Why Every Agent Run Needs to Be a Data Point

Anthropic hits $30 billion and says intelligence is not the bottleneck anymore. Here's what happened and what matters for teams deploying agents to production. You need to stop managing your own agent infrastructure, if you can, and let Cloudflare handle execution so you could focus on what your agent actually does. That's sort of the promise in, uh, the recent team-up from Anthropic and Cloudflare. Cloud-managed agents on Cloudflare. Cloudflare and Anthropic have collaborated to integrate cloud-managed agents with Cloudflare Sandboxes. Their new integration gives you more control over your agent sandboxes, secures connections to private services, and improves observability. Cloudflare's developer platform has expanded in the last year to give more developers the tools they need to run agents at scale. This includes sandboxes for stateful— full stateful Linux microVMs at scale, Agents SDK providing simple and customizable agent frameworks, Browser Run, which gives agents fully programmable and observable browsers, Dynamic Workers, allowing for dynamic sandboxed code execution at massive scale. Cloudflare has a goal: make Cloudflare the simplest, most secure, and most programmable cloud for agents. And this announcement of the Claude managed agents offering and partnership is definitely a step in that direction. This framing from Anthropic decouples sort of what they call the brain from the hands. So Claude reasons on the Anthropic's— On the Anthropic platform, but then tools can execute on your infrastructure. In this case, it could be executed on Cloudflare.

Infrastructure.

There are two sandbox types, Linux microVMs and V8 isolates. Boot in milliseconds and scale to tens of thousands of concurrent agents. Some behind the scenes moves, Matthew Prince, CEO of Cloudflare, turned down an Anthropic board seat and sent Dario Amodei Aristotle's Politics as a book. I thought that was a pretty interesting CEO move. Uh, just CEO stuff in the background, I guess. One last fact is that usage grew for Anthropic by 80x versus their planned 10x. So that is more towards some quantitative numbers for their statement infrastructure is really the bottleneck, not, not intelligence. Jonathan, what do you think here of this whole cloud managed agents on Cloudflare amongst some of the other plays that have been popping up with this whole like, give me more compute game that's happening.

Yeah. Um, you know, we talked about the OpenAI and AWS managed agents deployment and this felt like, uh, kind of a similar offering. I generally like working with Cloudflare because it, like, they do simplify the integration. Like Cloudflare versus AWS to do some of the same things, it's like probably 5 to 10 times easier to use Cloudflare. So it's exciting to see somebody really puts so much emphasis on the developer experience, be offering this kind of managed agents harness. The, again, the sandboxes, you know, so we can, we can run our agents locally and then use sandboxes and then have them just ready to deploy. That's like easy. Yeah, I was, I thought this was going to be something useful and something that we would use for our new stacked harness architecture that like, you know, as we mature our agents and deploy them. scale them.

Yeah, could you talk more about that? Like, any initial thoughts of how we would use this with our stacked agent architecture? And maybe talk about it from the problem that we face as AI builders ourselves, building AI products and experiences for our customers.

Yeah, I mean, um, so our, our stacked, uh, Harness architecture, we're, we're basically agentifying all the aspects of tools that we built, um, using Harness engineering practices. So the harness is going to include the context engineering. It's going to include all— every, every, like, a log of every run that the agent does and create a dataset and a set of evals and a set of ways to improve the functionality of the agent to get— make it work better. So this is our kind of, like, our internalization of how to create closed-loop agents. So, you know, like, we, we can spin these up and right now we're at the development phase where we're using them locally, but ultimately we need to deploy those agents into the cloud so that they can be used as context within our Codex and Cloud Code sessions in any way that we want it. And so then, you know, you and I can turn our attention and say like, okay, we need to work on this customer problem right now. Here's a set of agents that I need in my context window. And, you know, like they're all, they could all be provisioned on Cloudflare and it works seamlessly with whatever harness that we're using for development. Yeah.