AI agents don't just browse websites - they run commands. Here's a practical checklist for making your CLI tool agent-friendly in 2026.

• ai
• engineering
• tools

You can't make AI predictable. But you can make everything around it predictable. That changes more than you'd think.

• ai
• engineering
• nix
• infrastructure

AI agents learn by trial and error. Nix's atomicity, rollbacks, and project isolation make those errors cheap and reversible - turning mistakes into a feature, not a risk.

• ai
• nix
• engineering
• infrastructure

AI agents are browsing your website right now. Here's a practical checklist for making your site agent-friendly in 2026 - most of it is stuff you should already be doing.

• ai
• engineering
• web

Terragrunt's parallel output is unreadable. tgdash turns it into a real-time terminal dashboard with per-unit status, plan summaries, and error filtering.

• devops
• tools
• infrastructure

The same patterns that make codebases nice to work with for humans dramatically improve AI assistance. Consistency compounds when AI is your pair programmer.

• ai
• engineering

An engineer's experience report from recording product videos for the first time. The journey from 'I've never done this' to actually enjoying it.

• content
• career
• engineering

Not every MCP server is on npm. Here's how to run them directly from GitHub using npx.

• ai
• mcp
• tools

Engineers are discovering they can solve ten times more problems than before. The tools changed. We're adapting. Here's what that looks like.

• ai
• career
• engineering