<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Pilothouse blog</title><description>Notes on coding-agent approvals, Claude Code hooks, Codex and policy design.</description><link>https://pilothouse.dev</link><language>en-us</language><item><title>Approve Claude Code from your phone without opening ports</title><link>https://pilothouse.dev/blog/approve-claude-code-from-your-phone</link><guid isPermaLink="true">https://pilothouse.dev/blog/approve-claude-code-from-your-phone</guid><description>A walkthrough of how Pilothouse gets a Claude Code permission request from your laptop to your phone and back — hooks, presence, Tailscale Serve, web push and signed decisions — with no port forwarding and no account.</description><pubDate>Thu, 22 Oct 2026 00:00:00 GMT</pubDate></item><item><title>Rules before every tool call: the two-checkpoint design</title><link>https://pilothouse.dev/blog/rules-before-every-tool-call</link><guid isPermaLink="true">https://pilothouse.dev/blog/rules-before-every-tool-call</guid><description>Why an AI coding agent policy has to run on every tool call — not just on permission prompts — and how Pilothouse splits fast policy decisions from slow human ones.</description><pubDate>Thu, 22 Oct 2026 00:00:00 GMT</pubDate></item><item><title>Why we built Pilothouse</title><link>https://pilothouse.dev/blog/why-we-built-pilothouse</link><guid isPermaLink="true">https://pilothouse.dev/blog/why-we-built-pilothouse</guid><description>Agents now ask for permission dozens of times a day, across vendors, while you&apos;re in another tab or another room. We wanted one place to answer them — with rules we wrote, on hardware we own.</description><pubDate>Thu, 22 Oct 2026 00:00:00 GMT</pubDate></item></channel></rss>