Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing: PlayerZero The world's first Engineering World Model that puts debugging, fixing, and testing your code on autopilot. We've raised $20M from Foundation Capital, Matei Zaharia (Databricks), Peter Bailis (Workday), Guillermo Rauch (Vercel), Dylan Field (Figma), Drew Houston (Dropbox), and more PlayerZero frees up 30% of your engineering bandwidth... by: 1.⁠ ⁠Finding the root cause for bugs & incidents in minutes that engineering teams take days to identify. 2.⁠ ⁠Predicting in minutes, edge case issues that a 300-person QA team would take weeks to find. ------ Here's why this matters: No one in your org has a complete picture of how your production software actually behaves. Support sees tickets. SRE sees infra. Dev sees code. Each team builds their own fragmented view - and none of these systems talk to each other. When something breaks, everyone scrambles to stitch the picture together by hand. PlayerZero connects all of it into a single context graph - → The Slack thread where your lead said "we went with X because Y fell apart in prod last time" → The PR review where an engineer explained the tradeoff → The lifetime history of your CI/CD pipeline, observability stack, incidents, and support tickets So you can trace any problem to its root cause across every silo. And it compounds. Every incident diagnosed teaches the model something new. The longer it runs, the deeper it understands - which code paths are high-risk, which configurations are fragile, which changes tend to break which customer flows. So when you sit down to debug a live issue, you have your entire org's collective reasoning and production memory behind you - instantly. ------ Zuora, Georgia-Pacific, and Nylas have reduced resolution time by 90% and caught 95% of breaking changes and freeing an average of $30M in engineering bandwidth. ------ Our guarantee: If we can't increase your engineering bandwidth by at least 20% within one week, we'll donate $10,000 to an open-source project of your choice. Book a demo -show more

Animesh Koratana

9,396 subscribers

2,762,917 views • 7 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

47 Comments

Animesh Koratana7 months ago

We're also giving away a curated collection of 200+ Claude Code Skills our team uses daily — the workflows that made us faster engineers while building PlayerZero. Repost and comment "100X" to get access.

Animesh Koratana7 months ago

It's state of the art. Across 26,400 real PRs, PlayerZero predicted bugs before code shipped to production 64% of the time. For comparison: → Claude Code: 11% → Cursor BugBot: 16% Its not an incremental improvement, its a new paradigm.

Animesh Koratana7 months ago

For the last 7 years, I've been working on one question: can a machine truly understand software? Not just read or write it. But understand it like your best senior architect. Through my research at Stanford AI from '18–'21, deployment at OpenAI on GPT-2, and now through applied AI at PlayerZero. (the answer is yes)

Animesh Koratana7 months ago

Book a demo today:

litquidity7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Software engineers looking at AI do their job better than them

Abhishek Agarwal7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston I was discussing with our CTO why nobody has built this yet. We still take an embarrassingly long time to do RCAs. Congrats on the launch!

Animesh Koratana7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Thanks Abhishek. About time, someone built it!

Avid7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston this is so awesome. finally shipping fast and debugging faster will be the reality

Animesh Koratana7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Love this!

Avid7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston I appreciate it

Andrew Yeung7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston insane offer "If we can't increase your engineering bandwidth by at least 20% within one week, we'll donate $10,000 to an open-source project of your choice."

Anish Moonka7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston been testing this for a few days and it genuinely caught stuff I would've shipped blind

Damian Player7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston yuuuuuge! 30% of time back for engs is wild..

amrit7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston congrats on launch, v hard problem to solve

SumitM7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston This is interesting ... Debugging faster is great !! If it actually works at scale, this can save a lot of engineering time !!

Santiago7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Congrats on the launch. Congrats on the rise!

Rohan Paul7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston debugging is 70% of the bottleneck. If this works well, the value will be huge. Going to try it out now. Congrats on the launch.

AshutoshShrivastava7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston The gap has always been there. Most AI tools help you write code faster, but nothing serious handles what happens after it ships. Good to see that changing.

Chubby♨️7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston very cool!

OneManSaas7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston How does PlayerZero handle debugging distributed systems where the issue spans multiple services? Traditional debugging tools fall apart when you're trying to trace problems across microservices - curious if your world model can actually connect those dots.

Nandkishor7 months ago

Congratulations @akoratana on the launch. This is exactly what we’ve been looking for. As a DevOps engineer, it allows me to focus more on system design, reliability, and building scalable infrastructure rather than spending time debugging calls at 2 AM. It’s also going to help significantly in resolving issues faster when they occur next time.

Animesh Koratana7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Thanks! That's the future we see for every builder in the world :)

Connor Heyward-Fox7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston congrats on the launch - looks like a great solution! question: how does the context graph handle conflicting signals? when slack says one thing but CI history says another, does it surface both or pick a winner?

Animesh Koratana7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Code is the source of truth, other sources can be context. Maybe your docs say it should operate one way, but if the code doesn't actually match the docs, you want your production engineer to go off of what's actually in prod.

Connor Heyward-Fox7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston that makes sense. code as source of truth, everything else as context that might explain why the code is the way it is. clean hierarchy.

AndreWGMI7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston 90% faster resolution is crazy, but does it actually learn org-specific context or is that just marketing speak?

Animesh Koratana7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Yup. Org-specific, learns your own context from your own codebase

vas7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Congrats on the launch!

Animesh Koratana7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Thanks Vas!

Animesh Koratana7 months ago

@pbailis @rauchg @zoink @drewhouston UPDATE: Too many of y’all wanted this and X won't let us DM fast enough! Here's the link, it's available for everyone now: 200+ Claude Code Skills for Developers ⬆️

PlayerZero7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston So excited to launch this into the world

Tech with Mak7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston This is huge! You only realize how big this problem is once things start breaking in prod 😅

Alvaro Cintas7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Big congrats on the launch!

Ram7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Thanks @akoratana and playerzero team. You solved one of the biggest pain point.

Shruti7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Reducing resolution time by 90% is no small feat. Congrats on the raise.

Alexey Grigorev7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston 100x Congratulations on the launch!

Animesh Koratana7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Thanks Alexey.

Nandkishor7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston

Abraham Wolke7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Hey, if you're reading this we built a public code graph API that anyone can build things like this on top of -> DM me and I'll set u up

Daniel Ch7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Looks like a gamechanger!!

AI Panda7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Feels like a real shift toward actually understanding production systems.

Om7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston This is huge 🔥 Debugging now finally getting the upgrade it deserves. Excited to see this in action ..

Masters Mind7 months ago

@powerbeastt @matei_zaharia @pbailis @rauchg @zoink @drewhouston PlayerZero isn’t just AI coding — it’s AI that understands your whole production system. Connects tickets, PRs, Slack threads, and CI/CD into one context graph. Cuts debugging time, predicts edge cases, and boosts engineering bandwidth. 🚀

pika capital7 months ago

@litcapital @matei_zaharia @pbailis @rauchg @zoink @drewhouston Let me know if you are still taking any Angel checks 👀👀👀

David Ch7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston wow.. no way this doesn't go into the history books keeping an eye on this, congrats guys!

𝗿𝗮𝗺𝗮𝗸𝗿𝘂𝘀𝗵𝗻𝗮— 𝗲/𝗮𝗰𝗰7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Debugging is the biggest issue in the agentic world. Game changer. Congrats to you & your teams for the launch.

Rez Karim7 months ago

@matei_zaharia @pbailis @rauchg @zoink @drewhouston Congrats Animesh. PlayerZero just automated the one thing vibe coded apps especially need, testing and debugging all the AI generated code.

Related Videos

Your engineering team is about to snap. And your AI coding agent is making it worse. Introducing CodeRabbit Agent for Slack 🎉 A second brain for engineering teams. Because your tribal knowledge lives in Slack threads nobody can find. At CodeRabbit, we review millions of PRs every week and know how ace engineering teams operate on the planet. The same three things slow every team we see: - Context and decisions that live elsewhere. - Lack of a team-level durable knowledge base - And a trust layer that gives a safety net to your teams Built for Agentic SDLC workflows, CodeRabbit Agent for Slack solves all three problems in one shot while enabling teams to collaborate in real-time with the Agent. CodeRabbit Agent is Slack-native and builds your team’s operating context from every thread, every decision, every conversation your team has ever had. Make your team’s context compound!

Your engineering team is about to snap. And your AI coding agent is making it worse. Introducing CodeRabbit Agent for Slack 🎉 A second brain for engineering teams. Because your tribal knowledge lives in Slack threads nobody can find. At CodeRabbit, we review millions of PRs every week and know how ace engineering teams operate on the planet. The same three things slow every team we see: - Context and decisions that live elsewhere. - Lack of a team-level durable knowledge base - And a trust layer that gives a safety net to your teams Built for Agentic SDLC workflows, CodeRabbit Agent for Slack solves all three problems in one shot while enabling teams to collaborate in real-time with the Agent. CodeRabbit Agent is Slack-native and builds your team’s operating context from every thread, every decision, every conversation your team has ever had. Make your team’s context compound!

Harjot Gill

4,778,147 views • 6 months ago

1/ Today we're introducing Breken, and with it the final job in software: production engineering. Your tests check what your team thought of. Production checks everything else. Today, your users run that second test for you. Breken runs it instead. Your real software, in worlds that behave like production, down to the chaos and the users, finding and fixing what breaks before a single user does. Here it is:

1/ Today we're introducing Breken, and with it the final job in software: production engineering. Your tests check what your team thought of. Production checks everything else. Today, your users run that second test for you. Breken runs it instead. Your real software, in worlds that behave like production, down to the chaos and the users, finding and fixing what breaks before a single user does. Here it is:

breken

2,197,957 views • 7 days ago

Resource Network: The underlying technology by which all your vehicle’s components and items communicate, and your best friend at the engineering terminal. Take in the whole picture as you maintain the health of your ship and manage its power distribution. Playable Now in Alpha 4.5 Dawn of Engineering:

Resource Network: The underlying technology by which all your vehicle’s components and items communicate, and your best friend at the engineering terminal. Take in the whole picture as you maintain the health of your ship and manage its power distribution. Playable Now in Alpha 4.5 Dawn of Engineering:

Star Citizen

16,716 views • 9 months ago

Nobody is writing 90% of their code using AI. Here's the uncomfortable truth: The real productivity gain from using AI to write code is closer to 10%, nowhere near the 90% people claim. Sundar Pichai said in 2024 that 30% of the new code at Google was AI-generated. However, he went on to admit, during Lex Friedman's podcast, that engineering velocity had only increased by about 10%. AI-generated code isn't free code. It still has to be reviewed, tested, and made production-ready. Optimizing a single step (code generation) doesn't boost output if bottlenecks shift elsewhere (code reviews). It doesn't matter how much code you generate if you can't keep up the review process. The solution: Automate as much as you can the review and verification of your code. I'm working with Sonar, who is sponsoring this post, and they will take care of the code quality and security analysis of your code: • They review over 300B lines of code every single day • They cover reliability, security, and maintainability for your code • You can integrate them into your CI/CD pipeline • You can install them in your IDE (I use their VSCode extension) • Support for more than 30 languages Here is a link so you can check them out:

Nobody is writing 90% of their code using AI. Here's the uncomfortable truth: The real productivity gain from using AI to write code is closer to 10%, nowhere near the 90% people claim. Sundar Pichai said in 2024 that 30% of the new code at Google was AI-generated. However, he went on to admit, during Lex Friedman's podcast, that engineering velocity had only increased by about 10%. AI-generated code isn't free code. It still has to be reviewed, tested, and made production-ready. Optimizing a single step (code generation) doesn't boost output if bottlenecks shift elsewhere (code reviews). It doesn't matter how much code you generate if you can't keep up the review process. The solution: Automate as much as you can the review and verification of your code. I'm working with Sonar, who is sponsoring this post, and they will take care of the code quality and security analysis of your code: • They review over 300B lines of code every single day • They cover reliability, security, and maintainability for your code • You can integrate them into your CI/CD pipeline • You can install them in your IDE (I use their VSCode extension) • Support for more than 30 languages Here is a link so you can check them out:

Santiago

296,928 views • 1 year ago

🚀 Today, we announced frontier agents, a new class of AI agents which are a step-function change in what you can do with agents. Our first three agents mark the beginning of a new era in software development: 🟠 Kiro autonomous agent maintains persistent context and learns over time while working independently, so you can focus on your biggest priorities. It can handle a range of tasks—from triaging bugs to improving code coverage—with a single change spanning multiple repositories. 🟠 AWS Security Agent is your virtual security engineer that helps build secure applications by being a security consultant for app design, code reviews, and penetration testing. 🟠 AWS DevOps Agent is your virtual operations team member that helps resolve and proactively prevent incidents. It is on call when incidents happen, instantly responding to issues and using its knowledge of your application and the relationship between components to find the root ause of the problem. More on how we’re helping customers driving towards an agentic future: #AWSreInvent

🚀 Today, we announced frontier agents, a new class of AI agents which are a step-function change in what you can do with agents. Our first three agents mark the beginning of a new era in software development: 🟠 Kiro autonomous agent maintains persistent context and learns over time while working independently, so you can focus on your biggest priorities. It can handle a range of tasks—from triaging bugs to improving code coverage—with a single change spanning multiple repositories. 🟠 AWS Security Agent is your virtual security engineer that helps build secure applications by being a security consultant for app design, code reviews, and penetration testing. 🟠 AWS DevOps Agent is your virtual operations team member that helps resolve and proactively prevent incidents. It is on call when incidents happen, instantly responding to issues and using its knowledge of your application and the relationship between components to find the root ause of the problem. More on how we’re helping customers driving towards an agentic future: #AWSreInvent

Swami Sivasubramanian

26,056 views • 11 months ago

FibeRobo, developed by an interdisciplinary team at MIT, represents a significant innovation in the textile industry. It's a liquid crystal elastomer fiber capable of changing its shape in response to temperature changes. 👉 Subscribe to our tech newsletter, The Blueprint, which is your daily source of tech, science, and engineering innovation. Here you go: #engineering

FibeRobo, developed by an interdisciplinary team at MIT, represents a significant innovation in the textile industry. It's a liquid crystal elastomer fiber capable of changing its shape in response to temperature changes. 👉 Subscribe to our tech newsletter, The Blueprint, which is your daily source of tech, science, and engineering innovation. Here you go: #engineering

Interesting Engineering

14,031 views • 2 years ago

One of John McAfee's final messages to the world: "Some of you may be living an existence of dissatisfaction... of emptiness... of longing." "This sense of longing... is really your loss of freedom. And it is freedom for which you yearn." "And you have none in this government. A government... which started out with the people being free and the government being our servants. It has become the government is free... and it's the people that are the servants." "You have woken up to your reality. That is what you are feeling." "Wake up a bit more and do something about it."

One of John McAfee's final messages to the world: "Some of you may be living an existence of dissatisfaction... of emptiness... of longing." "This sense of longing... is really your loss of freedom. And it is freedom for which you yearn." "And you have none in this government. A government... which started out with the people being free and the government being our servants. It has become the government is free... and it's the people that are the servants." "You have woken up to your reality. That is what you are feeling." "Wake up a bit more and do something about it."

Red Pill Dispenser

516,806 views • 1 year ago

hockeystick moments are the biggest opportunity of your career. It's exciting and kinda scary. Everything changes! I wrote Scaling Fast: Software Engineering Through the Hockeystick as your guide. 16 years of startup experience condensed into 240 pages Scaling Fast is based on startup war stories, academic research papers, talking to my mentors, and reading industry insights. It shows you what it takes to survive and thrive through the hockeystick. You'll learn about scaling teams and scaling code, how they influence each other, and why none of it matters if the business is bad. Scaling Fast: Software Engineering Through the Hockeystick is organized in 3 sections: - Scaling the Business - Scaling the Team - Scaling the Tech The business part, that's to help you evaluate the companies you join, this isn't a business book. The team part, that's key to shaping your everyday. We talk about delegating decisions, empowering engineers, working smooth instead of fast, finishing things all the way to done, good code review culture, and shipping incrementally without risky big bang releases. The tech part, that's my favorite. We talk about good abstractions, architectural complexity, observing your systems break, making steady improvements to your code without huge refactoring sprints, why tests don't solve everything, what's even worth testing, how your team structure impacts what you can do with the code, and why solving today's problem is more important than building for an imagined future. None of it is about numerical scaling [name|]. That's easy in 2025. Computers are fast. The challenge is building complex systems that don't fit in any one person's brain without breaking the business. oftware engineering when your whole company changes every 6 months is the fun part of this gig. And that's what Scaling Fast is about. 👉

hockeystick moments are the biggest opportunity of your career. It's exciting and kinda scary. Everything changes! I wrote Scaling Fast: Software Engineering Through the Hockeystick as your guide. 16 years of startup experience condensed into 240 pages Scaling Fast is based on startup war stories, academic research papers, talking to my mentors, and reading industry insights. It shows you what it takes to survive and thrive through the hockeystick. You'll learn about scaling teams and scaling code, how they influence each other, and why none of it matters if the business is bad. Scaling Fast: Software Engineering Through the Hockeystick is organized in 3 sections: - Scaling the Business - Scaling the Team - Scaling the Tech The business part, that's to help you evaluate the companies you join, this isn't a business book. The team part, that's key to shaping your everyday. We talk about delegating decisions, empowering engineers, working smooth instead of fast, finishing things all the way to done, good code review culture, and shipping incrementally without risky big bang releases. The tech part, that's my favorite. We talk about good abstractions, architectural complexity, observing your systems break, making steady improvements to your code without huge refactoring sprints, why tests don't solve everything, what's even worth testing, how your team structure impacts what you can do with the code, and why solving today's problem is more important than building for an imagined future. None of it is about numerical scaling [name|]. That's easy in 2025. Computers are fast. The challenge is building complex systems that don't fit in any one person's brain without breaking the business. oftware engineering when your whole company changes every 6 months is the fun part of this gig. And that's what Scaling Fast is about. 👉

Swizec Teller

59,366 views • 10 months ago

.Postman is now natively available in your favorite coding agent! The new Postman CLI is designed to bring API engineering for agents: 1️⃣ Works in Git and your code repo - Just drop Postman where your agent lives and works. 2️⃣ No GUI - Work in your coding agent. Bring up the Postman UI for review and approval. 3️⃣ No sign-up - Get started right away. Sign-up when you have to save your work and want more. Install once, work in your agent. Run npm install -g postman-cli, then postman init. This loads Postman's skills into your coding agent so it can create collections, write tests, and much more. Available as a plugin for all coding agents! The skills cover the API lifecycle: find APIs your org already has, generate tests that catch regressions, mock an API before it exists, watch live endpoints for downtime and drift, run checks in CI on every commit, and run performance tests. You can also extend the abilities of your agent with the Context Graph. An agent often sees only the code that is accessible to them. The Context Graph API gives it a map of your team's infrastructure, APIs, and services, and how they depend on each other. As your agent works, you stay the reviewer. Your agent does the work from the command line. Open Postman when you want to review or approve it. Check out more at

.Postman is now natively available in your favorite coding agent! The new Postman CLI is designed to bring API engineering for agents: 1️⃣ Works in Git and your code repo - Just drop Postman where your agent lives and works. 2️⃣ No GUI - Work in your coding agent. Bring up the Postman UI for review and approval. 3️⃣ No sign-up - Get started right away. Sign-up when you have to save your work and want more. Install once, work in your agent. Run npm install -g postman-cli, then postman init. This loads Postman's skills into your coding agent so it can create collections, write tests, and much more. Available as a plugin for all coding agents! The skills cover the API lifecycle: find APIs your org already has, generate tests that catch regressions, mock an API before it exists, watch live endpoints for downtime and drift, run checks in CI on every commit, and run performance tests. You can also extend the abilities of your agent with the Context Graph. An agent often sees only the code that is accessible to them. The Context Graph API gives it a map of your team's infrastructure, APIs, and services, and how they depend on each other. As your agent works, you stay the reviewer. Your agent does the work from the command line. Open Postman when you want to review or approve it. Check out more at

Abhinav Asthana

493,807 views • 28 days ago

Americans are under surveillance Roughly 40,000-60,000 cameras have been placed throughout 42 states that are tagging your vehicle and entering it into a database to track you “These cameras capture more than your license. They can capture the interior of your vehicle as you drive by these cameras, especially the positioning of the camera and it's legal (Attorney shows a picture of what one of these “Flock Cameras” looks like, when you see it you’ll instantly recognize it. They’re everywhere) “So what happens is this camera captures your tag and when it captures your tag is able to detect where your vehicle has been anywhere in the United States where there are flock cameras. If you're in Georgia and you travel to New York, every time your vehicle tag gets captured by a flock camera, it is entered into a database and they are able to track it.”

Americans are under surveillance Roughly 40,000-60,000 cameras have been placed throughout 42 states that are tagging your vehicle and entering it into a database to track you “These cameras capture more than your license. They can capture the interior of your vehicle as you drive by these cameras, especially the positioning of the camera and it's legal (Attorney shows a picture of what one of these “Flock Cameras” looks like, when you see it you’ll instantly recognize it. They’re everywhere) “So what happens is this camera captures your tag and when it captures your tag is able to detect where your vehicle has been anywhere in the United States where there are flock cameras. If you're in Georgia and you travel to New York, every time your vehicle tag gets captured by a flock camera, it is entered into a database and they are able to track it.”

Wall Street Apes

329,561 views • 1 year ago

AI is changing the software engineering craft. Anders Hejlsberg (Anders Hejlsberg) - creator of C#, TypeScript and industry legend - on why code review needs to get more enjoyable in response: #1 - AI is shifting the craft from writing code, to reviewing code: "In a sense, we're all turning into project managers. We can have an army of junior programmers, called agents, that will just spit out reams of code but someone's got to have the big picture and review all of that. And so, increasingly, our craft is going from one of writing the code, to one of reviewing the code and building the architecture of the code and overseeing the work. It's a different kind of craft. It's a different kind of enjoyment. I've always liked writing the code. To me that was the fulfilling part, seeing it work. In a way, AI robs a little bit of that, because I am less interested in reviewing code." #2 - The code review experience should be improved: "I think we could also make the process of reviewing code much more interesting than it is today. I mean, today, you see a list of diffs in alphabetical order and now it's up to you to make heads or tails of it. There are more pedagogical ways of presenting that. And you could have commentary generated by the AI that tells you what the changes are and whatever, and then tries to guide you along. So that symbiotic relationship, I think we need to work on that more and to keep the enjoyment in there."

AI is changing the software engineering craft. Anders Hejlsberg (Anders Hejlsberg) - creator of C#, TypeScript and industry legend - on why code review needs to get more enjoyable in response: #1 - AI is shifting the craft from writing code, to reviewing code: "In a sense, we're all turning into project managers. We can have an army of junior programmers, called agents, that will just spit out reams of code but someone's got to have the big picture and review all of that. And so, increasingly, our craft is going from one of writing the code, to one of reviewing the code and building the architecture of the code and overseeing the work. It's a different kind of craft. It's a different kind of enjoyment. I've always liked writing the code. To me that was the fulfilling part, seeing it work. In a way, AI robs a little bit of that, because I am less interested in reviewing code." #2 - The code review experience should be improved: "I think we could also make the process of reviewing code much more interesting than it is today. I mean, today, you see a list of diffs in alphabetical order and now it's up to you to make heads or tails of it. There are more pedagogical ways of presenting that. And you could have commentary generated by the AI that tells you what the changes are and whatever, and then tries to guide you along. So that symbiotic relationship, I think we need to work on that more and to keep the enjoyment in there."

The Pragmatic Engineer

39,073 views • 5 months ago

I'm sharing with you one of the best papers I've read on Harness Engineering it takes apart Claude Code (Opus 5.5), Codex, Gemini CLI and more, and boils all of them down to one line: agent = model + harness what you walk away with: > what a harness actually is > how today's coding agents are built under the hood > the patterns every one of them repeats > where the whole category is heading > their checklist for building your own the model gets the headlines. the harness decides whether the agent works loop and graph engineering on top of it - in my article below

I'm sharing with you one of the best papers I've read on Harness Engineering it takes apart Claude Code (Opus 5.5), Codex, Gemini CLI and more, and boils all of them down to one line: agent = model + harness what you walk away with: > what a harness actually is > how today's coding agents are built under the hood > the patterns every one of them repeats > where the whole category is heading > their checklist for building your own the model gets the headlines. the harness decides whether the agent works loop and graph engineering on top of it - in my article below

Mr. Buzzoni

84,231 views • 23 days ago

We are truly overwhelmed with gratitude for each and every one of you who took the time out of your incredibly busy days and navigated through the Lagos traffic just to support Violet Charm at our very first pop-up event. It means so much to us that you chose to spend your precious time with us, and your presence brought so much warmth, energy, and joy to the day. This milestone is just the beginning of what we hope will be a beautiful journey, and while this was our first pop-up, it certainly won’t be the last. We are inspired by your encouragement and are committed to learning, growing, and improving every step of the way. Next year, we promise to come back bigger, better, and more exciting, all because of your unwavering support. Thank you from the depths of our hearts for believing in us and being part of this special moment ,we couldn’t have done it without you, and we can’t wait to create even more unforgettable memories together. Full video on my instagram

We are truly overwhelmed with gratitude for each and every one of you who took the time out of your incredibly busy days and navigated through the Lagos traffic just to support Violet Charm at our very first pop-up event. It means so much to us that you chose to spend your precious time with us, and your presence brought so much warmth, energy, and joy to the day. This milestone is just the beginning of what we hope will be a beautiful journey, and while this was our first pop-up, it certainly won’t be the last. We are inspired by your encouragement and are committed to learning, growing, and improving every step of the way. Next year, we promise to come back bigger, better, and more exciting, all because of your unwavering support. Thank you from the depths of our hearts for believing in us and being part of this special moment ,we couldn’t have done it without you, and we can’t wait to create even more unforgettable memories together. Full video on my instagram

Isabella Esther Georgewill

56,275 views • 10 months ago

In two years, every new tech company will run on a CRM you can vibe code to fit your business. This CRM will not be built from scratch on a coding platform though. It will be built on top of managed infrastructure with complete data capture, indices designed for LLMs to understand the whole picture, clean APIs, curated UI frameworks designed for selling, enterprise-grade security, and come with 24/7 support. You’ll instruct the agent using natural language and it will write the code + run it for you. That’s what we’re building at Lightfield and today we’re announcing step two of our plan - code execution. You can now ask your agent to build programs, artifacts, and run complex analysis instantly. It does this by writing and running Python in a high performance sandbox using full customer memory — including every email, meeting, and note that Lightfield has captured — and reasoning across every relationship to deliver high quality work. Ask your agent to build a competitive battle card before a call tomorrow. It pulls positioning, objections, and win/loss patterns from real conversations. Ask it to flag every open deal where your champion's engagement has dropped or sentiment has shifted. It reads across every conversation and tells you where to focus. Ask it to build a pipeline review with charts and graphs for your board. It produces the whole thing in minutes. Here’s what we did with it this week: → We asked our agent to grade our sales team on discovery, rapport, and closing. It gave a structured scorecard with specific examples from real conversations. → Our GTM team asked the agent to build a plan to expand one of our enterprise customers. It pulled competitive threats, upsell paths, stakeholder mapping, and a phased execution plan — in minutes. → We used it to find every feature request from the last quarter that our engineering team has since shipped, and draft a personalized follow-up to each customer using their original words. It closed loops across dozens of accounts that would have taken days to track down manually This is the first step towards building any custom GTM workflow in natural language on top of what Lightfield knows about your business - a world model built from every single interaction your team has had with customers.

In two years, every new tech company will run on a CRM you can vibe code to fit your business. This CRM will not be built from scratch on a coding platform though. It will be built on top of managed infrastructure with complete data capture, indices designed for LLMs to understand the whole picture, clean APIs, curated UI frameworks designed for selling, enterprise-grade security, and come with 24/7 support. You’ll instruct the agent using natural language and it will write the code + run it for you. That’s what we’re building at Lightfield and today we’re announcing step two of our plan - code execution. You can now ask your agent to build programs, artifacts, and run complex analysis instantly. It does this by writing and running Python in a high performance sandbox using full customer memory — including every email, meeting, and note that Lightfield has captured — and reasoning across every relationship to deliver high quality work. Ask your agent to build a competitive battle card before a call tomorrow. It pulls positioning, objections, and win/loss patterns from real conversations. Ask it to flag every open deal where your champion's engagement has dropped or sentiment has shifted. It reads across every conversation and tells you where to focus. Ask it to build a pipeline review with charts and graphs for your board. It produces the whole thing in minutes. Here’s what we did with it this week: → We asked our agent to grade our sales team on discovery, rapport, and closing. It gave a structured scorecard with specific examples from real conversations. → Our GTM team asked the agent to build a plan to expand one of our enterprise customers. It pulled competitive threats, upsell paths, stakeholder mapping, and a phased execution plan — in minutes. → We used it to find every feature request from the last quarter that our engineering team has since shipped, and draft a personalized follow-up to each customer using their original words. It closed loops across dozens of accounts that would have taken days to track down manually This is the first step towards building any custom GTM workflow in natural language on top of what Lightfield knows about your business - a world model built from every single interaction your team has had with customers.

Keith Peiris

27,634 views • 8 months ago

Head of Claude Code: "85% of our engineers are running dozens or hundreds of agents. The way you do it is graph engineering." In 40 minutes he explains how a single engineer now does the work of a whole team, how far this has gone inside Anthropic and where it goes next. This is something you can't skip if you don't want to be left behind. Watch it, then read the full guide on graph engineering below.

Head of Claude Code: "85% of our engineers are running dozens or hundreds of agents. The way you do it is graph engineering." In 40 minutes he explains how a single engineer now does the work of a whole team, how far this has gone inside Anthropic and where it goes next. This is something you can't skip if you don't want to be left behind. Watch it, then read the full guide on graph engineering below.

Anatoli Kopadze

1,733,188 views • 3 months ago

Head of Claude Code: "85% of our engineers are running dozens or hundreds of agents. The way you do it is graph engineering." In 40 minutes he explains how a single engineer now does the work of a whole team, how far this has gone inside Anthropic and where it goes next. This is something you can't skip if you don't want to be left behind. Watch it, then read the full guide on graph engineering below.

Head of Claude Code: "85% of our engineers are running dozens or hundreds of agents. The way you do it is graph engineering." In 40 minutes he explains how a single engineer now does the work of a whole team, how far this has gone inside Anthropic and where it goes next. This is something you can't skip if you don't want to be left behind. Watch it, then read the full guide on graph engineering below.

0xRafy

83,051 views • 2 months ago

Head of Claude Code: "85% of our engineers are running dozens or hundreds of agents. The way you do it is graph engineering." In 40 minutes he explains how a single engineer now does the work of a whole team, how far this has gone inside Anthropic and where it goes next. This is something you can't skip if you don't want to be left behind. Watch it, then read the full guide on graph engineering below.

Head of Claude Code: "85% of our engineers are running dozens or hundreds of agents. The way you do it is graph engineering." In 40 minutes he explains how a single engineer now does the work of a whole team, how far this has gone inside Anthropic and where it goes next. This is something you can't skip if you don't want to be left behind. Watch it, then read the full guide on graph engineering below.

Codez

22,107 views • 2 months ago

New short course: Collaborative Writing and Coding with OpenAI Canvas! Explore new ways to write and code with OpenAI Canvas, a user-friendly interface that allows you to brainstorm, draft, and refine text and code in collaboration with ChatGPT. In the short course, created with OpenAI, and taught by , a research lead at OpenAI, you’ll learn to use Canvas to enhance your workflows. Canvas lets you go beyond simple chat interactions. It provides a side-by-side workspace where you and ChatGPT can edit and refine text or code collaboratively. This makes brainstorming, drafting, and iterating as you write feel more natural and effective. As the first major update to ChatGPT’s visual interface since its launch in 2022, Canvas gives a new, innovative approach to collaboration with AI. For instance, after writing the first version of your code, Canvas can review it and give suggestions for improvement. It can also help with debugging by adding logging, identifying problems to fix, and writing comments. In addition, you'll also learn what it takes to train the model for an interface like Canvas. In this video-only short course, you’ll: - Learn how to ask for in-line feedback and control the iteration of your work by directly editing selected areas of your text or code from the model’s output. - Learn how to access quick automation tools in a shortcut menu that allows you to modify your writing tone and length, enhance your code, and restore previous versions of your work. - Learn how to use Canvas as a research assistant tool with an example of asking the model to reason through the screenshot of a plot to write a research report, in which you can ask questions within the created report. - Ask the model to write Python code to replicate the graph seen on a screenshot image. - Go behind the scenes of how you can create a video game, such as Space Battleship, from scratch, edit it, and display it in one self-contained HTML file. - Get a real-world application example of creating a SQL database from the image of its architecture. - Understand the model training and design processes that power Canvas! Please sign up here:

New short course: Collaborative Writing and Coding with OpenAI Canvas! Explore new ways to write and code with OpenAI Canvas, a user-friendly interface that allows you to brainstorm, draft, and refine text and code in collaboration with ChatGPT. In the short course, created with OpenAI, and taught by , a research lead at OpenAI, you’ll learn to use Canvas to enhance your workflows. Canvas lets you go beyond simple chat interactions. It provides a side-by-side workspace where you and ChatGPT can edit and refine text or code collaboratively. This makes brainstorming, drafting, and iterating as you write feel more natural and effective. As the first major update to ChatGPT’s visual interface since its launch in 2022, Canvas gives a new, innovative approach to collaboration with AI. For instance, after writing the first version of your code, Canvas can review it and give suggestions for improvement. It can also help with debugging by adding logging, identifying problems to fix, and writing comments. In addition, you'll also learn what it takes to train the model for an interface like Canvas. In this video-only short course, you’ll: - Learn how to ask for in-line feedback and control the iteration of your work by directly editing selected areas of your text or code from the model’s output. - Learn how to access quick automation tools in a shortcut menu that allows you to modify your writing tone and length, enhance your code, and restore previous versions of your work. - Learn how to use Canvas as a research assistant tool with an example of asking the model to reason through the screenshot of a plot to write a research report, in which you can ask questions within the created report. - Ask the model to write Python code to replicate the graph seen on a screenshot image. - Go behind the scenes of how you can create a video game, such as Space Battleship, from scratch, edit it, and display it in one self-contained HTML file. - Get a real-world application example of creating a SQL database from the image of its architecture. - Understand the model training and design processes that power Canvas! Please sign up here:

Andrew Ng

128,180 views • 1 year ago