Aaron Friel

Earlier this year we launched Pulumi AI, a purpose-built AI assistant that can create Infrastructure as Code (IaC) from natural language prompts using Pulumi. Since launch, we’ve seen incredible adoption of Pulumi AI, with over 200,000 questions asked so far and growing fast. Pulumi AI is popular with users new to Pulumi and/or new to the Cloud, but also heavily used by many of the most advanced IaC users and organizations to quickly discover solutions to new problems they need to solve. Over the last few months, we’ve driven major improvements to Pulumi AI through the recently launched Pulumi AI Answers pages with thousands of AI generated answers to common questions, improvements to code generation correctness and performance, and expansion of the languages supported by Pulumi AI.

Today, we are taking the next big step, introducing support for deploying cloud infrastructure directly from Pulumi AI. Going from idea to running cloud infrastructure is just a natural language prompt away!

Read more →

Pulumi AI harnesses a form of generative AI, known as large language models, to help you discover, learn, and use new cloud infrastructure APIs with ease. Think of Pulumi AI as a sophisticated compass, guiding you through the ever-changing landscape of cloud infrastructure and pointing you in the direction of the most suitable solutions for your unique requirements. In this blog post, we’ll explore our recent enhancements to Pulumi AI, focusing on how we’ve integrated Pulumi Package schema data to generate more accurate and relevant Pulumi programs.

Read more →

Pulumi enables engineers to employ the best practices of their field to infrastructure as code. The pulumi watch command is an example of this, enabling rapid prototyping and a “hot reload” style developer experience for prototyping Pulumi programs. In this post you’ll see what watch mode enables, the challenges encountered in maintaining the feature, and how we were able to use Rust to bring that feature to more of our users.

Read more →