# Collection of Posts

1. [Parallel agent workflows often use Git worktrees: one checkout per task, one branch per agent. That improves isolation, but it also creates a subtle permissions problem. A child agent running in one worktree may still try to read or edit sibling worktrees, parent directories, or shared files outside its assigned](/content/blog/opencode-worktree-relative-deny-rules/index.html)

2. [OpenCode permissions are useful when you are driving agents from a terminal. They become awkward when the human approver is not sitting at that terminal. A better shape for remote approval is event-driven: subscribe to permission.asked, send the request to a mobile queue, then handle permission.replied as the](/content/blog/opencode-permission-events-mobile-approval-queue/index.html)

3. [Your agent ran. You have no idea what decisions it made along the way. That's not a trust problem — it's an architecture problem.](/content/blog/inside-loop-vs-outside-loop-agent-architectures/index.html)

4. [Three sandbox runtimes, one painful decision: Daytona (90ms, production-grade, $24M funded), AgentBox (Docker-simple, just launched), or DIY (full control, full maintenance burden). Here's how to actually choose.](/content/blog/daytona-vs-agentbox-vs-diy-sandbox-runtime-ai-agents/index.html)

5. [Only 1–2% of agent code is actual AI logic. The other 98% — permission systems, hook composition, sandboxing, context management, subagent delegation — is what determines whether your agent is safe to run in production.](/content/blog/agent-permission-layer-architecture/index.html)

6. [Your AI agent finished the session. But did it stay on task? Here's the post-run audit to catch silent scope creep — before it compounds into something you can't easily reverse.](/content/blog/how-to-audit-ai-agent-post-run-drift/index.html)