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 engineering metrics are broken. They count PRs and commits, not real impact. Developer 360 from CodeAnt AI (YC W24) changes that. Built on top of their AI code reviews, it shows what’s actually being built, fixed, or improved— with real visibility into engineering work.

Y Combinator

1,620,464 subscribers

16,430 次观看 • 9 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

Engineering teams have a secret: most still use metrics like lines of code to judge their teams. Weave (YC W25) built a better option: an AI agent that accurately measures engineering output & quality. Congrats on the launch, Adam Cohen + Andrew!

Engineering teams have a secret: most still use metrics like lines of code to judge their teams. Weave (YC W25) built a better option: an AI agent that accurately measures engineering output & quality. Congrats on the launch, Adam Cohen + Andrew!

Y Combinator

25,339 次观看 • 1 年前

30% of code at top tech companies is now AI-generated. Most engineering leaders have no idea what that means for speed, quality, or ROI. Nivara ( gives them visibility into how humans and AI build together. The future of engineering is hybrid.

30% of code at top tech companies is now AI-generated. Most engineering leaders have no idea what that means for speed, quality, or ROI. Nivara ( gives them visibility into how humans and AI build together. The future of engineering is hybrid.

Y Combinator

26,597 次观看 • 7 个月前

Traditional coding benchmarks do not reflect how software is actually built and maintained. That's why we built a new benchmark, APEX-SWE, in partnership with Cognition. It measures whether AI models can perform complex, real-world software engineering work to ship systems that work and debug them when they don't. OpenAI GPT 5.3 Codex (High) tops the leaderboard at 41.5% on Pass@1.

Traditional coding benchmarks do not reflect how software is actually built and maintained. That's why we built a new benchmark, APEX-SWE, in partnership with Cognition. It measures whether AI models can perform complex, real-world software engineering work to ship systems that work and debug them when they don't. OpenAI GPT 5.3 Codex (High) tops the leaderboard at 41.5% on Pass@1.

adarsh

209,542 次观看 • 3 个月前

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

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

922,423 次观看 • 2 个月前

.InspectMind AI (YC W24)'s AI agent reviews construction drawings, specs, and building codes to catch issues before they turn into rework, delays, or lawsuits. It flags dimension errors, materials mismatches, code violations, and coordination gaps across architectural, structural, civil, and MEP drawings. On one $100M job, it caught a materials mismatch that saved the general contractor $2M.

.InspectMind AI (YC W24)'s AI agent reviews construction drawings, specs, and building codes to catch issues before they turn into rework, delays, or lawsuits. It flags dimension errors, materials mismatches, code violations, and coordination gaps across architectural, structural, civil, and MEP drawings. On one $100M job, it caught a materials mismatch that saved the general contractor $2M.

Y Combinator

19,218 次观看 • 7 个月前

YC W24's Decipher AI (YC W24) offers an AI agent that watches thousands of session replays for you, enabling teams to uncover customer issues, track feature usage, and answer product questions—all in real time.

YC W24's Decipher AI (YC W24) offers an AI agent that watches thousands of session replays for you, enabling teams to uncover customer issues, track feature usage, and answer product questions—all in real time.

Y Combinator

19,533 次观看 • 1 年前

Introducing Repo2RLEnv Turn any repository into runnable, verifiable coding environments built from real PRs and commits for coding-agent evaluation or RL training > uv pip install repo2rlenv

Introducing Repo2RLEnv Turn any repository into runnable, verifiable coding environments built from real PRs and commits for coding-agent evaluation or RL training > uv pip install repo2rlenv

Adithya S K

66,475 次观看 • 1 个月前

Introducing Entelligence AI Leaderboard: World's first engineering leaderboard 🚨 Athletes have rankings, researchers have citations but developers have been largely hidden We built a real time scoreboard for engineers & teams on actual PR performance: code quality, security and impact. If you're a cracked engineering team, join the leaderboard (Link below👇)

Introducing Entelligence AI Leaderboard: World's first engineering leaderboard 🚨 Athletes have rankings, researchers have citations but developers have been largely hidden We built a real time scoreboard for engineers & teams on actual PR performance: code quality, security and impact. If you're a cracked engineering team, join the leaderboard (Link below👇)

Aiswarya Sankar

233,627 次观看 • 10 个月前

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

37,751 次观看 • 5 个月前

Most AI coding tools still act like “one brain does everything.” Oh My Open Code flips that idea — it orchestrates multiple models like a real engineering team. Claude plans, Gemini builds, GPT reviews… all in parallel.

Most AI coding tools still act like “one brain does everything.” Oh My Open Code flips that idea — it orchestrates multiple models like a real engineering team. Claude plans, Gemini builds, GPT reviews… all in parallel.

Mervin Praison

39,392 次观看 • 6 个月前

How good is Claude Code Review really, and is it worth $25+ per review? We scraped every OSS repo on GitHub that's using it to figure out how devs actually use it. Here's how it stacks up against 22 other tools: Featuring: Augment Code baz CodeAnt AI (YC W24) CodeRabbit Cognition cubic Cursor Google Gemini Greptile Kilo Kody from Kodus Mesa Qodo

How good is Claude Code Review really, and is it worth $25+ per review? We scraped every OSS repo on GitHub that's using it to figure out how devs actually use it. Here's how it stacks up against 22 other tools: Featuring: Augment Code baz CodeAnt AI (YC W24) CodeRabbit Cognition cubic Cursor Google Gemini Greptile Kilo Kody from Kodus Mesa Qodo

Martian

49,116 次观看 • 3 个月前

While we are at Prometheus, there are reports that Jeff Bezos is creating an AI startup called ‘Project Prometheus’ that has amassed $6 billion and aims to develop AI capable of engineering, manufacturing, and real-world physical systems, not just chatbots or purely online software. They are building their guards and workers for their doomsday bunkers!

While we are at Prometheus, there are reports that Jeff Bezos is creating an AI startup called ‘Project Prometheus’ that has amassed $6 billion and aims to develop AI capable of engineering, manufacturing, and real-world physical systems, not just chatbots or purely online software. They are building their guards and workers for their doomsday bunkers!

Open Minded Approach

29,947 次观看 • 7 个月前

CONTEXT ENGINEERING > PROMPT ENGINEERING Everyone is obsessed with writing better prompts. The next generation of AI builders is focused on context engineering instead. • Prompt engineering shapes the question. Context engineering shapes everything the AI sees. • Great prompts can't save an agent missing critical context, memory, or tools. • AI failures often come from missing information, not weak models. • Context engineering combines prompts, memory, RAG, state management, and tool access into one system. What powers effective AI agents? → Memory: Remembers preferences, past interactions, and ongoing tasks. → State Management: Tracks progress across multi-step workflows. → RAG: Retrieves only the most relevant information when needed. → Tools: Connects AI to APIs, databases, code execution, and real-world actions. → Dynamic Prompts: Enriches instructions with live context at runtime. The key insight: Prompt Engineering = Better Questions Context Engineering = Better Systems The future of AI isn't building smarter prompts. It's building smarter environments for AI to think, remember, retrieve, and act.

CONTEXT ENGINEERING > PROMPT ENGINEERING Everyone is obsessed with writing better prompts. The next generation of AI builders is focused on context engineering instead. • Prompt engineering shapes the question. Context engineering shapes everything the AI sees. • Great prompts can't save an agent missing critical context, memory, or tools. • AI failures often come from missing information, not weak models. • Context engineering combines prompts, memory, RAG, state management, and tool access into one system. What powers effective AI agents? → Memory: Remembers preferences, past interactions, and ongoing tasks. → State Management: Tracks progress across multi-step workflows. → RAG: Retrieves only the most relevant information when needed. → Tools: Connects AI to APIs, databases, code execution, and real-world actions. → Dynamic Prompts: Enriches instructions with live context at runtime. The key insight: Prompt Engineering = Better Questions Context Engineering = Better Systems The future of AI isn't building smarter prompts. It's building smarter environments for AI to think, remember, retrieve, and act.

Dami-Defi

10,107 次观看 • 18 天前

This House Was Built from Scratch — 100% Real Work. ai-animated

This House Was Built from Scratch — 100% Real Work. ai-animated

Architecture Presentation

167,630 次观看 • 5 个月前

ANTHROPIC'S HEAD OF ENGINEERING SAYS THEY JUST SHIPPED THE MOST CAPABLE MODELS THEY HAVE EVER BUILT Mythos 5 and Fable 5. Fable 5 can run for days on a single goal and get it right on the first pass, on work that used to need an entire team. Most people use AI to summarize things. The real leverage is the long autonomous task you keep putting off.

ANTHROPIC'S HEAD OF ENGINEERING SAYS THEY JUST SHIPPED THE MOST CAPABLE MODELS THEY HAVE EVER BUILT Mythos 5 and Fable 5. Fable 5 can run for days on a single goal and get it right on the first pass, on work that used to need an entire team. Most people use AI to summarize things. The real leverage is the long autonomous task you keep putting off.

0xMarioNawfal

57,078 次观看 • 21 天前

We've built a massive verification bottleneck: • 72% of developers use AI to generate code every day • 96% of them don't fully trust it Writing code is now free. All the work now is verifying that the code does what it's supposed to. According to a new State of Code Survey, almost half of the respondents believe the number one skill that will matter most in the coming years is "reviewing and validating AI-generated code for quality and security". Not prompt engineering or vibe-coding, but checking AI's work.

We've built a massive verification bottleneck: • 72% of developers use AI to generate code every day • 96% of them don't fully trust it Writing code is now free. All the work now is verifying that the code does what it's supposed to. According to a new State of Code Survey, almost half of the respondents believe the number one skill that will matter most in the coming years is "reviewing and validating AI-generated code for quality and security". Not prompt engineering or vibe-coding, but checking AI's work.

Santiago

16,299 次观看 • 5 个月前

I built an AI system that builds itself. Not metaphorically. The AI agents literally rewrote their own orchestrator, tested it, reviewed their own code, fixed their own CI failures, and shipped it. Introducing Agent Orchestrator. Open source. Link below.

I built an AI system that builds itself. Not metaphorically. The AI agents literally rewrote their own orchestrator, tested it, reviewed their own code, fixed their own CI failures, and shipped it. Introducing Agent Orchestrator. Open source. Link below.

prateek

267,177 次观看 • 4 个月前

Users state the goal. xBubble handles the building path. With Bubble Code, xBubble helps users create different kinds of Code AI Agents & AI roducts. The key is not just generating a prototype. Bubble Code is built to turn user goals into ready-to-use products with real interfaces, logic, integrations, and deployment paths. AI products should not stop at a mockup. With xBubble, they can be built, deployed, and used directly.

Users state the goal. xBubble handles the building path. With Bubble Code, xBubble helps users create different kinds of Code AI Agents & AI roducts. The key is not just generating a prototype. Bubble Code is built to turn user goals into ready-to-use products with real interfaces, logic, integrations, and deployment paths. AI products should not stop at a mockup. With xBubble, they can be built, deployed, and used directly.

DAPPOS

95,873 次观看 • 4 天前

🚀 Codegen is now generally available! After 2 years of development, we're thrilled to introduce an AI-powered developer agent that transforms how engineering teams work. Built on Claude 3.7, Codegen seamlessly integrates with Slack, GitHub, and Linear to help you build better software, faster. Try it free, today:

🚀 Codegen is now generally available! After 2 years of development, we're thrilled to introduce an AI-powered developer agent that transforms how engineering teams work. Built on Claude 3.7, Codegen seamlessly integrates with Slack, GitHub, and Linear to help you build better software, faster. Try it free, today:

Codegen

16,418 次观看 • 1 年前