Code with Claude: The 5 biggest updates explained

[00:04] Welcome back to How I AI. I'm Claire Vo, product leader and AI obsessive here on a mission to help you build better with these new tools. Today, I attended Code with Claude, Anthropics' first developer event, and they announced some things in Claude Code and Claude Managed Agents I think you want to know about. I'm going to walk you through five things that launched today, how they work, what they are, and what I might build with them. We're going to keep it under 10 minutes, [00:31] new Cloud Code and Cloud API products experience. Okay, the first thing that shipped at Code with Cloud that I think you want to know about are some updates to the Cloud Code app. And one of the updates that I know we've all been waiting for is routines, the ability to trigger events or actions on a schedule. We love it. You know, I love OpenClaw and what I love about OpenClaw are the crons. And so now Cloud Code has that built in right here in the app. All you have to do is [01:01] or remote. I'm going to run it [01:03] locally. And I'm going to say weekly newsletter. This is something that I haven't been doing. I'm sorry, if you're a chat PRD customer, I know I haven't done my newsletter. I'm going to say, look at our change log and draft a newsletter for us to send weekly. And then I'm going to go in here and just say, we have a change log dot empty in the [01:27] Docs folder. [01:29] review it every monday and write a customer facing newsletter

[01:34] based on the best customer-facing features we should. [01:40] don't talk about behind the scenes things like tech debt [01:46] or security unless they really impress customers. Okay, so I'm going to do that. I'm going to run it daily or no, sorry, I'm going to run it weekly on Mondays at 6 a.m., [01:59] And I think... [02:01] That's all I need to do. [02:03] Oh, I'm going to select my folder where my project is, and then I'm going to create create. And now, [02:09] CloudCode will run my newsletter draft cron every week. And then I can come back in here, grab the HTML. If I were being really fancy, I would hook this up to my newsletter platform. I would hook it up to my Slack and ping us. But again, this is very useful to me. This is something that I used to kick off manually in CloudCode every Monday. And now I can do that here in CloudCode on a schedule. Okay. [02:36] So how does that work? There are three trigger types. You can trigger them on a cron, which is a schedule, HTTP or a GitHub webhook. So you can do sort of a normal webhook or a GitHub webhook. You can trigger these three ways. [02:50] scheduled like I just did off of a GitHub action or a general webhook. So you can hook it up to other systems to kick off a routine. All the stuff in connectors come along. So I have Slack connected, I have GitHub connected. So you can use those things as part of your routine. And it can run in the cloud, or it can run on your laptop like I showed. And this is an example of a use case where you could say weekly, I want you to check every PRD modified this week and check if it matches

[03:20] and post a summary to the team channel. So that's item one. [03:25] Um, [03:25] The second one is in Claude Manage Agents in the API. If you haven't paid attention, OpeningEye released something in codex called goal. You can do slash goal in beta in codex and it'll basically bang its head against the problem, do what's called a RALF loop against a problem until it actually hits the goal. [03:43] Anthropic released very similar product called outcomes, where you can define what done looks like for Claude code or for an agent. And then the agent will then, Anthropic released something very similar in the Claude API called outcomes. You define what done looks like for an agent, it can self grade and iterate until it gets there. There's a couple interesting things you need to know about how outcomes are defined. They all anchor on what's called a rubric. So [04:13] a markdown file that's uploaded either through the files API or in line, and it's going to tell your agent what success looks like, then there is a grader and it can do up to 20 iterations on the task to get to the outcome that you're going for. I want to walk through this one in a very specific example to make this just a little bit more concrete for folks. So imagine that I want you to ship a ship ready PRD. And I don't know if you can relate to this. Often you go through feedback [04:43] check it against priorities. You have to check it against technical capabilities. Now using a Claude Manage agent, you could in theory write a rubric, which is what does a good ship ready PRD look like? And then the agent can just take your PRD or your idea and iterate over and over and over again until it's fixed. Of course, you could expect...

[05:08] Of course, you could expose this to your customers in an app like I might do for chat PRD. But again, this idea of outcome is define a rubric. [05:15] Give the agent the task, let it bang its head against that at least 20 times till it gets it right. I think this is a really interesting model for agentic products and something I suspect many of us will use. The second thing I really love is a multi-agent framework supported in Cloud Managed Agents. So now you can, through the API, explicitly define a multi-agent team that's going to work against the same container, the same file system, up to 25, which is kind of amazing. [05:45] a orchestrator and then delegates. And so there's explicit hierarchy and each agent can have its own tool set. I think this is really cool because now you're able to define not just individual agents, but teams of agents programmatically through the API. And so the example I would give for something like chat PRD is you can have a PRD orchestrator. This is sort of like the master agent that is intended to define and drive the work across the team. And then you can have three [06:15] - Thanks. [06:16] a strategy agent that reflects the CPO voice, the critic agent that's sort of like supposed to poke at the holes in the PRD. I like being the critic agent. And then end review that could maybe have access to something like GitHub to optimize the technical implementation of the PRD. And so you can define this as you see over here in the API. You define an agent in the API. You give it a.

[06:43] a orchestrator level set of tools, and then you can define the sub agents in the in the API with their own set of tools. And then you could expose that, as you can see here on the right. [06:55] As three agents all working in parallel against the same problem owned by the coordinator or orchestrator level. Again, I think this is an interesting enhancement on the primitives of agents that people are going to be using quite a bit. [07:13] Okay, the next one I really like it is dreams. So this is all about agent memories. Just to make it simple for folks, memory is basically the idea of writing markdown files to the file system your agent uses that helps it do a better job the next time. It's not that fancy. Often those files have a date on them, but you don't really have to overthink it. [07:43] on an event. And so what they do is like when you close a session, it writes memory or when something happens, write memory or like with OpenClaw, you can explicitly tell it to write memory. [07:54] But what I like about Dreams, which is a very funny brand for an agentic memory product, but will allow it, is... [08:04] It's a primitive to call against a list of agent sessions. So let's say you've done 50 things with your agent. It's an explicit call to take those 50 things.

[08:17] sessions, review them, and then come up with important memories to write. [08:23] to disk. And as I'm saying this, I guess this is what we do when we dream. We go through our day, we review it. [08:30] silently and then we decide what to commit to memory. I don't know. I don't know if this is the perfect metaphor, but it's the one we got and it looks great on a on a branded website. This one's in research preview. So I don't think everybody has access to this through API. I certainly don't have access to it. So I'm looking forward to touching it. [08:47] But why I think this one's important to know is it just gives you a frame of reference for how Anthropic and these labs are thinking about the primitives, again, of agents and agent memory. And you can predict that some framework like this is going to be integrated into agentic platforms or agentic products where on Anthropoc, [09:06] some action or some regular cadence. [09:09] You're going to review past sessions and you're going to explicitly write the right things to DISC so they can be referred to moving forward. Side note, I think we think a lot about agent memory, but not a lot about agent forgetting. So I'm looking forward to like the purge version of this, which is dreams that. [09:28] tell you what to forget. I don't know if that's like trauma erasure or whatever, but I think there's something interesting here. Okay, and then number five, the only announcement people really care about, which is usage limits. [09:41] are up. So starting today, Claude Code's five-hour limits are now doubled across Pro, Max, Team, and seat-based enterprise platforms. Peak hours are going away for Pro and Max plans, and the rate limits for Opus models in the API are going up. So

[10:00] We can all use these products more. [10:03] Again, what did we see today at Code with Claude? Lots of other stuff. They might put data centers in space. There was a partnership with SpaceX. All sorts of fun things are happening. But the things that I think you can use immediately. Routines for scheduling tasks in Claude code so you can get things done either on a webhook or on a schedule. Outcomes, which is the ability to set a rubric and task and have an agent work against that task at least 20 times to nail the rubric. [10:30] Multi-agent orchestration, which allows you in the API to define an orchestrator role and sub agents, I think up to 25 to get work done from different points of view with different tools. Dreams, which are a way to consolidate agent memory over sessions. [10:45] over time and do that on demand. And then finally we can all use more Claude code, which makes everyone happy. I do not know if these limit increases apply to Claude design. I suspect they do not, but I hope they will. I think they launched a lot of stuff that we can use practically right now in Claude code and gave me some good ideas for what the future of agentic products look like. None of this was mind blowing, but I think it's all really practical. [11:15] of choice for builders. I look forward to seeing what you build with it and I'm going to go play with the API. [11:20] Bye.