What's new in Claude Code

Good morning, London. Good morning, folks. How's it going? Yeah, there you go. That's the London energy we're we're looking here. So, yes, uh my name is Ralph. I'm part of the technical staff at Entropic and in my role I work with partners and customers all across Europe helping them to build on and with cloud and when they asked me to present what's new in cloud code I was already prepared to do like a 7-hour session straight with everything that the team has been releasing the last couple of months because if you have been following the change log there's quite a lot of things we we have to cover but luckily for you and for me uh the veno doesn't have another day extra for us to have an event and we created a sub subset of features that uh we released in the last few months. So let's take a look into the two main categories that we are going to cover today. Starting with the developer experience because yes we know that you're using this tool more and more every day and we want this to make to make you a pleasant and convenient experience while you're using the tools that you love. And the second bit we are talking about autonomy meaning we are empowering claude to do more without interrupting you when it doesn't need it. So the feature functions and features that let claude do the work on its own. And last because again the change log sometimes looks like more a news feed with the amount of features we we are releasing. I'm going to point you to where you can find more information, more details, and keep yourself up to date with the latest and greatest. All right, so let's start with the first one because even though cloud can do a lot on its own, we care a lot about developer experience and having this tool that is convenient, nicer to use and pleasant to interact every day is paramount for everyone at Entropic. So start with the first functionality which is remote control. Can I get a show of hands if any of you have used remote control before? Yes. Very small fraction with a big audience. Remote control is a very nice feature that lets you start a session on your computer and take this on the go from your mobile app with cloud or in any browser in any other device. Think about it dispatching a session and go run some errands walking the dog. That's something I do a lot. Or maybe even a bio break if you want. Let's stop doom scrolling and start like cloud coding whenever you want. And it's a really convenient way to dispatch a task and interact with cloud every time it needs to come back with a prompt. You receive notifications on your app whenever clouds needs an input. And also is pretty easy to set up as and as you saw in the audience, not a lot of people are using it. So why don't we take a look in a demo of how simple it is to set up. So I'm going to start with a demo around. So what I have here on the screen is on the left hand side I have my session running on cloud.ai. So this is on on the on the website and also on the side here I have my cloud session that I usually have. So what you can do with remote control is just start with a comment. Actually let me make it bigger for you. remote control and just press enter. Now your session is active in the web and on your mobile phone and you can start saying, "Hey, G uh just a simple prompt. Give me 10 jokes about the London weather because that's what's happening today. It's a joke. It's spring and we have like this raining outside." And there you go. It started in there. And if you see on the left hand side, I already have a session in here, which is kind of with a weird name, but I can take over my session from on the go on the website. What I can do as well, and something that you also should be doing is that you can rename your session for if you don't place any arguments here, cloud will make sense of what you're doing and give it a name. Like if I press enter, it will tell me, oh, this is a London rain jokes. And now you know from your mobile phone that that's what the session was was about. And you can keep on online. So I say, "Okay, another 10 jokes about the tube." And there you go. You can have the back and forth between your session on the go and your session on your computer. All your tooling, all your dev environment, everything that you're doing on your computer is accessible from the both the web UI, but also from the cloud mobile web app. Very neat feature, very nice functionality. Just start using today. And if I can give you a pro tip that we use it on our side, you can set up on your cloud settings.json file for remote control to always be on. So every session is a remote control accessible because you never know when your puppy needs to go for a new walk or when nature calls. Right. All right. Let's go back to the slides and go to the next feature. And yes, I was supposed to ask for a show of hands, but I'm seeing a lot of people smiling and nodding that hey, this is something that I was expecting. So yes, we finally have it a flickering free experience. And turns out that in our previous uh our previous approach for appending data and new information into the terminal was a bit tricky to get right because when you have like a big scroll back on your terminal every time you want to append something new depending of what is it is that something it might cause the whole repainting of the terminal and that's why you see the flickering. But now cloud code has a new full screen mode which actually virtualizes the whole scrollback of the terminal. So you have cloud not only inside your terminal cloud code is the terminal now whenever you want to to interact. That means that scrollback that caused all the flickering is now virtualized. We are only rendering the parts of the screen that you are actually seeing it. Meaning even on very long sessions we can keep the memory usage super flat by virtualizing that scrollback and virtualizing this experience inside cloud code full screen. You can also we can also start playing with other types of functionalities like for example clickable elements inside the terminal. So now you can have an option to both expand uh text and also other types of buttons that are inside the terminal. But better than myself talking about functionalities inside the CLI. Let me show you in a quick demo as well. So I have here my cloud codes as you usually have and as you see it started in the regular uh regular mode not not a full screen one but now you can come with a slash command TUI that stands for terminal user interface and you have just the option now to pass the parame parameter full screen. But with this one, cloud will reload and now you are in a flickering free rendering experience. Now the full terminal is cloud code. And now you can I can give just two examples. So let's say uh write me a file with 10 facts about Europe and another one with 10 facts about the UK. And while your cloud is doing all of this, you're going to see that normally what you have is like the part portions of the file that is going to be rendered. And that's you can only see like a couple or a couple lines. But now because of the clickable options, clickable experience that we have. You can already start expanding some of these options. So I can already click here for example and open the whole 10 facts. And also you can see here down the bottom I have an option to go way down to the bottom of my uh my conversation. In fact, if I just put here uh another instruction, write me a paragraph about the UK. I'm very inspired by the UK today. And uh you're going to see that this option here if we're going to the end now it's updated with hey, you have a new message right at the bottom. So you can click it and go straight down. So with this experience with the teams are guaranteeing a flickering free experience whenever you're working with cloud code. Uh I invite you to try on and just like the other the other functionalities we discussed you can enable this by default. So every new session comes with a full screen UI and that's how we are mostly doing ourselves as well. All right, up next we do have a whole UI refresh on Cloud Code Desktop. And for those of you that have used the Cloud Code Desktop in the previous versions, like a couple months ago, and saw it, yeah, not for me. Not something I use. I rather use the CLI. I'm with you. A lot of us do prefer the CLI for most of the things. But I do invite you to come back and take a second look because the team have revamped completely the experience in the desktop app and there's a lot of new functionalities that you can use. You saw a little pick in the first keynote and we're going to see a little bit more in a in a in in just a moment but we are seeing that other users are preferring the desktop app for very specific tasks. I don't think we are going to expect you to use this on your full-time job like the the 8 hours of the day or maybe 12 hours of the day depending how much you're building. But for some specific bits, the desktop actually provides a much better experience. But let me give you a walk through in a quick demo. So I have here my desktop app. Let me just make this a little bit bigger. And first thing that you're going to notice is that on the left hand side you have an option with all your sessions, right? Uh and from the sessions you can start grouping them in different categories. And what I like a lot is to group them by projects. This will group every session by what GitHub repo or what repo you are you are working on. So if I just click over here, you're going to see that I have three sessions on my scholar demo. The other ones I have another projects working on and these are grouped. So you can for the ones that are parallel coding using a lot of sessions you can really see uh which one pertains to each each project. uh the other bits as well. Let me take here some for example one of these sessions that I was running. Uh you have the option on the top to take a look if you have a a conversation you can take a look at the plan that spin up that conversation. For those of you that use it plan mode and want to find a step-by-step implementation steps of a functionality for example you have the option to take a look really easily from the desktop app into what the plan look like it for that feature. So for example, I was creating here a dart mode for this application. The nice thing about the this UI is that you can start appending comments on it. So if you select any part of that plan that you didn't like, you can just leave a comment to it. This will be pushed back to claude for making that fix. If we go even beyond that, so let's say for example, I have here one application that I was I built and I have a lot of diffs on it. So that's another point as well. You can start seeing the diffs of the of the files from that pull request. Let me close this file one. And you can start appending comments as well for your code. So you can say okay uh claude explain me this line for example. And what's going to happen is that cloud will take that line in particular and start uh and start as checking what is that uh what is that particular particular line and giving you an explanation of that piece of code. So oops let me close this one. Uh yes what else do we have on the desktop app? Yes. As as Boris also mentioned you do have the GitHub integration quite neat on the bottom. So you can append fixes into it and even going beyond check for your files of a particular of a particular develop development project that you are doing. So as I was saying this is not only the diff but I can take a look at the files themselves. So if I click over here and I have the full files of that project. So yeah take a look explore a lot more. Uh like everything else we are doing with the with cloud code we are very open for your feedback. So experiment, report bugs, report new features and suggest what direction of travel we should be going. And yeah, with that, let's go back to the slides and we can cover well, we cover a little bit on the development experience bit. And now I want to talk about the autonomy part because each of the functionalities that I'm going to cover next have one major root cause. And do you know when you started a long running session or what do you expect was a long running session on cloud code just to come back and see that cloud got stuck it into maybe uh prompt authorization request or maybe got the wrong building comment for example just something silly that you thought oh claude come on you could do this without me I don't you don't need my my interjection on this one. So yes uh models are getting much more capable as we saw it in the previous session and cloud is getting a lot smarter into assess when does it need your input or not. So yeah everything that we are going to show in this part of the session is to show you that is it is is your time to get more confident in that claude can assess when does it need to bother you for any of those those points that I mentioned before. And the first one with a new mode that we have in cloud code which is the auto mode. Auto mode is that for that specifically case when you are working think put a prompt into cloud and think hey okay this is going to run for for some time and come back is that an authorization request hey can I read this file for example do you authorize me access this folder. So that can that was quite frustrating and with auto mode those days are gone. What auto mode is doing is first leveraging the high capability of the latest models as well to assess if a situation is destructive or not because what auto mode does is that for every time where otherwise claude we will stop and go to you and say hey can I guess permission for this bit auto mode check that with two with a classifier that checks two things so the first thing is is this action destructive am I going to regret this down the line so yeah that's the first check the second check is pretty much uh does this look like a prompt injection? So yeah, this is this part of the the the situation looks like that is going to inject something on my prompt. So if the checks passes, so none of this is true, Cloud takes the action on your behalf. So it doesn't stop and doesn't it continues running. If any of those checks fails, what happens is that cloud will try to find a workaround. maybe a scenario there's another path that we don't have to go and ask for those this particular permissions and don't have that destructive way that we are going uh and if that case is not as well possible then cloud will come to you and say hey I need your permission to execute this bit so this gives cloud a lot more autonomy and don't bother you when you don't need to be so for example we value a lot your time and cloud should earn your time that's that as well Boris was talking about a synchronous coding that's exactly the type things that we we can start leveraging it. Let cloud run and just bother you when you when you actually need it to be uh consulted for. Yes. The next one is work trees. And can I get a show of hands if you ever use a work trees on your day-to-day? Yes. Oh, that's that's much better. Yes. Uh still I mean I would love to have the the whole room working but work work trees are your friend whenever you want several clots to work on the same project same repo and you don't want claw different clouds to step on each other's feet. The idea here is that a work tree is a copy of your project in a segregated subdirectory that is only assessed by one cloud session. Actually work trees existed way before cloud code and they are supported by cloud code since the early beginnings. But to be honest, it was quite tricky to get it right because you had to manage all these different directories. Work trees are kind of ephemeral if you start working on on something and stop it. So managing all of that yourself was something that was quite tricky. But now it's super simple because cloud code now has this native support for work trees. Whenever you want to start working in a new feature that needs to be parallelized amongst several sessions, you can just start your session using cloud-work tree and cloud will copy that repo to a segregated directory and work on it independently. You can have multiple clouds working on the same project in different features without then checking and editing the same files. If you don't if you're already in a session for example and don't want to start a new cloud code session, you can just ask cloud to create a work tree for you. You will also see that in other UIs that we're going to present uh the desktop app for example and the other one that we're going to show in a moment work trees are native to it. So if you start a new session in the desktop app for example there's a flag already saying hey this session is going to start a new work tree. So you don't have to manage yourself. So yeah work trees use it they're a friend and yeah if you are a par parallel cloud code user like a lot of us this is there's no other way to to get it better. Yes. Okay. Auto memory. That's another nice feature that is giving Claude a lot of autonomy as well. How many of you think that have thought that every time you starting a new session on cloud, it looks like you are working on a blank slate. You need to tell cloud the same things a lot of times and even though you have like your cloud. MD file and some instructions to get it right, there are some little things that it's never there or most of the times are never there. Automemory fix that because automemory is something that cloud does automatically. So it will check for some notes and some some things as your session progresses and take notes in the back. So think about it your coding styles some architectural choices your debugging insights for example the ways that only you know how how how it works. Cloud will assess that and save this in a memory MD file. It's not going to update that file in every session. It's really have the discerning capabilities to understand, oh, this is something I need to remember for the for the future. And it will load for every other new session together with your cloud. MD file. And you might be asking, yeah, but we have cloud.mmd files. We have memory.mmd files. What are why do we have the two and what are the differences? I think an easier way to understand, imagine that the cloud.md is your is the onboarding document you give to claude on the first day of work and the memory. MD file is the notes that CL is taking while you're actually doing the work. So one is a manual, the other one is a note takingaking. Well, the other thing as well is that the memory MD file is a very short file. It's not like a big one is mainly an index to other files with specific memories itself. So it's not bloating your context. Actually we are explo we are leveraging progressive discovery because every time cloud needs for example to get access to your debugging memory it get access first to the index find the file for the debugging memory itself and then it loads in your context so you don't have like this bloated context uh in in in in every session. Other thing as well, all the sessions that are part of your project, all the work trees in that project as well leverage the same memory and uh and also the memory files do not leave your computer. It's not something that's pushed to your GitHub. Uh it's not something that lives in the cloud. So it sits on your machine. Last bit, you can definitely audit and check for those memory files by just typing /memory and you can see the whole directory that cloud is managing for you. Okay. All right. The next one, and this one happens with me a lot. I happen to work with partners and and customers all across Europe, as I mentioned, and in a lot of these conversations, people ask me, hey, how is the entropic developer team using cloud in their day-to-day? And of course, there's nothing not I can not a lot I can talk about, but this one I can definitely do because this is a practice the teams have incorporated, tested, saw it was working, and baked it into the product. So code review is an automated review process for every PR that you you create and it's a process that is both multi- aent and multifaced. So imagine that every time you create a PR claude spun up a team of different agents to assess different parts of that PR and uh these agents are checking for different stuff. Some are checking for errors. Some are some some are checking for bugs. Some are checking for vulnerabilities, logical errors, for example. And based on all of those findings, that's the first phase. There's a second phase which will actually assess all the findings from those agents against your actual code. So we can actually make sure that those findings are actually real. In that sense, we can speed up the findings of those errors much quicker. So you will find errors or logical uh logical problems that will take hours for you to discover now in a matter of minutes. You can start uh the the code review is already native on the GitHub app if you have installed cloud on your GitHub repo. So you can automate this for every new pull request that your repo uh receives. And you can also manually uh start a new p uh a new review session using the command ultra review. It's not a super reveal, not a great review. It's a ultra review/ ultra review from your cloud code terminal and you you're going to see you're going to start implementing PR reviews the same way that entropic teams are doing. Yeah. Now for one that is really exciting and we talked a little bit about it in the in the keynotes early this morning. Routines. This is sh was shipped uh early this month I think. uh still in research preview and this helps you create sessions in cloud code without you have to manually triggering them yourself. So think about this a schedule a workflow that can be triggered based on an API call from another system for example or based on a timer or based on a web hook. So you can start imagining all the capabilities that you can uh incorporate on your on your workflows. This already works natively with GitHub. We're going to see this in example, but as I said, you can just plug an API call to it. Think about every time your e-commerce makes a sale, you want to start a routine with cloud, that's just an API call away. And the capabilities of the routines routines themselves are the same ones as an actual chat window as an actually cloud code session that you're having. So if you want cloud to make curl requests for other systems to check for some specific connectors and so on, it's it's what we are going to be able to do it. And uh yeah, why don't we see a quick demo of routines and some of its capabilities as well. So I'm back here on my cloud code desktop and as you can see here on the top we have the routines button. So in this one I have already prepared two of them but uh as you can see you can well let's check take a look at the first one. So, for example, in this one, I'm checking a repository that's not mine repository. It's just one one one public repo out there. And I created one routine that runs both at 8 a.m. and 4 p.m. every day, checking for new commits on this master repo and also for new issues on it. If I scroll down, as you can see here, I also can like incorporate some curl requests, right? You can do everything. You can ask cloud to do anything that cloud would do in a regular sessions. And down here you can see we have it run every day. So this one already run today. And I have here the both the new issues request and no new commits for this repo in particular. And you have all the login of every every day it was running without my intervention. My computer doesn't even need to be on because these are running in the cloud. So let's create one just to see how easy it is. So I'm going to click on new routines and here on this side click on a new one and you can create uh on a remote environment. That's what we are going to do. And I'm going to say here let's say issue issue triage and let's say assess the issue and give me your review. do sound like a medieval knight because that's always more funnier that way. So we're gonna select a repo, a remote repo and I'm going to put here on my own scaly draw fork and my GitHub event in this case you can pick one that's going to be an issue oops sorry an issue open not request sorry the issue open that one. So every time an issue is open, cloud will execute this routine. You can also add some connectors to it. In this case, it's not applicable. So I just click on create. And this one, we have it connected to my repo and so on. So what I can do is access that repo itself, which is this one. And I can create a new issue. Let's create here a new issue. and I say, "Hey, I found a back door on this app." There's a back door. Please fix it. I mean, there's no back door, but issues are random. So, let's just create one of these. And what happens that this will trigger a web hook, we will trigger my routine, and that will start. This take a couple of seconds, but while this is is running, I can show you the other one that I created before. So I have here my poshmp MP review which runs every time somebody creates a pull request on that same repo and this one is reviewing this PR and comments with findings in the PR itself. So the one that I created is not interacting with with the issue. It's just like providing me the report. This one is coming back to the issue and creating one review right there. So I'm clicking here and I'm seeing all the first one and I have this PR that was open. So I created a first PR yesterday and Claude came and did a review based on that routine. So it's not nobody has to tag anything. Nobody has to to make the integrations just the web hook from GitHub trigger a cloud session and that started uh the whole PR sounding like a very posh MP. So that should give us time to come back to the one that I created with the issue. Let's say this one. Yeah, we already done this one in here. And this one is my medieval knight checking for the issue. So yeah, that's the kind of workflows that can start already building it. Think about a lot of the web hooks from GitHub, any API calls from your external systems. All of this running in the cloud without your computer being open. That's boils a lot to what Boris what was mentioning that hey now you are asynchronous doing your work. lets the clouds do your work for you and just come back and assess what is going on in there. All right. Uh yeah, that being said, we can go really quick talk about agents view and we saw a little bit of this this morning. Uh with agents views, you have one view for your all your cloud code sessions. So if you are like an addicted to cloud code parallel sessions like I am, you have that window with with that monitor with many terminals opens at once. Ter uh the agent view lets you manage that in a much more seamless and easy way. You can see all your sessions based on what's their current status, which one are waiting for a prompt, which one are completed, which one needs your input for example. and better than myself showing you a slide. Let's go to the last demo of today so I can show you how does that work. So agent view is really easy to get started. So if we just start your session with cloud agents like this uh you're going to see the first agent views is something that makes your sessions run in the background because as you can see here I already have two sessions with cloud code open in there. And if I go a little bit smaller, you can see that I can start dispatching. So, uh, what is my schedule for today? Uh, give me a Spotify playlist for code with clothes London. And let's plan a new dark mode for this app. So as you can see all of this is running in parallel and it's actually running in the background. So I can leave cloud code as I just did right now and come back. Everything keep on running. So you don't have to be attached to the terminal anymore. You can go inside any of the sessions if you press enter. And you can see here I already have a Spotify playlist for London. You can come back uh you can pick on some of these. So for example calendar is there. So I can if you just press space you can send a prompt to that session without del delving into the session itself. So uh how many appointments for today and yeah they are cloud will if there's a session that is waiting for you to take action for example there's a group you can see the grouping already from working to complete in this case for example now session needs an input and you can go over over there go into it or uh just pick on into it as I as I said before so yeah agent views is released in public preview And I welcome you to try it if you are one person that uses several cloud code sessions at once. So I could be talking a lot more. Actually I'm already over time and we could talk a lot more about over other features in regards to cloud code. But one thing that I have to mention to you is that none of this will be possible without first you leveraging those tools and using this every day but also providing all the feedbacks, all the features requests and all the bug reporting that you have been doing. So please keep on doing that. And for particularly the ones that are managing teams or enterprise uh deployments of cloud code, we released several features that were made just for you. Better Windows support wizards for cloud deployments with both Google Cloud Platform and AWS. We have native binaries so you can leverage installation straight from your your your governance pipeline. Uh and yes, the last bit just to be super crisp is that there's a lot of of other things and a lot of more that you we can talk about cloud code. Follow the dev dev team on the socials. You have the cloud devs on Twitter. We do have a what's news section inside the documentation that just sums up what needs to be assessed and what's what's important for you to that. And of course, the change log is there. uh subscribe to our our newsletter. And one thing that we should never stop doing, especially in this day and age, it's never stop learning because there's a lot of things that we we we need to be aware of. So, keep learning, keep building, keep thinking. Thank you so much. You guys were amazing. That was fantastic.