Code with Claude Opening Keynote

• AI model capabilities are advancing exponentially, but most organizations adopt AI on a linear path, creating a significant gap between what AI can do and what it's actively achieving.
• Developers play a crucial role in closing this gap by building innovative applications that translate cutting-edge AI capabilities into real-world solutions for users.
• Anthropic is enhancing its Claude platform with features like managed agents, multi-agent orchestration, outcomes, and dreaming to empower developers to build scalable, intelligent agentic systems faster and more efficiently.

• AI model intelligence is improving exponentially, with recent examples including Mythos discovering a 27-year-old vulnerability in Open BSD.
• Developers are essential in bridging the "gap" between exponential model capabilities and linear organizational adoption by creating practical applications.
• Anthropic's Claude platform is being updated to support advanced agentic systems with new primitives and infrastructure for speed and scale.
• The Advisor strategy allows combining a smaller, cheaper model for execution with a more powerful model for advice, achieving frontier quality at significantly lower costs.
• Claude Managed Agents offer a production-grade agentic harness that bundles best practices like memory management, enabling teams to go from prototype to production much faster.
• New features for Managed Agents include Multi-agent orchestration (fleets of agents for complex tasks), Outcomes (specifying success criteria for agents to iterate towards), and Dreaming (agents self-learning from past sessions to improve memory and skills).
• Developers are encouraged to design for future, more capable AI models, building ambitious prototypes and robust evaluations to capitalize on upcoming intelligence jumps.
• Anthropic is increasing rate limits for developers on Claude Code and the Claude Platform, including doubling Claude Code's 5-hour rate limits for pro, max, team, and C-based enterprise plans, and raising API limits for Claude Opus.

Ray tracers — A computer graphics rendering technique that generates images by tracing the path of light rays. JDK — Java Development Kit; a software development environment used for developing Java applications. API volume — The total number of requests or calls made to an Application Programming Interface over a specific period. Frontier models — The leading-edge, most advanced and capable artificial intelligence models available at a given time. Agentic coding — An approach where AI agents autonomously perform coding tasks, including planning, executing, and debugging, often going beyond simple code completion. Tool use — The capability of an AI model to interact with and leverage external tools, APIs, or systems to perform tasks. Context windows — The maximum amount of information (e.g., text, code) an AI model can process and understand in a single interaction or turn. Task horizon — A metric measuring how long an AI model or agent can operate autonomously and continue to improve its performance and quality of work. Scaffolding — Supplementary code, frameworks, or instructions used to assist an AI model in performing a task or reaching a desired outcome. Rate limits — Restrictions on the number of requests a user or application can make to an API within a specified time frame. Multi-agent orchestration — The coordination and management of multiple AI agents working collaboratively to achieve a complex, shared goal. Outcomes — A feature that allows users to define specific success criteria or a rubric for an agent, enabling the agent to iterate until those criteria are met. Dreaming — An AI capability where an agent reviews its past performance and sessions to self-learn, identify areas for improvement, and update its internal knowledge or memory. Advisor strategy — An agent architecture where a smaller, cost-effective model handles the primary execution, while a larger, more intelligent model provides guidance and advice when needed.

a band for office. A good morning everyone. It is such a pleasure to see you all. Thank you for joining us. When I think about why I'm here today, I go back to the first time I wrote a computer program and it worked. I didn't grow up coding. I grew up in the foothills of the Appalachians. I never built my own computer. I didn't even play video games. The first time I actually tried to build anything complicated was in my college computer science classes. This was so long ago we had to wait in line to log directly into the servers because they were the only thing powerful enough to handle our ray tracers. This might be familiar to some of you. The hum of servers, the smell of old pizza, coffee, and that very specific aroma of a windowless space made computer lab. I can still remember that feeling of hitting compile and waiting to see if my program worked. That feeling of joy, discovery, a little relief. And the excitement that I had made something that had never existed in the world before. That's what hooked me. And that's why I'm here today. It's so much has changed. What I could only get by waiting in line at a college computer science lab, that's available to anyone, any day of the week, anywhere in the world. No line, no weird smells, no barriers. Just that same feeling of excitement, joy, and relief. And I know a lot of you feel the same way. People say to me all the time, I feel like Claude has given me superpowers. It's one of my favorite things to hear. And we're seeing people use those powers. For instance, Scott McVicar runs developer inference stripe. One of his teams had 50,000 lines of scallop that needed to become Java before they could upgrade their JDK. The initial estimate was 10 engineering weeks. They used Claude and finished in four days. And sometimes speed isn't just about efficiency. It's about what's waiting on the other side. Felicia Krakuru is the co-founder and CEO of Binti. Her software runs the systems that case workers used, place kids in foster care. The paperwork, the home visits, the licensing process. This year her team used the Claude API to give case workers back hours they used to spend on paperwork. That took 20 days off the process of licensing a foster family. 20 days. It's not just an efficiency metric. That's a kid connecting with a family. And that excitement, joy, relief, that feeling of discovery, something I hear from everyone. I'm going to guess though that everyone here experiences it differently. Some of you are living on the frontier every day. Some of you are bringing along the people around you. And some of you came here because like me, you can feel the ground shifting under us and you want a view of what's to come. Trust me, I feel all of those things often in the same morning. I come to work with a plan and then I have to tear it up by lunch time because something new has happened. That sounds familiar. And you know, that makes sense when we step back and look at how fast these models are getting better. Anthropic, we talk a lot about the exponential. And I think that's what we're all feeling right now. Remember a couple years ago, the frontier of model development was something so good, it could write a decent email. And we were pretty happy about that. A year ago, we were standing on this stage. Opus 4 was the headline. And the idea that an agent could run for an hour without a human checking in felt like a stretch goal. But then six months ago, agents were running end to end overnight. So we'd wake up to finished work. And then last month, mythos read the entire Open BSD source tree and found a 27 year old vulnerability that had survived every human reviewer, every fuzzer, every static analyzer thrown at it for almost three decades. The jumps keep getting bigger and the intervals keep getting shorter. But even though model capabilities are improving on an exponential, most organizations are still adopting AI on a linear path. And that means there's a gap between what AI can do and what it's actually doing for people. Using that gap, translating model capability into something real people used to solve their problems, that's what developers do. That's what you all are doing. And we're seeing it happen. Year over year, API volume is up nearly 17X on the cloud platform. And on Claude Code, the average developer is now spending 20 hours per week running Claude. Now, like you, we've been shipping a lot lately. But we want you to walk away from today with a clear picture of where we're headed. So you can plan for it and ride the exponential with us. Let me say up front, we don't have a new model to unveil. Today is about how we're making our products work better for you. So you can close the gap for the rest of the world. And this morning, we'll show you what that looks like. First, Diane will talk about our foundation, the model layer. So share more about our frontier models and what's coming. On the cloud platform, we're shipping updates to Claude managed agents, outcomes, dreaming, multi-agent orchestration. And Angelin, Caitlin, will walk you through how the platform handles the infrastructure. So you don't have to. And on Claude Code, Cat and Boris will walk you through how you can use new primitives like routines to let Claude Code prompt itself, even when you're away from your computer. But all this comes back to you and what you're going to build. Because most people will never call the Claude API. They'll never open a terminal and type Claude. They'll experience AI through something one of you built on the cloud platform. Whether that's a designer exploring new directions with Canva, or a lawyer getting a brief out the door faster with LaGora, or a developer using any one of the world's best coding agents. So thank you. You all shape what AI feels like for everyone else. We'd never be able to build everything that people need to solve their problems. That's something only you all can do. And one way we want to show our gratitude is by sharing a little exciting news. As of today, we are increasing rate limits for developers on Claude Code and the cloud platform to help you keep building and closing that gap for the world. More specifically, we are doubling Claude Codes five hour rate limits for pro, max, team, and C-based enterprise plans. And we're raising our API limits considerably for Claude opus. We are making this possible by expanding our compute partnerships. We're partnering with SpaceX to use all the capacity of their Colossus One data center. And we're investing this directly into individual developers and small teams. Over time, we'll continue to explore every way to help you get the best out of Claude, including our existing compute efforts and even bolder bets. So thanks for being here today. Thanks for partnering with us to shape what AI looks like for the world. Thanks for giving people superpowers. Up next Diane who leads our research PM team. Thank you. Thanks on me. I'm Diane and I joined Anthropic back in 2023. And I've been a part of every model since Claude two. For those of you who are counting that's bringing 18 versions of Claude across Hikou, Sonnet, Opus, and now Mythos to users and developers like you. We wrestled with making Opus three great at adhering to JSON and also making it the best a writing long form code. With Sonnet three five new or as we all now finally know it, Sonnet three six, we talked plot to make and use a computer safely. And with Sonnet three seven, which had a tendency to be slightly to over eager, we figured out the right way to expose that to users and developers. So you could get the most out of Claude. This time last year, we used Claude four to be able to use thinking dials in a way that worked well and to address test time compute. And we haven't slowed down. In the last 12 months, we shipped eight frontier models to developers and users. Each one building upon the last allowing you to write better code and the products you build go further than previously before. The model layer underpins everything else you'll hear about today. And that's the bottom line. As model intelligence increases, your starting line moves forward. And you could do more than ever before. We talk about the exponential a lot at Anthropic. You heard it a little bit from Ami as well. For me, the exponential means that as model intelligence increase, the use cases you can build and deliver to your users increases exponentially. For example, agentic coding is far more impactful than code autocomplete. And in this way, new products and new experiences create new markets and grow the pie for everyone. In research, we don't think about the exponential as sweep and numbers going up. It's also about creating and tracking capabilities that previously didn't exist until we designed and created them. Tool use, computer use, thinking that adapts to the problem. Agentic loops that hold a plan over hundreds or thousands of steps. And long context windows that teach Claude knowledge that it previously didn't have. And these capabilities don't just stop at code. Today, clock and generate and iterate on visual designs, analyze and create complex work deliverables, and also navigate business domains you might be a part of in open-ended and big-us-fascions. That's because the model intelligence, the core foundation, has gotten smart enough and strong enough to support all of this. When you're building on Claude, you're building on the model family that created these capabilities first and has had the most time to make them reliable. Let me make that concrete with our latest model, Opus 47. AMP, the coding agent, moved their entire smart mode onto Opus 47 because it scored the highest on their benchmarks and they were able to simplify their tooling, change your scaffold because the model no longer needed the help. Rakuten ran it on their benchmarks and resolved three times the number of production engineering tasks than they previously could. And finally, into a cell Opus 47, identify its own logical faults during the planning stage, figure out what was wrong, backtrack, resolve it, ultimately leading to faster and cleaner execution. The day after we launched Opus 47, we launched Claude Design by Anthropic Labs, one of my favorite launches this year. Already, people are building production interfaces with a combination of Claude Design and Claude Code. This is because Opus 47 has a real taste for visual design that right nuances to show while adhering to your design principles. And we also hear from everyday users that people like to use Claude because it understands a full assignment and can figure out when to push back and question assumptions. At the same time, as each of us already know, having built on these systems, the models are unfinished and their works in progress. They can still be stomped sometimes by very basic things and also lose the thread when you introduce a lot of context. That's what makes this exciting and thanks for being on this journey with us. Here's a little about what we're working on and what's ahead. First, higher judgment and better quality co-taste. This means versions of Claude that you can trust with complex, autonomous, engineering work. Second, context windows that feel infinite when combined with high quality memory. So it feels like you could do a long-running task while getting better results. And finally, multi-agence coordination, powering teams of agents and instances of Claude that collaborate on big goals that are too big for any single instance ever could. The way I think about progress in model intelligence is task horizon, which is a measure of how long a version of Claude or a model can work autonomously while improving on its deliverables and the quality of its work. Last time this year, models can work for minutes. Now, most of you and I probably have agents that are running for hours on end. And tomorrow, we'll have agents that are proactive, always on and know what to work on without losing the threat. So what do we as developers make of all of this? The exponential will keep improving. And you need to build for emerging capabilities, not just for today's versions of Claude. This is because new models would be far more capable than the ones we have accesses today. It used to be that we have to build scaffolding to keep every version of Claude up. And now scaffolding is there to actually amplify model intelligence. Used to have to design complex iterative loops, give it the right tools, figure out how to do retrys. And now all of that can be folded into the right thinking and the right execution right within the model. You are already seeing where this can go. Opus Preview, Missos, is the next point of that exponential. And it's not a small step. Therefore, how we all work with model and Claude need to change. Here are some things we think about at Anthropic. First, you need to design for the next version of Claude, not just the current one. We've seen countless times that the developers who when are the ones who optimize their architectures to absorb the next intelligence jump, not just today's incremental accuracy. This means maintaining and creating harder e-vows, building ambitious prototypes that you don't think might work today. Because that's how you'll notice when the exponential is improving and moving under you. That's something that previously didn't work. All of a sudden starts passing. That's a sign that you probably have something magical to give to your users that didn't work before. And here is what the teams that are getting the most out of Claude have figured out. Model upgrades are a business opportunity. The teams that are getting the most out of Claude models are the ones who make upgrade cheap. This is automated e-vows, simple scaffolding, and ambitious prototypes and uses of capabilities that others haven't imagined yet. We believe that the exponential on slide one is going to keep looking like that. As model intelligence increase, US developers have the chance to make a head start to experiment with building new use cases, creating exciting new products for your users, and ultimately creating new designs and markets and ultimately growing the pie. Everything Caitlin and Angela are about to show you will give you the tooling to make all of this possible and come to life. Thank you so much for being here. So model capabilities are on the exponential. But businesses are still operating on the linear. And so as a business, it's never been more important to make sure that you're really able to harness the power of that exponential. But what's stopping businesses from really snapping to that? Well, it really boils down to two key problems. The first one is getting the right outcomes. Getting the right outcomes is still too difficult. You have to be able to do a lot of prompt optimization, tool construction, harness engineering. There's still a lot of work that it takes to really steer the model to exactly what you need to go. That's right. And the second problem is you want to ship fast, but you want to ship scalable at the same time. Everyone in the tech space is moving insanely fast right now, and you've got to keep up. But to win, you need quality too. It's really easy to ship prototypes, but it's really hard to scale in production. So we've built a cloud platform to give you everything you need to get those great outcomes and to ship with speed and scale at the same time. The platform comes with API primitives that are tuned to Claude models. It gives you infrastructure to build and scale agentic systems. And it gives you controls to operate those systems. That's right. So if we go back to our problem statements that we hear all the time from different businesses, one of the most common ones that Kaelenite here all the time is how much businesses need high intelligence, but of course at lower cost. So one of the ways that we're solving this is with the advisor strategy. This is really easy to implement. All you have to do is update your tools array inside the messages API. And what we're doing is that we're actually providing an agent architecture that splits execution from advising. So in execution, you can pick a smaller model. It'll be a little cheaper. But then that small model when it needs advice and what to do next, it can actually reach out to a bigger model for help. Yeah, so in practice, this means you could use a Hikou or a Sonnet class model to execute an opus as an advisor. And when we ran this with Sonnet executing and opus advising, we saw Sonnet perform way better than Sonnet alone. But more importantly, we saw Sonnet perform even more cheaply than Sonnet alone, because Opus was able to advise it to get its work done better. A great example of this was EVE legal. EVE legal used the advisor strategy. And they told us they got frontier model quality at five times lower cost. Yeah, and that's awesome. We love stuff like this, because you can go ahead and use this in things like a freemium model. When you offer these kinds of freemium experience to your users, you have to be conscious of the costs that you're going to incur. But obviously, you want to make sure you have a good experience for them. It's also really great for areas where you have an extremely high volume amount of workloads. And of course, you'd have to be a little conscious of your ROI. So that's all great. But what about speed and scale? Those two things that Katelyn mentioned to be really difficult to achieve at the same time. Well, most recently, we introduced Clawed Managed Agents. Clawed Managed Agents is an agentic harness that's paired with production grade infrastructure. Teams are able to go from prototype to production and literally a matter of days. The teams that we've worked with have been able to ship literally 10 times faster with managed agents. Another great thing with managed agents that we love is that it bundles in a lot of the best practices out of the box. So for example, when you build an agent, one of the best practices that you want to make sure that you do is, of course, give it memory. That way, the agent persists user preferences and it kind of remembers closer to what you wanted to do every single session. It's a little difficult to build memory. And so this is an example of a best practice that we actually just bundle in out of the box and it's automatically tuned for Clawed. And we want to make sure that everyone hears this. When we do give you memory, that memory is ultimately yours. So you can take that and import it wherever you'd like. So one of our favorite examples of someone who built on managed agents was notion. Notion wanted to build for speed and scale at the same time so they chose to build on managed agents. And they built the ability for you to fire off Clawed agents directly within their product experience for long running complex autonomous tasks. Yeah, and we love that feature. That's super cool. All right, well, today we are upgrading Clawed Managed agents with three really powerful features. We're going to be introducing multi-agent orchestration so that you can actually create fleets of agents to solve really complex tasks. We're going to introduce outcomes which allow you to specify exactly what success looks like. And then Clawed will literally just iterate until it gets it done. And we're going to introduce Dreaming. And this one we're really excited about. But with Dreaming, Clawed is actually able to self-learn. It's able to actually inspect over its previous sessions, figure out skills that it missed, less than this should have learned, and actually apply those directly to memory on its own. But instead of just showing these all, talking about all these with you, we're actually going to show you live what these things look like. So OK, let's do that. Let's do it. So Caitlin and I have been inspired by some of the announcements earlier today. There's greater API rate limits for Opus. And we've been hanging out with a particular space company for most recently. So we've been inspired to create a little startup of our own, a fictional one to be clear called Bumara. And with Bumara, we decided, why don't we build a gentics software that helps us autonomously land drones on the moon? And we really care about speed and scale at the same time. So obviously, we are going to build this on Clawed Managed Agents. Exactly. So let's say we line up our first customer. And this hypothetical first customer wants to land drones on the moon to mine for hypothetical materials. And this is a big ambitious job. And despite all of our dreams, we're not actually aerospace engineers. So we're going to need really awesome agents to get this work done for us. So we're going to integrate all three of the new features that we just talked about. And we did this for our first customer. And I'm going to show you using the Clawed API CLI, how we actually set that up. So first things first, this is a big job. So we actually want multiple agents to help us get this work done. So I'm going to go ahead and show you the agents that we actually have set up for our customer. The first one we have a commander agent, and really the commander agent's job is to make sure that this whole mission goes well. Then we've got a detector agent. And the detector agent's job is to make sure that we're actually finding the sites to land on that will have high quality mining materials. And then we've got our navigator agent. And the navigator is making sure that we're landing our drones safely and flying them to their destination. So I'm going to go ahead and actually set up our commander to be a coordinator of the other two agents. And when this is running, what's actually happening is that the commander is spinning up a session. And then for each of these sub agents, they have their own independent threads so that they have independent context windows. This is a very intentional design. And we found that by doing this altogether, then merging in all the results, we get better performance. Exactly. So that's multi agent. Let's go ahead and integrate outcomes. So the way outcomes work is we want to make sure that our customer, which has very specific criteria for what they want to accomplish, can define that criteria. And then we can provision a greater agent that actually makes sure we get that outcome. And so outcomes actually just start with a pretty simple markdown file. So here you can see a markdown file, again, really, really simple. And it just kind of outlines this criteria that shows us whether a run is successful. So we want our drones to touch down softly. We want them to land on clear ground. And pretty importantly, actually, we want to have enough fuel and reserve so that we can get our drones safely back to Earth. So in order to actually set out this rubric for our outcomes, I'm going to go ahead and send an event to our session that defines this rubric as our outcomes. Yeah. When this is running, like Caitlin mentioned, we actually create a separate greater. And this greater agent is evaluating across the session as to whether or not in each run, we've actually met the rubric that was specified. Now, of course, it could one-shot this, but more likely than not, it probably needs to iterate over a couple sessions to do it. And as Caitlin has highlighted here, you can specify the maximum of iterations you want to allow this to do. So we've integrated multi-agent, we've integrated outcomes, and it's time to test. Our customer gave us some data on six hypothetical sites that they might want to land their drones on for us to run some simulation sessions and see what happens. So I'm going to pop over into the Lumara's dashboard, where you can see that I ran a simulation against these six sites. Yeah, and this is pretty good. I mean, this is a one-shot with our whole system. It's got the multi-agent architecture. It's got the outcomes feature integrated. And you can see here that it's solved four out of six sites correctly. But clearly, it could have done a bit better on sites three and sites four. And like any two good founders, we obviously want to hill climb on this system. And normally, hill climbing is a pretty difficult process. You have to put a lot of work together to go and do that. But we're going to show you how we are hill climbing on this with just dreaming. Yeah, so we ran this simulation yesterday. We weren't quite happy with our results. And we came into the Claude Developer Console into our dreaming interface. And you can see I can actually just hit this little button that says, dream. Choose a memory store where a dreaming agent can go and look over all of those past simulation sessions and write its learning to memory so that all of our new sessions can actually reference those learnings in memory to do a better job. So I did this last night. And this is our dream that ran. And you can see that we wrote a bunch of stuff to memory, which is awesome. And crucially, most importantly, the agent actually chose to write a descent playbook so that all of our additional sessions that we run going forward will have this playbook to reference, including all sorts of heuristics from the different missions that it ran previously. This is like a really robust playbook of a whole bunch of information that we can go ahead and use. So this ran overnight last night. And I popped back into Lumara's dashboard this morning and ran a new simulation now that our system is upgraded. And that's awesome. We were able to actually hill climb and not progress on any of the ones that we cared about, but the two sites that could have improved have actually improved. And to hill climb on this, all we had to do was just have Caitlin press a button in the console called Dream. All right, awesome. Let's wrap up. And everything that we showed you here today live in this demo is available on the Claude platform for you all to build on. Multi-agent orchestration, outcomes, and dreaming are now making the Claude Managed Agents primitive so much more powerful so that you can use it to construct deep, powerful, agentic systems that scale. Whether you're landing drones on tons of the moon or you're building the next big business, Claude Managed Agents is here to help you construct the agentic systems that you need and solve the problems that you're looking to solve. Now we'd love to pass it on to Kat and Boris, who will show you how Claude Code is making it even more fun to build that developer. Thank you. Angela and Caitlin just showed you how the Cloud Platform closes the gap between what models can do and what agents' business is ship. We have a related challenge on Claude Code. We also want to close the gap between model capabilities and what every developer can actually do with them. First, I just want to thank all the developers here in this room. Thank you for trusting Claude Code on your production databases back when Sonic 3.7 was our frontier model. And what our product was a bit rough around the edges. Your support is what makes our team so excited to come in every day and make Claude Code even better. Let's start with why Claude Code exists. Software development is being reinvented in real time. The mission of Claude Code is to close this gap between the great ideas that you all have and shipping a product to the market. And the way that we enable this is we build tools that elicit the frontier intelligence from our models and we make them accessible to every builder. And we don't think of ourselves as having a finished road map for you. We think of ourselves more like mountaineers, kind of like climbing alongside you into terrain that none of us have explored before, learning together what works as we go. And we're growing with you. We're growing with increasing AI capabilities. And we're navigating these new challenges together. I still remember a year ago when I would give Claude Code a task and I would carefully review every single edit it was trying to make. Every single permission prompt giving it really detailed feedback on what I liked and what I didn't. And just like holding its hand every step of the way until the result was good. I remember some of these tasks would be like 100, 200 permission prompts until I got the final result. And now most of you are running in auto mode. You're delegating permissions to Claude. And you're checking in after Claude has done a lot of its work and has a PR for you to review. Over the last year, we've expanded the number of ways that you can use Claude. We started with the terminal, then we launched the IDE, and now we have desktop. We started with the CLI. This is still the interface for power users who want a minimal text interface, who want all the latest customizations and the most control. Then we added IDE because a lot of you actually want the same powerful agents, but you want to follow along with all the code changes that it's making. And then based on all of your feedback for something a bit more visual, we knew where we had to go next. We launched our newest surface called Code on Desktop. It's a surface that's designed for people who want this full screen graphical interface, built-in preview so you can watch as Claude develops your app, a sidebar control plane for all your agents, and the ability to render images and rich outputs. We've built desktop to be a control plane not only for your local sessions, but for your remote ones as well, with visual indicators for which agents are stuck and which ones are ready to go. The IDE and the desktop app are built on the Claude Agent SDK, the same SDK that many of you are already building on. Many enterprises have adopted Claude Code tools wall-to-wall. And in a traffic, this has driven a 200% increase in the number of PRs per engineer, while keeping the same code quality bar even as our engineering team has scaled substantially. Together with you all, we're discovering and redefining the future of what software engineering looks like. We're embracing these new challenges by embracing automations powered by Claude to overcome each. I'm going to walk through a few of them right now. Here's the feedback that we heard from our users and what we've built with the help of this community. We heard from you that you want to spend less time on code review. So we shift code review that deploys a team of agents to catch critical bugs on your behalf. Thousands of companies use this every day, including all internal and through our team. We heard from you that you really want to code on the go. So we launched remote control, and we added Claude Code to the iOS and Android Claude apps so that you can fire off a task from anywhere. You're no longer walking around with an open laptop, balancing it, trying not to fall. And you're no longer stuck at your desk. You can now go to a park, touch grass, and still code. We heard that you're spending a lot of time babysitting PRs, fixing FWAKY CI tests, addressing code review comments, resolving all the merge conflicts. So we added auto-fix. It just listens to all these events proactively puts up fixes so that your PRs are always green. We heard from you that you're kicking off Claude Code tasks on new tickets and new customer bug reports. So we thought we should build routines. So we have routines, and if you configure once, listen for web hooks, API events, or run on the schedule. And I'll just kick off Claude Code automatically for you. So instead of you having to manually kick things off, Claude will handle it. And last, we heard from you that you're launching so many features that your security teams are having a hard time keeping up. So we built Claude security. It scans your whole code base overnight, and it can kick off Claude Code to address the vulnerabilities that it finds. All of these primitives compose together. And this helps all of us together adapt to the future of what engineering looks like. Everything I've covered is something that you can pick up today. It's been especially exciting to see how a range of companies have taken these tools and adopted them at the scale of entire orgs. First, I wanted to share about Shopify. They power e-commerce for millions of merchants worldwide. And they've imbued AI across the entire engineering org and changed their culture. They're using Claude Code across the company, both on engineering teams but also non-engineering, so design, product, data science. They're building a directly into their platform and standing up tools at scale. Andrew McNamara is the director of applied AI at Shopify. And in his words, the speed is just crazy. Claude-code has completely transformed how they build internal tools. Another example is Mercado Libre. They're Latin America's most popular e-commerce platform. They serve over 100 million buyers. Their org is 23,000 engineers, and everyone runs on Claude Code. When that happens across an org, the work itself changes shape. Engineers are pointing agents at tech debt that people haven't touched in a long time and people don't have time for. It's reviewed more than 500,000 PRs with human oversight and modernized more than 9,000 apps. Oscar Mullin, who leads technology, is aiming for 90% autonomous coding and fully of agent-driven PR loop by Q3 of this year. And we hear this from many others across the industry. The detail I love the most here actually isn't this number. It's not a lot of the managers and VPs we talk to are like getting their hands dirty in the code base again. Claude-code is putting coding back in the hands of people who've spent the last decades on roadmaps and reviews. And now, they're back building. We see this across the industry. Millions of developers are getting more product shipped at a higher quality than before. Now, let's see what this actually looks like in practice. To take you through it, please welcome the head of Claude Code Boris Churney. Thanks, Scott. Can we do a quick selfie? True. All right. Before I jump into this demo, I just want to mention something. Everything that we're showing today still feels magical to me. And I work on Claude Code every day. Even in Anthropic, we share screenshots back and forth of the cool things that people are building with Claude and things that people are doing in the wild. And honestly, I just feel excited to be on this journey together, discovering all of this. So today, I'm excited to share a few more examples of what this looks like. Unfortunately, we can't all work in the winner-tron business. So for this demo, let's imagine that we're an engineer at Acme Pay. And it's a payments infrastructure company. We're going to start the Claude desktop app. And we're going to start by working on a single task. In this session, Cludds working on adding refunds to Acme's merchant dashboard. It's building a full implementation, item potency. So a duplicate webhook doesn't double refund a merchant. There is multi-currency handling across all the regions Acme serves and audit logging for the compliance team. It rates the implementation, and it's going to verify its own work. Cludd pulls up the merchant dashboard. It triggers a refund. And there's no success toast. That's a real edge case. Cludd sees the failure. It traces a back-to-race condition in the optimistic update. It fixes it. And it's going to verify that it actually works in a browser before it calls the task done. Now, let's zoom out. This session wasn't running alone. It's actually one of many sessions that were all running in parallel and being managed in parallel. In the Cludd desktop app, you can now see all your Cludd code sessions, which ones are running, which ones need your input, and which have PRs that have already been merged and closed. Synchronous coding is now just a slice of what's happening at any given moment. And we think that going forward, a lot more code is going to start to be written in an A-sync way. And this is why we keep talking about verification. If Cludd can check its work, you can just let it run. Well, you work on something else, and you come back to a fully working result. And for me, personally, a lot of my code nowadays is written by routines. I'm not the one doing the prompting. I'm the one creating a routine that does the prompting. For engineers in the room, think of it like a higher order function. Routines are a higher order prompt. For example, the refund session that we just hooked at. A teammate filed a GitHub issue overnight. A routine watching the repo picked it up A-sync, and then kicked off the work in Cludd. With routines, developers can set up A-sync automations and wake up to peers that are ready to merge. Here's our routines view. Routines can be run on a schedule. They can be kicked off by webhooks, or they can even be kicked off by arbitrary API calls. You can run them locally on your machine, or on remote Claude compute. Let's look at one more feature. This is CI AutoFix that Kat talked about earlier. And what it's doing is it's watching the PR, the prior session just opened. It's job is to babysit the PR to get it all the way to production. It's going to auto-fix any comments from CoderView and SecurityReview. It's going to auto-fix CI, and it's going to auto-rebase if there's merge conflicts. And look at what just happened. CI flaked on the network timeout. The routine woke up, it diagnosed it as a known infer issue. It retried the job and outscreen. And actually in the Claude Code Base, we have it not just retried. We have it fixed the root cause every time. Then Shadeer who owns the PR is never going to see a red X. And that work is off their plate. That's the shift. The default isn't, I'm going to prompt Claude Code. The default is now I will have Claude prompt Claude Code. Everything you just saw is available today, including routines, the latest updates, the Claude desktop app. We're excited for you to try it out and let us know what you think. We hope these features continue to close the gap between your ideas and shipping products. And that's really what every talk today was pointing out. Diane's capability curve, Antioen Ketlin's agents that grade and improve themselves. What Kat and I just showed you. These are three layers of one story. The capabilities are ready here. The gap left is how fast we put it to work. I encourage you to spend the rest of today exploring these layers. Research talks, if you're evaluating the models, Cloud Platform sessions, if you're building for your users, or Claude Code workshops, if you want to learn more ways to bring Claude into your day-to-day development work. Diane, go deep and start building with us. Thank you.