正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Autosana ( is an AI QA agent that tests iOS and Android apps like a real user. It plugs into your CI/CD, replacing flaky test scripts and manual QA, saving hours per release. Congrats on the launch, Uv Sundrani & @JSteinberg54132!

Y Combinator

1,619,400 subscribers

29,681 次观看 • 1 年前 •via X (Twitter)

科学技术新闻政治

Anya Rossi• Live Now

Private livecam show

11 条评论

Uv Sundrani 的头像

Uv Sundrani1 年前

Thanks YC !

Niftyessence 的头像

Niftyessence1 年前

Designed for effortless installation. Get:

John Ferrara 的头像

John Ferrara1 年前

@yuvansundrani Let’s go guys!

Steph from OpenVC 的头像

Steph from OpenVC1 年前

@yuvansundrani Nicely done!

nyx - r 的头像

nyx - r1 年前

Congrats on the launch! From the demo video on your site, it seems like you need to upload the ipa or apk. I’m guessing the navigation and AI don’t run locally, but you have a cloud-based AI system that handles navigation within the app? Also, could you let me know about the pricing for this service?

Harsha Gaddipati 的头像

Harsha Gaddipati1 年前

@yuvansundrani Les gooo!

nizzy 的头像

nizzy1 年前

@yuvansundrani w

Hassen 的头像

Hassen1 年前

@yuvansundrani shoutout startup shell!

Kenneth Onwuzolum 的头像

Kenneth Onwuzolum1 年前

@yuvansundrani Good job

Roger R 的头像

Roger R1 年前

@yuvansundrani Finally, a bot that actually gets the job done. No more flaky tests, just smooth sailing!

Sanskar Tiwari 的头像

Sanskar Tiwari1 年前

@yuvansundrani Congrats team autosana, we are building QA agent for web app at browsingbee .com

相关视频

Autosana (Autosana (YC S25)) is the end-to-end validation harness to close the loop with your coding agents, across iOS, Android, and web apps. Engineering teams using Autosana have cut QA time by over 80%, caught huge bugs, and increased shipping velocity. Congrats on the launch, Uv Sundrani and @jsteinberg54132!

Autosana (Autosana (YC S25)) is the end-to-end validation harness to close the loop with your coding agents, across iOS, Android, and web apps. Engineering teams using Autosana have cut QA time by over 80%, caught huge bugs, and increased shipping velocity. Congrats on the launch, Uv Sundrani and @jsteinberg54132!

Y Combinator

60,871 次观看 • 3 个月前

Mobile Operator is an AI agent that tests mobile apps by using them like a real user would. You send a build, and it sends back a full bug and UX report. Congrats on the launch, Filippo Facioni!

Mobile Operator is an AI agent that tests mobile apps by using them like a real user would. You send a build, and it sends back a full bug and UX report. Congrats on the launch, Filippo Facioni!

Y Combinator

22,155 次观看 • 1 年前

✨Spur (YC S24) is building an AI QA Engineer that helps users test their websites with natural language. Congrats on the launch, Sneha Sivakumar and Anushka!

✨Spur (YC S24) is building an AI QA Engineer that helps users test their websites with natural language. Congrats on the launch, Sneha Sivakumar and Anushka!

Y Combinator

36,249 次观看 • 1 年前

Is your Agent ready for real-world users? Learn how to run an evaluation using Agentverse’s Response QA Agent - a built-in tool that stress-tests your Agent with realistic queries and scores its performance. This is the first step to improving discoverability, trust, and performance. Run your first QA check and see how your Agent responds under pressure. Watch 👇

Is your Agent ready for real-world users? Learn how to run an evaluation using Agentverse’s Response QA Agent - a built-in tool that stress-tests your Agent with realistic queries and scores its performance. This is the first step to improving discoverability, trust, and performance. Run your first QA check and see how your Agent responds under pressure. Watch 👇

Agentverse by Fetch.ai

20,202 次观看 • 8 个月前

QualGent is an AI Quality Assurance agent for mobile that helps companies catch bugs and ship faster without hiring QA testers. One customer hit #3 in the Edu App Store using QualGent. Congrats on the launch, Shivam Agrawal and Aaron Yu!

QualGent is an AI Quality Assurance agent for mobile that helps companies catch bugs and ship faster without hiring QA testers. One customer hit #3 in the Edu App Store using QualGent. Congrats on the launch, Shivam Agrawal and Aaron Yu!

Y Combinator

27,335 次观看 • 1 年前

Propolis (Propolis) is automating away QA. Propolis deploys swarms of browser agents that test products like real users would, catching bugs before deployment with zero setup or maintenance required. Congrats on the launch, Marc Papazian and Matt!

Propolis (Propolis) is automating away QA. Propolis deploys swarms of browser agents that test products like real users would, catching bugs before deployment with zero setup or maintenance required. Congrats on the launch, Marc Papazian and Matt!

Y Combinator

18,405 次观看 • 1 年前

Anyone who’s worked in QA knows the gap. Requirements live in one place and tests live somewhere else. Every change creates another round of rewriting. Kane AI by TestMu AI (formerly LambdaTest) approaches that gap differently. Instead of forcing teams to rewrite tests in a new abstraction, it lets you describe intent in natural language and turns that into structured, executable tests that can be exported into your existing frameworks. During exploration, the most practical part wasn’t just test generation, it was how expressive the language layer is. Complex assertions, branching conditions, and validations can be described without switching mental modes into code, but the resulting output still integrates cleanly with real pipelines. There’s also a strong emphasis on API coverage and auto-bug detection, which matters when UI tests aren’t enough. Kane AI by TestMu AI (formerly LambdaTest) can detect failures during execution and attempt self-healing based on original intent, while still requiring review and validation from the team. It doesn’t pretend QA disappears. It acknowledges QA is hard, contextual, and constantly changing. That honesty makes it useful. If you’re dealing with test maintenance and curious how natural-language testing fits into real QA work, Kane AI by TestMu AI (formerly LambdaTest) is available to try. See it in action: TestMu AI

Anyone who’s worked in QA knows the gap. Requirements live in one place and tests live somewhere else. Every change creates another round of rewriting. Kane AI by TestMu AI (formerly LambdaTest) approaches that gap differently. Instead of forcing teams to rewrite tests in a new abstraction, it lets you describe intent in natural language and turns that into structured, executable tests that can be exported into your existing frameworks. During exploration, the most practical part wasn’t just test generation, it was how expressive the language layer is. Complex assertions, branching conditions, and validations can be described without switching mental modes into code, but the resulting output still integrates cleanly with real pipelines. There’s also a strong emphasis on API coverage and auto-bug detection, which matters when UI tests aren’t enough. Kane AI by TestMu AI (formerly LambdaTest) can detect failures during execution and attempt self-healing based on original intent, while still requiring review and validation from the team. It doesn’t pretend QA disappears. It acknowledges QA is hard, contextual, and constantly changing. That honesty makes it useful. If you’re dealing with test maintenance and curious how natural-language testing fits into real QA work, Kane AI by TestMu AI (formerly LambdaTest) is available to try. See it in action: TestMu AI

AI Highlight

61,494 次观看 • 5 个月前

Synthetic Society tests your product with AI-powered user simulations. Their agents mimic real users to catch bugs, bad UX, and edge cases. Ship faster, kill manual testing, and build with confidence. Congrats on the launch, Aaron Chew and kavan!

Synthetic Society tests your product with AI-powered user simulations. Their agents mimic real users to catch bugs, bad UX, and edge cases. Ship faster, kill manual testing, and build with confidence. Congrats on the launch, Aaron Chew and kavan!

Y Combinator

63,188 次观看 • 11 个月前

Arden (Arden AI) is building agents that automate the manual work of audit teams. They gather evidence, test controls, and write audit-ready workpapers, turning weeks of work into hours. Congrats on the launch, aryaman and David Lomelin!

Arden (Arden AI) is building agents that automate the manual work of audit teams. They gather evidence, test controls, and write audit-ready workpapers, turning weeks of work into hours. Congrats on the launch, aryaman and David Lomelin!

Y Combinator

18,310 次观看 • 2 个月前

Friday. 5:47 PM. Quick Claude session, small auth refactor. LGTM, merge, done. Monday, 10:00 AM. SSO is broken in production. Introducing Canary, the AI QA engineer that reads your codebase and catches broken user flows before production. Check it out at Congrats on the launch, Viswesh N G and team!

Friday. 5:47 PM. Quick Claude session, small auth refactor. LGTM, merge, done. Monday, 10:00 AM. SSO is broken in production. Introducing Canary, the AI QA engineer that reads your codebase and catches broken user flows before production. Check it out at Congrats on the launch, Viswesh N G and team!

Y Combinator

19,735 次观看 • 5 个月前

Operative (Operative) is an AI website creation agent that writes and tests code in your browser — so anyone can build and launch a working web app in minutes. No coding knowledge required. Congrats on the launch, Christopher Settles & Erik Quintanilla!

Operative (Operative) is an AI website creation agent that writes and tests code in your browser — so anyone can build and launch a working web app in minutes. No coding knowledge required. Congrats on the launch, Christopher Settles & Erik Quintanilla!

Y Combinator

40,738 次观看 • 1 年前

GStack is an open-source toolkit built by YC President & CEO Garry Tan that turns Claude Code into an AI engineering team — with skills for office hours, design, code review, QA, and browser testing. In this video, Garry walks through how GStack works, starting with Office Hours, a skill modeled after real YC partner sessions that pressure-tests your idea before you write a line of code. He demos it live, going from idea through adversarial review, design mockups, and automated QA in a single session.

GStack is an open-source toolkit built by YC President & CEO Garry Tan that turns Claude Code into an AI engineering team — with skills for office hours, design, code review, QA, and browser testing. In this video, Garry walks through how GStack works, starting with Office Hours, a skill modeled after real YC partner sessions that pressure-tests your idea before you write a line of code. He demos it live, going from idea through adversarial review, design mockups, and automated QA in a single session.

Y Combinator

923,495 次观看 • 3 个月前

Jazzberry (Jazzberry) is an AI bug finder that automatically tests your code when a pull request occurs to find and flag real bugs before they are merged. Congrats on the launch, Marco Dewey and Mateo Perez!

Jazzberry (Jazzberry) is an AI bug finder that automatically tests your code when a pull request occurs to find and flag real bugs before they are merged. Congrats on the launch, Marco Dewey and Mateo Perez!

Y Combinator

22,199 次观看 • 1 年前

Companies spend millions on events because relationships drive revenue, but converting attendees is still manual. Pavoot (Pavoot (YC P26)) is an AI agent that sources your top leads and turns events into personalized customer journeys. Congrats on the launch, Gohar Tamrazyan and Ana Yoon Faria de Lima!

Companies spend millions on events because relationships drive revenue, but converting attendees is still manual. Pavoot (Pavoot (YC P26)) is an AI agent that sources your top leads and turns events into personalized customer journeys. Congrats on the launch, Gohar Tamrazyan and Ana Yoon Faria de Lima!

Y Combinator

13,721 次观看 • 2 个月前

.Roark helps teams test and debug voice AI agents using real production calls. Replay past conversations, catch failures, and ensure your AI works before it goes live - no more manual testing. Congrats on the launch, James Zammit + Daniel Gauci!

.Roark helps teams test and debug voice AI agents using real production calls. Replay past conversations, catch failures, and ensure your AI works before it goes live - no more manual testing. Congrats on the launch, James Zammit + Daniel Gauci!

Y Combinator

19,503 次观看 • 1 年前

YouLearn (YouLearn) is an AI tutor personalized to each student. It turns your learning materials into concise notes, an AI tutor you can talk to, and personalized tests to help you study smarter. Congrats on the launch, David Yu, ach, and @KapadiaSoami!

YouLearn (YouLearn) is an AI tutor personalized to each student. It turns your learning materials into concise notes, an AI tutor you can talk to, and personalized tests to help you study smarter. Congrats on the launch, David Yu, ach, and @KapadiaSoami!

Y Combinator

157,608 次观看 • 1 年前

Firmware development is broken. Hardware companies spend months finding engineers, months reading datasheets, and months debugging. BootLoop built an AI agent that writes, tests, and debugs firmware on real hardware in minutes - not months. Congrats on the launch, Noah Pacik-Nelson & Chris Markus!

Firmware development is broken. Hardware companies spend months finding engineers, months reading datasheets, and months debugging. BootLoop built an AI agent that writes, tests, and debugs firmware on real hardware in minutes - not months. Congrats on the launch, Noah Pacik-Nelson & Chris Markus!

Y Combinator

16,758 次观看 • 1 年前

🚀 Meet KaneAI TestMu AI the next-generation AI-powered testing assistant for modern QA teams. KaneAI helps teams plan, author, and evolve end-to-end tests using natural language, turning requirements directly into executable code. Built for enterprise-scale complexity, it handles sophisticated workflows across all major programming languages and frameworks. QA teams often face hurdles like rapid development cycles, test case debt, and complex framework management. KaneAI addresses these challenges by: ✅ Generating structured test cases from text, JIRA, PDFs, images, audio, video, or spreadsheets ✅ Enabling complex testing workflows with natural language ✅ Supporting multi-language code exports and deep integrations with JIRA and GitHub ✅ Automating API and database testing, smart versioning, and auto bug detection ✅ Self-healing tests for UI changes and flexible manual interaction KaneAI augments QA teams, boosting productivity, reducing errors, and helping teams focus on outcomes rather than repetitive tasks. Learn more about KaneAI here: Connect with TestMu AI : LinkedIn: Twitter: #QA #TestAutomation #AI #GenAI #KaneAI #TestMu

🚀 Meet KaneAI TestMu AI the next-generation AI-powered testing assistant for modern QA teams. KaneAI helps teams plan, author, and evolve end-to-end tests using natural language, turning requirements directly into executable code. Built for enterprise-scale complexity, it handles sophisticated workflows across all major programming languages and frameworks. QA teams often face hurdles like rapid development cycles, test case debt, and complex framework management. KaneAI addresses these challenges by: ✅ Generating structured test cases from text, JIRA, PDFs, images, audio, video, or spreadsheets ✅ Enabling complex testing workflows with natural language ✅ Supporting multi-language code exports and deep integrations with JIRA and GitHub ✅ Automating API and database testing, smart versioning, and auto bug detection ✅ Self-healing tests for UI changes and flexible manual interaction KaneAI augments QA teams, boosting productivity, reducing errors, and helping teams focus on outcomes rather than repetitive tasks. Learn more about KaneAI here: Connect with TestMu AI : LinkedIn: Twitter: #QA #TestAutomation #AI #GenAI #KaneAI #TestMu

Mohini Shewale

16,809 次观看 • 6 个月前

I'm thrilled to announce Bug0 Studio - a self-serve, AI-native browser testing tool. We're in private beta. DM me your email for access + $250/mo in credits for 3 months. What you can do today: - Create tests from video recordings - Natural language test steps - Self-healing tests (adapts to UI changes) - Live browser preview - CI/CD integration (Vercel, Netlify, GitHub Actions) - Scheduled runs + reports via Slack, email, or PRs - Auto-extract emails (OTPs, magic links) - Team collaboration Most QA tools hide behind "contact us for demo." But I believe powerful QA shouldn't be gatekept behind sales calls and enterprise pricing. Help us build the most user-friendly and powerful AI QA tool that is open and accessible to all🙏 Today it's private beta. Soon, it's open to everyone.

I'm thrilled to announce Bug0 Studio - a self-serve, AI-native browser testing tool. We're in private beta. DM me your email for access + $250/mo in credits for 3 months. What you can do today: - Create tests from video recordings - Natural language test steps - Self-healing tests (adapts to UI changes) - Live browser preview - CI/CD integration (Vercel, Netlify, GitHub Actions) - Scheduled runs + reports via Slack, email, or PRs - Auto-extract emails (OTPs, magic links) - Team collaboration Most QA tools hide behind "contact us for demo." But I believe powerful QA shouldn't be gatekept behind sales calls and enterprise pricing. Help us build the most user-friendly and powerful AI QA tool that is open and accessible to all🙏 Today it's private beta. Soon, it's open to everyone.

Sandeep

114,592 次观看 • 6 个月前