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。

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

1,631,724 subscribers

37,962 次观看 • 6 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

AI agents fail silently in production: tool failures, hallucinated outputs, incomplete workflows, and long traces hide the real issue. Moda (moda) is monitoring & reliability built for AI agents, helping you catch issues before users do. Congrats on the launch, pranav & mo!

AI agents fail silently in production: tool failures, hallucinated outputs, incomplete workflows, and long traces hide the real issue. Moda (moda) is monitoring & reliability built for AI agents, helping you catch issues before users do. Congrats on the launch, pranav & mo!

Y Combinator

30,287 次观看 • 5 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

19,516 次观看 • 1 年前

The Context Company (The Context Company) is redefining observability for AI agents. Catch silent failures like bad tool calls, infinite loops, and hallucinations in just 10 lines of code. Congrats on the launch, Rohil Agarwal & arman!

The Context Company (The Context Company) is redefining observability for AI agents. Catch silent failures like bad tool calls, infinite loops, and hallucinations in just 10 lines of code. Congrats on the launch, Rohil Agarwal & arman!

Y Combinator

49,529 次观看 • 9 个月前

Fulcrum (Muzafar Bhai) is an agentic debugger for AI systems. It helps developers fix their RL environments and improve their agents. Congrats on the launch, Uzay and @kaivuhariharan!

Fulcrum (Muzafar Bhai) is an agentic debugger for AI systems. It helps developers fix their RL environments and improve their agents. Congrats on the launch, Uzay and @kaivuhariharan!

Y Combinator

14,892 次观看 • 11 个月前

.@SonarlyDev is your AI engineer for production. Most teams don’t trust their production alerts anymore because of the noise. They end up relying on user feedback (too late) or manual digging (too slow). Sonarly connects to your monitoring stack (like Sentry or Datadog) and your user feedback channels, automatically triages all these signals, investigates root causes, and ships a proposed fix. Congrats on the launch Dimittri and Alexandre Klobb!

.@SonarlyDev is your AI engineer for production. Most teams don’t trust their production alerts anymore because of the noise. They end up relying on user feedback (too late) or manual digging (too slow). Sonarly connects to your monitoring stack (like Sentry or Datadog) and your user feedback channels, automatically triages all these signals, investigates root causes, and ships a proposed fix. Congrats on the launch Dimittri and Alexandre Klobb!

Y Combinator

16,396 次观看 • 5 个月前

Casco (Casco) evaluates AI agents and apps on security, safety, and accuracy. Casco simulates attacks on AI systems to identify and fix vulnerabilities before they impact end users. Congrats on the launch, René Brandel and ian!

Casco (Casco) evaluates AI agents and apps on security, safety, and accuracy. Casco simulates attacks on AI systems to identify and fix vulnerabilities before they impact end users. Congrats on the launch, René Brandel and ian!

Y Combinator

33,908 次观看 • 1 年前

.Armature (YC P26) 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 (YC P26) and Louis Scremin!

.Armature (YC P26) 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 (YC P26) and Louis Scremin!

Y Combinator

11,605 次观看 • 2 个月前

Sira ( automates time tracking, scheduling, payroll & HR for hourly teams in minutes using AI agents. Congrats on the launch, Anto 👨‍💻 and Nathan Belaye!

Sira ( automates time tracking, scheduling, payroll & HR for hourly teams in minutes using AI agents. Congrats on the launch, Anto 👨‍💻 and Nathan Belaye!

Y Combinator

20,542 次观看 • 1 年前

Today we’re shipping new capabilities that make Resolve AI the platform where engineering teams run and fix production software with AI agents. New capabilities include background agents that run operational tasks, new agent architecture that delivers 2x investigation quality, new agent capabilities like governed actions, and new ways to work with agents in UI or terminal. With Resolve AI engineering teams can: - Delegate on-call to agents - Co-work with agents to resolve incidents - Run operational tasks with background agents.

Today we’re shipping new capabilities that make Resolve AI the platform where engineering teams run and fix production software with AI agents. New capabilities include background agents that run operational tasks, new agent architecture that delivers 2x investigation quality, new agent capabilities like governed actions, and new ways to work with agents in UI or terminal. With Resolve AI engineering teams can: - Delegate on-call to agents - Co-work with agents to resolve incidents - Run operational tasks with background agents.

Resolve AI

313,834 次观看 • 2 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

63,206 次观看 • 1 年前

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!

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!

Y Combinator

23,816 次观看 • 11 个月前

Vogent (Vogent) just launched voice AI agents that design and improve themselves, learning from real failure cases and requiring no prompt engineering. Congrats on the launch, Jagath Vytheeswaran and Vignesh Varadarajan!

Vogent (Vogent) just launched voice AI agents that design and improve themselves, learning from real failure cases and requiring no prompt engineering. Congrats on the launch, Jagath Vytheeswaran and Vignesh Varadarajan!

Y Combinator

106,181 次观看 • 1 年前

Nexus (Nexus) helps non-technical teams build production-ready AI agents without code. Orange's business team shipped an agent generating $4M+/month in just one week using Nexus. Congrats on the launch, Assem & Shady A.!

Nexus (Nexus) helps non-technical teams build production-ready AI agents without code. Orange's business team shipped an agent generating $4M+/month in just one week using Nexus. Congrats on the launch, Assem & Shady A.!

Y Combinator

22,554 次观看 • 10 个月前

.Corelayer (YC W26) is the AI on-call engineer for data pipelines. Their platform monitors both data and infrastructure for issues and uses AI agents to debug and suggest fixes in minutes. Congrats on the launch, Mitch Radhuber + Shipra Jha!

.Corelayer (YC W26) is the AI on-call engineer for data pipelines. Their platform monitors both data and infrastructure for issues and uses AI agents to debug and suggest fixes in minutes. Congrats on the launch, Mitch Radhuber + Shipra Jha!

Y Combinator

19,043 次观看 • 6 个月前

Fenrock AI (Fenrock AI) is building back office AI agents for banks. and private lenders. Process loans in minutes. Resolve customer complaints in seconds. Investigate 10x AML and fraud cases. Congrats on the launch, Charu Sharma (YC W26) and Michael M!

Fenrock AI (Fenrock AI) is building back office AI agents for banks. and private lenders. Process loans in minutes. Resolve customer complaints in seconds. Investigate 10x AML and fraud cases. Congrats on the launch, Charu Sharma (YC W26) and Michael M!

Y Combinator

18,082 次观看 • 5 个月前

Kinro (Kinro) helps brokers and D2C carriers sell P&C insurance with AI assistants. They train AI sales agents to handle qualification, quoting, recommendations, and binding while staying compliant. Today: human-to-agent on websites. Tomorrow: agent-to-agent across AI platforms. Congrats on the launch, Pierre-Alex & Corentin Hugot!

Kinro (Kinro) helps brokers and D2C carriers sell P&C insurance with AI assistants. They train AI sales agents to handle qualification, quoting, recommendations, and binding while staying compliant. Today: human-to-agent on websites. Tomorrow: agent-to-agent across AI platforms. Congrats on the launch, Pierre-Alex & Corentin Hugot!

Y Combinator

30,315 次观看 • 4 个月前

With the stack fixed, can an AI agent choose data and experiment like a researcher? At Evolvent AI, we built RSIBench-Data to test whether agents can diagnose failures, design data, train checkpoints, and use feedback. 🧵 📄 💻

With the stack fixed, can an AI agent choose data and experiment like a researcher? At Evolvent AI, we built RSIBench-Data to test whether agents can diagnose failures, design data, train checkpoints, and use feedback. 🧵 📄 💻

Fanqing

47,006 次观看 • 12 天前

LineWise (LineWise) is building an AI assistant to help manufacturing teams get their production lines back up and running— fast. Congrats on the launch, Tanachart Kujareevanich, ZHICHU REN, and Wenbo Zhang!

LineWise (LineWise) is building an AI assistant to help manufacturing teams get their production lines back up and running— fast. Congrats on the launch, Tanachart Kujareevanich, ZHICHU REN, and Wenbo Zhang!

Y Combinator

28,665 次观看 • 1 年前

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, Tusk flags issues before code merge so teams can focus on building great products.

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, Tusk flags issues before code merge so teams can focus on building great products.

AWS Startups

16,182,083 次观看 • 4 个月前

YC W22's Spinach AI automates meeting workflows using AI. Their new AI meeting agent joins your Zoom and helps run the meeting. Congrats on the launch, Matan Talmi, joshwillis, and Yoav Grossman!

YC W22's Spinach AI automates meeting workflows using AI. Their new AI meeting agent joins your Zoom and helps run the meeting. Congrats on the launch, Matan Talmi, joshwillis, and Yoav Grossman!

Y Combinator

16,872 次观看 • 1 年前