<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0"><channel><title>Agent Tile Blog</title><link>https://ta-blogs.web.app/agenttile/</link><description>Practical guides for running many Claude Code sessions in parallel on macOS — orchestration, review workflows, and staying sane with a fleet of AI coding agents.</description><item><title>The complete macOS setup for a fleet of Claude Code agents (2026)</title><link>https://ta-blogs.web.app/agenttile/the-complete-macos-setup-for-a-fleet-of-claude-code-agents/</link><guid>https://ta-blogs.web.app/agenttile/the-complete-macos-setup-for-a-fleet-of-claude-code-agents/</guid><pubDate>Tue, 08 Sep 2026 00:00:00 GMT</pubDate><description>A start-to-finish checklist for running 4–8 Claude Code sessions in parallel on a Mac — isolation with git worktrees, session identity, broadcast, crash recovery, and the settings that prevent the classic mistakes.</description></item><item><title>How to tell your Claude Code sessions apart (before you type into the wrong one)</title><link>https://ta-blogs.web.app/agenttile/how-to-tell-your-claude-code-sessions-apart/</link><guid>https://ta-blogs.web.app/agenttile/how-to-tell-your-claude-code-sessions-apart/</guid><pubDate>Mon, 07 Sep 2026 00:00:00 GMT</pubDate><description>Five Claude Code sessions, five identical terminal windows. Practical ways to label, color, and arrange parallel sessions on macOS so you never send an instruction to the wrong project.</description></item><item><title>tmux vs a GUI for parallel AI coding agents: an honest comparison</title><link>https://ta-blogs.web.app/agenttile/tmux-vs-a-gui-for-parallel-ai-coding-agents/</link><guid>https://ta-blogs.web.app/agenttile/tmux-vs-a-gui-for-parallel-ai-coding-agents/</guid><pubDate>Sun, 06 Sep 2026 00:00:00 GMT</pubDate><description>Running several Claude Code sessions at once? Here's where tmux genuinely wins, where a purpose-built GUI wins, and the three questions that decide it for your setup.</description></item><item><title>The 3-Agent Setup for Code Review: One Writes, One Reviews, One Watches</title><link>https://ta-blogs.web.app/agenttile/the-3-agent-setup-for-code-review-one-writes-one-reviews-one-watches/</link><guid>https://ta-blogs.web.app/agenttile/the-3-agent-setup-for-code-review-one-writes-one-reviews-one-watches/</guid><pubDate>Sun, 06 Sep 2026 00:00:00 GMT</pubDate><description>A durable pattern for AI-assisted code review: three parallel Claude Code sessions with clear roles. Writer, adversarial reviewer, and drift-watcher. When to use it and when not.</description></item><item><title>How to Recover Crashed Claude Code Sessions in Under 30 Seconds (2026)</title><link>https://ta-blogs.web.app/agenttile/how-to-recover-crashed-claude-code-sessions-in-under-30-seconds-2026/</link><guid>https://ta-blogs.web.app/agenttile/how-to-recover-crashed-claude-code-sessions-in-under-30-seconds-2026/</guid><pubDate>Sun, 06 Sep 2026 00:00:00 GMT</pubDate><description>When your terminal crashes with 6 Claude Code sessions running, recovery usually means starting from scratch. Here is the setup that restores all sessions in under 30 seconds.</description></item><item><title>Claude Code's agent view, and the two things it deliberately doesn't do</title><link>https://ta-blogs.web.app/agenttile/claude-code-agent-view-what-it-does-and-doesnt/</link><guid>https://ta-blogs.web.app/agenttile/claude-code-agent-view-what-it-does-and-doesnt/</guid><pubDate>Sun, 06 Sep 2026 00:00:00 GMT</pubDate><description>Claude Code now ships a built-in dashboard for background sessions. Here is what claude agents covers, where it stops, and how to tell which half of the job you actually have.</description></item><item><title>Do You Need a Tool to Run Multiple AI Agents, or Just Discipline?</title><link>https://ta-blogs.web.app/agenttile/tooling-vs-discipline-multiple-ai-agents/</link><guid>https://ta-blogs.web.app/agenttile/tooling-vs-discipline-multiple-ai-agents/</guid><pubDate>Sat, 05 Sep 2026 00:00:00 GMT</pubDate><description>Before buying anything to manage multiple AI coding agents, it's worth asking what a tool actually buys you over plain discipline. Here's an honest breakdown of where habits are enough and where a purpose-built layout pays off.</description></item><item><title>How many AI coding agents can you actually run at once?</title><link>https://ta-blogs.web.app/agenttile/how-many-ai-coding-agents-can-you-run-at-once/</link><guid>https://ta-blogs.web.app/agenttile/how-many-ai-coding-agents-can-you-run-at-once/</guid><pubDate>Wed, 02 Sep 2026 00:00:00 GMT</pubDate><description>The limit on parallel AI coding agents isn't CPU or RAM — it's how fast you can review their output. Here's how to find your real number.</description></item><item><title>Crash-proof your AI coding sessions: why session restore matters</title><link>https://ta-blogs.web.app/agenttile/crash-proof-ai-coding-sessions-restore/</link><guid>https://ta-blogs.web.app/agenttile/crash-proof-ai-coding-sessions-restore/</guid><pubDate>Tue, 04 Aug 2026 00:00:00 GMT</pubDate><description>Losing a fleet of AI coding sessions to a crash or restart wastes real context. Here's why session restore matters and how to keep your agents recoverable.</description></item><item><title>A workflow for reviewing AI-generated code across many agents</title><link>https://ta-blogs.web.app/agenttile/review-ai-generated-code-across-many-agents/</link><guid>https://ta-blogs.web.app/agenttile/review-ai-generated-code-across-many-agents/</guid><pubDate>Thu, 30 Jul 2026 00:00:00 GMT</pubDate><description>When several AI coding agents produce diffs at once, review becomes the bottleneck. Here's a workflow to review AI-generated code fast without missing things.</description></item><item><title>How to run multiple Claude Code sessions in parallel on macOS</title><link>https://ta-blogs.web.app/agenttile/run-multiple-claude-code-sessions-parallel-macos/</link><guid>https://ta-blogs.web.app/agenttile/run-multiple-claude-code-sessions-parallel-macos/</guid><pubDate>Sun, 26 Jul 2026 00:00:00 GMT</pubDate><description>A practical guide to running several Claude Code (and other AI coding) agents at once on macOS without losing track of which window is which.</description></item></channel></rss>
