The Agentic Infrastructure Era | Pulumi BlogSkip to main content<br>It’s launch week! The agentic infrastructure era is here, and we’ve got some new things to share.<br>Read the blog
25.2K<br>Contact us<br>Sign in<br>Dashboard<br>Get started<br>25.2K<br>Contact us<br>Sign in<br>Dashboard<br>Get started
Navigation
25.2K<br>Contact us<br>Sign in<br>Dashboard<br>Get started<br>Toggle Blog Navigation<br>Pulumi Blog
Program the Cloud<br>Create, deploy, and manage cloud infrastructure using your favorite language.<br>Get started →
Recent Posts<br>Seven Rules for Building an AI-Native Software Factory<br>Neo, Now in the Terminal<br>Neo Integrations: MCP Servers and Cloud CLIs<br>The Agentic Infrastructure Era<br>Ten More Things You Can Do With Pulumi Neo<br>Better CLI Interactions for Agents and Humans<br>How Building AI Agents Has Changed in 2026<br>The Dark Factory Pattern for Infrastructure: Running Pulumi Lights-Out<br>Connect Any Git or Mercurial Repo to Pulumi with Custom VCS<br>Policy Packs Can Now Access Pulumi ESC Environments
pulumi-releases<br>features<br>aws<br>kubernetes<br>ai<br>platform-engineering<br>azure<br>serverless<br>esc<br>infrastructure-as-code<br>secrets<br>security<br>cloud-engineering<br>pulumi-news<br>policy-as-code<br>continuous-delivery<br>containers<br>devops<br>typescript<br>iac<br>python<br>pulumi-cloud<br>automation-api<br>community<br>eks<br>pulumi-events<br>docker<br>pulumi-neo<br>ai-agents<br>google-cloud<br>terraform<br>insights<br>migration<br>cloud-native<br>guest-post<br>javascript<br>lambda<br>pulumi-service<br>yaml<br>best-practices<br>llm<br>packages<br>All blog tags →
The Agentic Infrastructure Era
Joe Duffy<br>Posted on May 19th, 2026<br>The first frontier agents excelled at was coding. The reason is evident: we have billions of lines of self-documenting code available on the internet for the LLMs to learn from. We can measure their performance on coding thanks to linters, type checkers, compilers, and test suites. The most advanced agentic systems to hit product/market fit have been coding-oriented, and it has resulted in an intense velocity increase in how much and how fast code we can write.<br>But as the AI tsunami whips up reams of code, what happens to it becomes just as critical. As an industry, we’ve moved beyond just coding to engineering, which includes documentation, tests, automation, and, yes, managing the very infrastructure our applications need to run. The deeper into production you go, however, the less good agents naturally are at helping. At Pulumi, we live and breathe infrastructure, and have seen this firsthand. But we’ve also been hard at work building the platform this new era runs on. In this post, I’ll share our point of view, what we’ve built, what we’re launching today, and why all infrastructure is about to be agentic.<br>LLMs are natural coders<br>It is remarkable to look back and note that frontier models, less than two years ago, in August 2024, scored just 33% on SWE-bench Verified. Present-day models score 86%, which represents a 4x reduction in the errors models will make when coding. This enables models to solve increasingly difficult coding problems, and humans can lean more heavily on them to offload tasks. Anthropic’s new Mythos model scores 94% and, although it isn’t generally available at the time of this article, there’s no question we’ll close in on 95% by the end of 2026. That is another 2.3x reduction in error rates. This very naturally puts us onto the last mile of fully agentic coding.<br>This has been the result of code being highly in-distribution combined with the relentless pursuit of solving coding problems from the frontier labs, especially with Anthropic’s Claude Code, but now with OpenAI’s Codex, driving a tight feedback loop that turns into an improvement flywheel.<br>Given that LLMs are natural coders, most of us simply assumed that the breakout success we’ve seen with agents for coding would automatically translate into new problem domains. And for sure, we have seen some success. But perhaps not as much as we’d like. Not all problem domains are documented equally well so that the models can naturally learn about them.<br>Andrej Karpathy noted nearly a year ago that, “Building a modern app is a bit like assembling IKEA furniture,” observing that, though writing the code was easy, fun, and fast, the next mile of actually getting the application running in production entailed many things the LLM wasn’t naturally good at, including “services, API keys, configurations, dev/prod deployments.”<br>At the same time, we’re seeing something magical happen here at Pulumi: LLMs are now doing over 20% of the infrastructure deployments, up from virtually zero a year ago. We expect this to grow to over 50% before the end of this year and well beyond afterwards.
The agentic infrastructure era is here. Today we’re announcing several new platform capabilities to accelerate it further.<br>Before getting to what’s new, however, why are we seeing this happening in reality?<br>Turning infrastructure problems into coding...