Prompt guardrails fail right when coding agents get dangerous. How Docker Sandboxes make YOLO mode safe, plus a ready-made kit for infrastructure work.
Engin Diri
11 min read
Agent Sandbox gives AI agents kernel-isolated, disposable environments as Kubernetes resources. Here's what it is and how to deploy it on GKE with Pulumi.
Adam Gordon Bell
10 min read
The best Terraform alternatives for 2026: Pulumi, OpenTofu, AWS CDK, Crossplane, and Bicep, compared on multi-cloud reach, governance, and AI-agent readiness.
Pulumi Content Team
16 min read
Set monthly organization or per-member Pulumi Neo dollar limits and get alerts via email.
John Keiser
2 min read
Google's Open Knowledge Format: a one-page spec for the LLM wiki. Markdown, one required field, git. Why knowledge as code is your agent loop's missing layer.
Engin Diri
8 min read
A zero-touch Ollama GPU inference server on AWS, Azure, or Google Cloud as one Pulumi program, with OIDC credentials from Pulumi ESC and no static keys.
Engin Diri
20 min read
Deploy a self-hosted Hermes agent as one Pulumi program across Render, Modal, and Tailscale — a code-executing AI agent with nothing on the public internet.
Engin Diri
30 min read
Neo code reviews analyze pull requests against what Pulumi Cloud knows about your running infrastructure and leave feedback right in the PR.
Pulumi Neo Team
2 min read
The unit of work moved from the prompt to the loop. The five pieces of loop engineering, the memory that makes it compound, and what it won't do for you.
Engin Diri
9 min read
Self-host multimodal Gemma 4 on a Mac with Pulumi, llama.cpp, and Tailscale, using Unsloth's Gemma 4 12 B Q8 GGUF with a 128K context window.
Pablo Seibelt
8 min readPage 1 of 8
