Each guide starts from a concrete problem and focuses on what actually works in practice.
The areas I cover in depth.
Fresh writing from the archive.
How Claude MCP tunnels let Managed Agents reach private MCP servers without exposing them publicly. The architecture, the IAM model, and the deployment shape.
Claude Code's /goal command keeps Claude working until a completion condition holds. Agent view puts every background session on one screen. What changed.
Claude Dreaming consolidates agent memory between sessions. How it works, the architecture changes it asks for, and where it actually moves the numbers.
How to package commands, agents, skills, hooks, and MCP servers into a single Claude Code plugin your team or customers install once. Real structure, marketplace.json, and what belongs inside.
How travel companies build rebooking agents that hold up at storm scale. Orchestrator-worker layout, PNR locks, GDS rate limits, and autonomy boundaries that work.
Deep Agents v0.5 async subagents return a task ID instead of blocking the supervisor. The Agent Protocol wiring, mid-task steering, and where the pattern breaks in production.
I publish on AI-driven development, cloud infrastructure, and software architecture on a Tuesday and Friday cadence. Subscribe to get each new article when it lands.