Loading video...

Video Failed to Load

Go Home

.@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...

ycombinator's profile picture

Y Combinator

1,617,645 subscribers

16,396 views • 4 months ago •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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!
1:10

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 views • 5 months ago

Deeptrace (Deeptrace) is an AI SRE and debugging companion that automatically investigates every production alert and surfaces a clear root cause, so your engineers spend less time firefighting and more time building. Congrats on the launch, srinth & andy lee!
1:35

Deeptrace (Deeptrace) is an AI SRE and debugging companion that automatically investigates every production alert and surfaces a clear root cause, so your engineers spend less time firefighting and more time building. Congrats on the launch, srinth & andy lee!

Y Combinator

67,909 views • 8 months ago

.Salus (YC W26) is building runtime guardrails to validate your AI agent’s actions before they execute. By adding their API to your codebase, incorrect actions are automatically blocked and your agent receives actionable feedback to self-correct. Congrats Vedant Singh and Kevin Pan on the launch!
1:56

.Salus (YC W26) is building runtime guardrails to validate your AI agent’s actions before they execute. By adding their API to your codebase, incorrect actions are automatically blocked and your agent receives actionable feedback to self-correct. Congrats Vedant Singh and Kevin Pan on the launch!

Y Combinator

14,633 views • 4 months ago

Manually dealing with user feedback is about to become a thing of the past. Extracting insights from feedback used to take hours every week. Now AI can do it for you, automatically. Introducing Cycle: the fastest way for your team to manage feedback – on autopilot. Start your free trial:
0:46

Manually dealing with user feedback is about to become a thing of the past. Extracting insights from feedback used to take hours every week. Now AI can do it for you, automatically. Introducing Cycle: the fastest way for your team to manage feedback – on autopilot. Start your free trial:

Mehdi Boudoukhane

15,762 views • 2 years ago

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!
1:37

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 views • 4 months ago

Introducing On-Call Copilot - a new agent template in LangSmith Fleet → Triages every alert and investigates root cause across your code and traces → Manages tickets and routes every incident to the right channels → Continuously learns from your runbooks, escalation rules, and noise patterns
0:33

Introducing On-Call Copilot - a new agent template in LangSmith Fleet → Triages every alert and investigates root cause across your code and traces → Manages tickets and routes every incident to the right channels → Continuously learns from your runbooks, escalation rules, and noise patterns

LangChain

14,235 views • 23 days ago

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!
2:24

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

29,681 views • 1 year ago

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!
0:49

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

62,939 views • 11 months ago

.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!
2:55

.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 views • 1 year ago

If a prototype takes a day, waiting a week for user feedback is "really painful," said Andrew Ng. Well....now you can get user feedback in under 60 seconds :) Whether you're prototyping a feature or building a full fledged product, learn how to build an AI-powered user research system that automatically generates user personas, conduct interviews, and synthesize insights. All in <60 seconds. Includes a full code notebook, recorded tutorial, and docs. The stack 🤖 fast inference 🤖 's LangGraph for orchestrating multi-agent workflows 🤖 's LangSmith for tracing and evaluating
0:32

If a prototype takes a day, waiting a week for user feedback is "really painful," said Andrew Ng. Well....now you can get user feedback in under 60 seconds :) Whether you're prototyping a feature or building a full fledged product, learn how to build an AI-powered user research system that automatically generates user personas, conduct interviews, and synthesize insights. All in <60 seconds. Includes a full code notebook, recorded tutorial, and docs. The stack 🤖 fast inference 🤖 's LangGraph for orchestrating multi-agent workflows 🤖 's LangSmith for tracing and evaluating

Sarah Chieng

231,233 views • 9 months ago

Introducing Runner, the knowledge work agent that works across all your apps to get real work done It's simply the best way to stay on top of messages, project management, user feedback, and much more Runner has become a daily driver for me and I think you'll like it too
0:37

Introducing Runner, the knowledge work agent that works across all your apps to get real work done It's simply the best way to stay on top of messages, project management, user feedback, and much more Runner has become a daily driver for me and I think you'll like it too

yitong

87,460 views • 2 months ago

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!
0:50

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 views • 1 year ago

Elon Musk on how he stays sane and grounded: “Don’t get high on your own supply. Don’t start thinking too highly of yourself... because it reduces your feedback loop.”
0:23

Elon Musk on how he stays sane and grounded: “Don’t get high on your own supply. Don’t start thinking too highly of yourself... because it reduces your feedback loop.”

Astro Greek

50,284 views • 1 month ago

‼️ Uphold is listening to user feedback! If you’re using Uphold , what features or tools would you actually want to see added? They’re openly asking the community for input, and honestly, I love the direction they’re taking. Drop your feedback below and I will share with their team!
1:30

‼️ Uphold is listening to user feedback! If you’re using Uphold , what features or tools would you actually want to see added? They’re openly asking the community for input, and honestly, I love the direction they’re taking. Drop your feedback below and I will share with their team!

CryptoSensei

11,378 views • 5 months ago

Get feedback on your app or website, then ask bolt.new to build the fix.
0:34

Get feedback on your app or website, then ask bolt.new to build the fix.

Granola

19,719 views • 3 months ago

$DDOG fits into agentic AI stack because AI makes infrastructure much more complex across models, managing GPU fleets, monitoring token costs and production workflows. That creates a massive monitoring problem and Datadog monetizes it by becoming the dashboard for AI complexity.
0:56

$DDOG fits into agentic AI stack because AI makes infrastructure much more complex across models, managing GPU fleets, monitoring token costs and production workflows. That creates a massive monitoring problem and Datadog monetizes it by becoming the dashboard for AI complexity.

Shay Boloor

54,452 views • 1 month ago

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

23,548 views • 8 months ago

Subtrace lets developers resolve production issues faster. Unlike Sentry and other backend monitoring tools, Subtrace makes it easy to search for the requests that truly matter during an incident. Congrats on the launch, and Sachin Sridhar!
0:58

Subtrace lets developers resolve production issues faster. Unlike Sentry and other backend monitoring tools, Subtrace makes it easy to search for the requests that truly matter during an incident. Congrats on the launch, and Sachin Sridhar!

Y Combinator

15,048 views • 1 year ago

Duck Tales 🎬 A behind-the-scenes look at DuckDuckGo Ep.8: AI chat organization, and the choices we make to transform user feedback into user benefits. Full episode: | 'Inside DuckDuckGo' on Spotify or Apple Podcasts
0:43

Duck Tales 🎬 A behind-the-scenes look at DuckDuckGo Ep.8: AI chat organization, and the choices we make to transform user feedback into user benefits. Full episode: | 'Inside DuckDuckGo' on Spotify or Apple Podcasts

DuckDuckGo

18,235 views • 8 months ago

Today we’re announcing our new product, Immutable Audience: AI-powered growth software built to 10x your game's acquisition, engagement, and retention. 95% of games fail at launch. This leaves millions of dollars and years of work to waste - often because teams weren’t able to prioritise marketing during their pre-launch process. Amidst the hard work of development, art design, lore creation, and testing, growth is frequently the forgotten step in the game development journey. However, growth is the single most important factor determining if your game will survive or die. Built on zkEVM, Audience abstracts this manual marketing work away, allowing studios to automatically: ➤ Convert your anonymous traffic from Steam, Discord, and UA channels into identified followers ➤ Use AI-powered quests and retention tools to keep your audience engaged across key milestones ➤ Track the value and engagement of your players before you launch ➤ Launch our AI-powered lifecycle marketer to run retargeting campaigns, on autopilot. Audience is now available for all game studios.
1:07

Today we’re announcing our new product, Immutable Audience: AI-powered growth software built to 10x your game's acquisition, engagement, and retention. 95% of games fail at launch. This leaves millions of dollars and years of work to waste - often because teams weren’t able to prioritise marketing during their pre-launch process. Amidst the hard work of development, art design, lore creation, and testing, growth is frequently the forgotten step in the game development journey. However, growth is the single most important factor determining if your game will survive or die. Built on zkEVM, Audience abstracts this manual marketing work away, allowing studios to automatically: ➤ Convert your anonymous traffic from Steam, Discord, and UA channels into identified followers ➤ Use AI-powered quests and retention tools to keep your audience engaged across key milestones ➤ Track the value and engagement of your players before you launch ➤ Launch our AI-powered lifecycle marketer to run retargeting campaigns, on autopilot. Audience is now available for all game studios.

Immutable

21,400 views • 7 months ago