce

@ZeroEval @pirchavez video done by the amazing @AustinPeirson !! we had very tight deadline and he was able to deliver something that was truly aligned to the vision we had for the video. 1000/10 would recommend

Oleg Zaremba profil fotoğrafı
Oleg Zaremba1 yıl önce

@ZeroEval @sebcrossa @pirchavez Oh, I like this. Current evals feel like unit tests, which they are, and not fit for the AI age.

brett goldstein profil fotoğrafı
brett goldstein1 yıl önce

@ZeroEval @sebcrossa @pirchavez so good!

Srikar Dandamuraju profil fotoğrafı
Srikar Dandamuraju1 yıl önce

@ZeroEval @sebcrossa @pirchavez This is amazing! Super needed and useful

Umair profil fotoğrafı
Umair1 yıl önce

@ZeroEval @sebcrossa @pirchavez Good luck with the launch, fantastic work!

Matt Schkolnick profil fotoğrafı
Matt Schkolnick1 yıl önce

@ZeroEval @sebcrossa @pirchavez let’s goooo @sebcrossa & team! just the beginning 📈

Sacha Tedoldi profil fotoğrafı
Sacha Tedoldi1 yıl önce

@ZeroEval @sebcrossa @pirchavez The future of AI won’t be about perfection— It’ll be about who learns fastest. Congrats on the launch!

Santiago Yeomans profil fotoğrafı
Santiago Yeomans1 yıl önce

@ZeroEval @sebcrossa @pirchavez This is fire! Amazing work!

Himanshu Kumar profil fotoğrafı
Himanshu Kumar1 yıl önce

@ZeroEval @sebcrossa @pirchavez Impressive. Adaptive evaluation is key for robust AI development. This could significantly improve agent reliability long term.

Keven Crick profil fotoğrafı
Keven Crick1 yıl önce

@ZeroEval @sebcrossa @pirchavez The system prompts must be atrocious

ijon profil fotoğrafı
ijon1 yıl önce

@ZeroEval @sebcrossa @pirchavez zero mentioned

FlickBloom profil fotoğrafı
FlickBloom1 yıl önce

@ZeroEval @sebcrossa @pirchavez Love this focus on AI learning from mistakes; we're constantly improving our AI marketing agent, FlickBloom, to generate higher ROI for businesses. #flickbloom

Pedro Fernández profil fotoğrafı
Pedro Fernández1 yıl önce

@ZeroEval @sebcrossa @pirchavez We definitely need this

Juicy Lucy profil fotoğrafı
Juicy Lucy1 yıl önce

@ZeroEval @sebcrossa @pirchavez I'm curious, how do you think AI agents will change the web3 landscape?

Naveen profil fotoğrafı
Naveen1 yıl önce

@ZeroEval @sebcrossa @pirchavez Congratulations 🚀 @sebcrossa & team! Can't wait to try it out

Benzer Videolar

Lemma (Lemma) helps AI agents learn from real-world use, so they get better instead of breaking over time. They turn user feedback into automated prompt improvements, so teams can focus on shipping products. Congrats on the launch, Jerry Zhang & Cole Gawin!
1:42

Lemma (Lemma) helps AI agents learn from real-world use, so they get better instead of breaking over time. They turn user feedback into automated prompt improvements, so teams can focus on shipping products. Congrats on the launch, Jerry Zhang & Cole Gawin!

Y Combinator

23,608 görüntüleme • 1 yıl önce

Leeroo (Leeroo) builds trainable AI agents that keep learning—and get better at their job— every day. Congrats on the launch, Alireza Mohammadshahi, Majid, and Arshad!
2:08

Leeroo (Leeroo) builds trainable AI agents that keep learning—and get better at their job— every day. Congrats on the launch, Alireza Mohammadshahi, Majid, and Arshad!

Y Combinator

17,007 görüntüleme • 1 yıl önce

Theta (Theta) allows AI agents to learn from their mistakes in real-time. Their memory layer has already improved the accuracy of OpenAI Operator by 43% with 7x fewer steps taken. Congrats on the launch, Rayan Garg, tanmay sharma, and Gurvir Singh!
0:55

Theta (Theta) allows AI agents to learn from their mistakes in real-time. Their memory layer has already improved the accuracy of OpenAI Operator by 43% with 7x fewer steps taken. Congrats on the launch, Rayan Garg, tanmay sharma, and Gurvir Singh!

Y Combinator

52,880 görüntüleme • 1 yıl önce

Cascade (Cascade (YC W26)) builds custom evaluation infrastructure that learns from real production workflows. It helps teams deploy agents that improve on their data for their use cases - making them safer and more reliable. Congrats on the launch, Adam Alsayyad and Haluk!
1:21

Cascade (Cascade (YC W26)) builds custom evaluation infrastructure that learns from real production workflows. It helps teams deploy agents that improve on their data for their use cases - making them safer and more reliable. Congrats on the launch, Adam Alsayyad and Haluk!

Y Combinator

12,390 görüntüleme • 8 ay önce

flowscope deploys agents that learn and document how businesses operate. From there, their agents redesign and automate those processes, shipping AI into production on the company's existing systems. In days, not months. Congrats on the launch, Javier & Samuel Mirpuri!
1:04

flowscope deploys agents that learn and document how businesses operate. From there, their agents redesign and automate those processes, shipping AI into production on the company's existing systems. In days, not months. Congrats on the launch, Javier & Samuel Mirpuri!

Y Combinator

28,146 görüntüleme • 5 ay önce

Despite constant improvements, AI agents still struggle with complex, multi-step tasks. @Gulp_AI (YC W25) solves this with Osmosis: a framework that helps AI agents learn (similar to DeepSeek R1) in real time. Congrats on the launch Kasey Zhang + Andy!
1:33

Despite constant improvements, AI agents still struggle with complex, multi-step tasks. @Gulp_AI (YC W25) solves this with Osmosis: a framework that helps AI agents learn (similar to DeepSeek R1) in real time. Congrats on the launch Kasey Zhang + Andy!

Y Combinator

78,484 görüntüleme • 1 yıl önce

Pingo AI (@mypingoai) is a language learning app that helps users build fluency through real-life conversations with an AI tutor. Over 300,000 people already use Pingo to speak a new language. Congrats on the launch, @mrmukeee and @MorrietheMoosee!
1:00

Pingo AI (@mypingoai) is a language learning app that helps users build fluency through real-life conversations with an AI tutor. Over 300,000 people already use Pingo to speak a new language. Congrats on the launch, @mrmukeee and @MorrietheMoosee!

Y Combinator

23,929 görüntüleme • 1 yıl önce

Bear (Bear (YC F25)) helps companies get recommended by AI Agents like ChatGPT, Google AI Mode, Perplexity, Cursor, Claude Code, and more. It's already used by Browserbase, WisprFlow, and 200+ companies to grow traffic from AI Agents. Congrats on the launch, janak & sid!
0:35

Bear (Bear (YC F25)) helps companies get recommended by AI Agents like ChatGPT, Google AI Mode, Perplexity, Cursor, Claude Code, and more. It's already used by Browserbase, WisprFlow, and 200+ companies to grow traffic from AI Agents. Congrats on the launch, janak & sid!

Y Combinator

160,213 görüntüleme • 1 yıl önce

.OpenSpec (YC W26) is building the open-source spec framework for coding agents. It helps devs generate software specifications that evolve with their codebase, making their agents reliable enough to take on larger, more complex work. Congrats on the launch, Tabish!
2:14

.OpenSpec (YC W26) is building the open-source spec framework for coding agents. It helps devs generate software specifications that evolve with their codebase, making their agents reliable enough to take on larger, more complex work. Congrats on the launch, Tabish!

Y Combinator

26,577 görüntüleme • 8 ay önce

Hyperspell (Hyperspell (YC F25)) gives AI agents memory. It connects to Slack, Gmail, Notion, and Drive, so agents get context and remember what they learn. Congrats @conor_ai and Manu Ebert on the launch!
1:32

Hyperspell (Hyperspell (YC F25)) gives AI agents memory. It connects to Slack, Gmail, Notion, and Drive, so agents get context and remember what they learn. Congrats @conor_ai and Manu Ebert on the launch!

Y Combinator

74,194 görüntüleme • 1 yıl önce

ANTHROPIC JUST INTRODUCED A FEATURE THAT LETS CLAUDE REVIEW AND IMPROVE ITS OWN WORK OVER TIME. The new “Dreaming” workflow helps agents learn from mistakes, refine outputs in the background, and improve task completion without changing the model itself.
8:36

ANTHROPIC JUST INTRODUCED A FEATURE THAT LETS CLAUDE REVIEW AND IMPROVE ITS OWN WORK OVER TIME. The new “Dreaming” workflow helps agents learn from mistakes, refine outputs in the background, and improve task completion without changing the model itself.

0xMarioNawfal

53,495 görüntüleme • 6 ay önce

Congrats! Today, your team gets stronger, faster, bigger, and better. Reintroducing - the AI work platform where people and agents work together as one team. You set the goals, and your agents get the work DONE: research, tickets, reports, follow-ups, budget tracking, and so (so, so) much more. ✅ Easy to build ✅ Always on ✅ Fully under your control And we're just getting started. Over the coming weeks, we'll walk you through new ideas on how to leverage agents in your work, build-along sessions, and handy tips from our agents experts.
0:40

Congrats! Today, your team gets stronger, faster, bigger, and better. Reintroducing - the AI work platform where people and agents work together as one team. You set the goals, and your agents get the work DONE: research, tickets, reports, follow-ups, budget tracking, and so (so, so) much more. ✅ Easy to build ✅ Always on ✅ Fully under your control And we're just getting started. Over the coming weeks, we'll walk you through new ideas on how to leverage agents in your work, build-along sessions, and handy tips from our agents experts.

monday.com

27,535 görüntüleme • 6 ay önce

Notte (Notte) is a platform to build and deploy web AI agents that don’t break. It turns messy, repetitive web tasks into reliable, self-healing workflows so businesses can confidently scale automation. Congrats on the launch, Andrea Pinto & Lucas Giordano!
1:22

Notte (Notte) is a platform to build and deploy web AI agents that don’t break. It turns messy, repetitive web tasks into reliable, self-healing workflows so businesses can confidently scale automation. Congrats on the launch, Andrea Pinto & Lucas Giordano!

Y Combinator

95,238 görüntüleme • 1 yıl önce

Clodo (CLODO) is the AI Assistant for Real Estate Agents. It helps agents remember and follow up with all their leads. Dominate your follow-up, dominate your market. Congrats on the launch, Sid Rajaram, Arnav Verma, and Rithvik Chuppala!
1:29

Clodo (CLODO) is the AI Assistant for Real Estate Agents. It helps agents remember and follow up with all their leads. Dominate your follow-up, dominate your market. Congrats on the launch, Sid Rajaram, Arnav Verma, and Rithvik Chuppala!

Y Combinator

31,833 görüntüleme • 1 yıl önce

.Armature helps companies monitor and optimize how AI agents experience their products. It runs real agent workflows and improves your MCP or CLI. Reinventing the Agent Experience! Congrats on the launch, Theo Otz and Louis Scremin!
1:09

.Armature helps companies monitor and optimize how AI agents experience their products. It runs real agent workflows and improves your MCP or CLI. Reinventing the Agent Experience! Congrats on the launch, Theo Otz and Louis Scremin!

Y Combinator

11,785 görüntüleme • 5 ay önce

Vellum is a platform for building and managing AI agents so that non-technical teams can create reliable, task-specific agents by simply describing their goal in natural language. With over 100 native integrations, Vellum lets teams automate insights, CRM updates, renewal risk, meeting briefs, and so much more. Congrats to Akash Sharma and team on the launch!
2:15

Vellum is a platform for building and managing AI agents so that non-technical teams can create reliable, task-specific agents by simply describing their goal in natural language. With over 100 native integrations, Vellum lets teams automate insights, CRM updates, renewal risk, meeting briefs, and so much more. Congrats to Akash Sharma and team on the launch!

Y Combinator

25,613 görüntüleme • 9 ay önce

Modern (Modern) is building the AI-native operating system for IT, with secure agents that automate help desk, access, devices, security, and on/off-boarding end-to-end. Congrats on the launch, Seb Poole & Aleksandar Tomovski!
1:57

Modern (Modern) is building the AI-native operating system for IT, with secure agents that automate help desk, access, devices, security, and on/off-boarding end-to-end. Congrats on the launch, Seb Poole & Aleksandar Tomovski!

Y Combinator

30,022 görüntüleme • 5 ay önce

.Corvera helps retail brands increase profits 40% with AI agents that handle their day-to-day ops. Retail brands are drowning in monotonous tasks. That ends now. Congrats on the launch Chris Kong, Dirk Breeuwer, and Matthew Collins!
1:21

.Corvera helps retail brands increase profits 40% with AI agents that handle their day-to-day ops. Retail brands are drowning in monotonous tasks. That ends now. Congrats on the launch Chris Kong, Dirk Breeuwer, and Matthew Collins!

Y Combinator

16,570 görüntüleme • 9 ay önce

Polymorph helps consumer & self-serve apps deepen engagement: they build live user profiles from in-app behavior and send custom messages at the right time and channel. Early customers already see 3.6x better reactivation rates. Congrats on the launch, andrew, David Nie, and Manas!
0:59

Polymorph helps consumer & self-serve apps deepen engagement: they build live user profiles from in-app behavior and send custom messages at the right time and channel. Early customers already see 3.6x better reactivation rates. Congrats on the launch, andrew, David Nie, and Manas!

Y Combinator

14,105 görüntüleme • 8 ay önce