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。

AI is transforming software development, but more code means more pull requests, more edge cases, and more QA pressure on engineering teams. Tusk, a Y Combinator startup, catches bugs that slip past both AI agents and humans using AI-enabled tests based on real production traffic. Built on Amazon Bedrock,... show more

AWS Startups

266,270 subscribers

16,181,543 次观看 • 2 个月前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Sennu AI (Sennu AI) is an AI code reviewer that reviews Salesforce pull requests like a senior architect would. It uses Salesforce best practices and your full org context to catch issues early and help dev teams merge code faster.

Sennu AI (Sennu AI) is an AI code reviewer that reviews Salesforce pull requests like a senior architect would. It uses Salesforce best practices and your full org context to catch issues early and help dev teams merge code faster.

Y Combinator

18,282 次观看 • 6 个月前

.@RoarkAnalytics 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!

.@RoarkAnalytics 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

19,468 次观看 • 1 年前

YC W24's Tusk is an AI agent that generates unit/integration tests for PRs. Tusk sits in the CI to suggest happy path and edge case tests. Engineering teams use it to prevent bugs while increasing test coverage.

YC W24's Tusk is an AI agent that generates unit/integration tests for PRs. Tusk sits in the CI to suggest happy path and edge case tests. Engineering teams use it to prevent bugs while increasing test coverage.

Y Combinator

21,898 次观看 • 1 年前

Teams are cooking some code. 🧑‍💻 Smart Contracts, APIs, frontend, AI agents. It is possible to develop products on chain under 24 hours. Complete products. Especially with the age of AI, everything is faster, and anyone with some prompting skills and an idea can start building. The night will be long. Time to build more!

Teams are cooking some code. 🧑‍💻 Smart Contracts, APIs, frontend, AI agents. It is possible to develop products on chain under 24 hours. Complete products. Especially with the age of AI, everything is faster, and anyone with some prompting skills and an idea can start building. The night will be long. Time to build more!

Robert Sasu | dev/acc

17,558 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 • 4 个月前

Mark Zuckerberg says, Meta is betting that within a year, AI will take over much of the model development work. teams are already testing AI in narrow tasks like feed and ads ranking, but the real focus is on building AI that can help build better AI.

Mark Zuckerberg says, Meta is betting that within a year, AI will take over much of the model development work. teams are already testing AI in narrow tasks like feed and ads ranking, but the real focus is on building AI that can help build better AI.

Haider.

70,103 次观看 • 1 年前

Stably (Stably AI) helps dev teams merge code 10× faster by auto-writing, running, and self-healing Playwright tests in minutes, eliminating flaky suites and hidden bugs. Congrats on the launch @jinjingliang, @nparker2450, and Raines!

Stably (Stably AI) helps dev teams merge code 10× faster by auto-writing, running, and self-healing Playwright tests in minutes, eliminating flaky suites and hidden bugs. Congrats on the launch @jinjingliang, @nparker2450, and Raines!

Y Combinator

20,066 次观看 • 11 个月前

Docket (Docket) is building AI agents for QA testing — enabling teams to write end-to-end tests in plain English. Congrats on the launch, nh and Boris Skurikhin!

Docket (Docket) is building AI agents for QA testing — enabling teams to write end-to-end tests in plain English. Congrats on the launch, nh and Boris Skurikhin!

Y Combinator

25,848 次观看 • 1 年前

Most AI agent failures are invisible until users complain. Sentrial detects loops, hallucinations, and user frustrations in real time and helps engineering teams diagnose and fix issues fast. Production monitoring built for AI agents. Congrats on the launch Neel Sharma and Anay Shukla!

Most AI agent failures are invisible until users complain. Sentrial detects loops, hallucinations, and user frustrations in real time and helps engineering teams diagnose and fix issues fast. Production monitoring built for AI agents. Congrats on the launch Neel Sharma and Anay Shukla!

Y Combinator

37,619 次观看 • 4 个月前

What are the second-order impacts on AI being widespread for coding? More code generated is the first order... second order is more PRs, more builds... and more bugs! From Tomas Reimers

What are the second-order impacts on AI being widespread for coding? More code generated is the first order... second order is more PRs, more builds... and more bugs! From Tomas Reimers

Gergely Orosz

23,679 次观看 • 1 年前

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

Official: Amazon just launched Nova Act - an AI agent platform on AWS for building reliable agents that handle browser workflows at scale. Agents that actually work in production - filling forms, running QA tests, handling repetitive UI workflows that waste hours every day. Thanks to Amazon for the early access and sponsoring this post. More details 👇 1/6

Official: Amazon just launched Nova Act - an AI agent platform on AWS for building reliable agents that handle browser workflows at scale. Agents that actually work in production - filling forms, running QA tests, handling repetitive UI workflows that waste hours every day. Thanks to Amazon for the early access and sponsoring this post. More details 👇 1/6

AshutoshShrivastava

48,322 次观看 • 6 个月前

We’ve been working on an AI that actually does things. Easier to install, way more powerful, built for teams and infinite memory.

We’ve been working on an AI that actually does things. Easier to install, way more powerful, built for teams and infinite memory.

Carlos Mendez

193,160 次观看 • 4 个月前

Building trusted AI agents is easier on Hedera. The open-source Hedera AI Agent Kit lets developers create AI-powered applications that understand natural language and perform real on-chain actions. Learn more: Get started:

Building trusted AI agents is easier on Hedera. The open-source Hedera AI Agent Kit lets developers create AI-powered applications that understand natural language and perform real on-chain actions. Learn more: Get started:

Hedera

17,756 次观看 • 6 天前

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!

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 次观看 • 5 个月前

Excited to announce that Entelligence AI has raised $5M to redefine how engineering teams ship! Today AI writes code faster than ever. But shipping quality products as a team? That's still a challenge. Launching Ask Ellie. An AI agent that triages questions across posthog, sentry, linear, github and more to answer anything about performance, ownership, blockers, and more without jumping between tools. Ellie also beats benchmarks against other code reviewers in catching real issues while also preventing security issues and keeping docs current. Round led Mayfield and Correlation Ventures with support from Embedding VC, DGVentures and an incredible group of leaders from GitLab, Nvidia, Auth0, Zapier, Cisco, Calm, and more!

Excited to announce that Entelligence AI has raised $5M to redefine how engineering teams ship! Today AI writes code faster than ever. But shipping quality products as a team? That's still a challenge. Launching Ask Ellie. An AI agent that triages questions across posthog, sentry, linear, github and more to answer anything about performance, ownership, blockers, and more without jumping between tools. Ellie also beats benchmarks against other code reviewers in catching real issues while also preventing security issues and keeping docs current. Round led Mayfield and Correlation Ventures with support from Embedding VC, DGVentures and an incredible group of leaders from GitLab, Nvidia, Auth0, Zapier, Cisco, Calm, and more!

Aiswarya Sankar

102,890 次观看 • 5 个月前

Jules is an experimental AI-powered code agent designed to help developers get things done. 🛠️ Using Gemini 2.0, it seamlessly integrates with @GitHub and allows you to offload bug fixes and other time-consuming tasks - so you can focus on more critical issues. ↓

Jules is an experimental AI-powered code agent designed to help developers get things done. 🛠️ Using Gemini 2.0, it seamlessly integrates with @GitHub and allows you to offload bug fixes and other time-consuming tasks - so you can focus on more critical issues. ↓

Google DeepMind

146,129 次观看 • 1 年前