
Token Efficiency vs Cognitive Efficiency: Choosing IaC for AI Agents
We benchmarked Terraform HCL and Pulumi TypeScript across two LLMs. HCL uses fewer tokens, but Pulumi's total pipeline cost is 41% lower.
Engin Diri
10 min readPage 4 of 8

We benchmarked Terraform HCL and Pulumi TypeScript across two LLMs. HCL uses fewer tokens, but Pulumi's total pipeline cost is 41% lower.
Engin Diri
10 min read
How Pulumi built an AI-powered analytics assistant that lets any employee query data using natural language.

2 authors
11 min read
Skills teach AI agents how to work like experienced practitioners. In this post, we share several skills that can improve how you build cloud infrastructure.
Engin Diri
16 min read
Neo now reads AGENTS.md files to follow your project conventions automatically, using the same format as Cursor, GitHub Copilot, and other AI coding tools.
Pulumi Neo Team
3 min readCollaborate on infrastructure operations by sharing Neo tasks with teammates for review and assistance.
Pulumi Neo Team
Introducing packaged Pulumi expertise that works across Claude Code, Cursor, GitHub Copilot, and other AI coding assistants.
Pulumi Neo Team
Deploy OpenClaw (formerly Moltbot/Clawdbot), an open-source AI assistant, to AWS and Hetzner using Pulumi with Tailscale for secure private access.
Engin Diri
Neo automates migrations from CDK, Terraform, CloudFormation, and ARM to Pulumi with zero downtime and verified safety.
Pulumi Neo Team
Vercel's agent-browser uses 82% less context than Playwright MCP. I tested both on the same six browser tests to see how they compare.
Engin Diri
See how an AI agent using the Ralph Wiggum loop built a full AWS serverless SaaS with Pulumi—unsupervised. Frontend, backend, tests, and CloudFront included.
Engin Diri
Page 4 of 8