“We’re going to have our very large United States oil companies, the biggest anywhere in the world, go in, spend billions of dollars, fix the badly broken infrastructure, the oil infrastructure, and start making money for the country.”

There you go. That’s the real reason for the invasion, just like Iraq. WMD? Drugs? These are just excuses to get the oil. Only a month ago, the POTUS pardoned the former President of Honduras for trafficking cocaine into the US. As usual, the lies are blatant.

The more it changes…

And the next n8n project is?

My next project with n8n automation is to build a replacement for Mailbrew. 🫣 I’m facing many architectural decisions:

  • How do I fetch content (web or RSS feeds)?
  • How do I extract articles for more efficient summarization?
  • How do I combine the results?
  • How do I control the size of the summary?
  • Do I need some form of temporary data persistence within the workflow?
  • How do I minimize LLM credits usage?
  • Should I use an n8n data table for storing data sources and loop through them one by one?
  • Where do I send the summary and how (Telegram, Discord, Email)?

…and probably a few more decisions to ponder!

My Microblog Poster web front end now supports Markdown files, drag-and-drop, and preview mode, all in a simple (but less simple than initially built) web interface! 😅

My updated profile description for 2026:

“I’m a compulsive creator and contributor, a digital nomad, a light painter. Aspiring peace supremacist and democracy propagandist. Proud member of the Secret Internet Curators (SIC) brigade.”

I’ve been working on a new workflow that would let me skip using Ulysses when sharing new content from Craft to Ghost. To that end, Claude came to the rescue as always, but I’m not done yet. Here are a few details.

Claude needs an n8n workflow (exposed via the n8n MCP server) to retrieve the content of a specific document using Craft APIs. Using an n8n workflow keeps credentials secure, as I don’t need to provide them directly in Claude prompts. Next, Claude converts Craft blocks to well-formatted HTML, the format Ghost expects from its APIs. Next, Claude depends on another small n8n workflow to securely push the HTML content to Ghost. Those two n8n workflows use webhooks (triggers) and HTTP requests (GET, POST) to transfer information between Craft and Ghost via their respective API endpoints.

The publishing workflow is done and handled by Claude AI, but posts are always in draft mode so I can review them in the Ghost Admin management interface before publishing. I need more work to finish this because now I have to make sure that on the next occasion, in a new Claude conversation, Claude will remember to use my n8n workflows and how I want the content converted. Another issue seems to be about the size of the request being sent to Ghost to create the draft post.

If I go back a few weeks, I barely knew how to use Claude Code or leverage webhooks and MCP servers meaningfully. Now I do, thanks to AI. I feel empowered by AI.

I’m making quite a bit of progress with my Micro.blog UI frontend to the point where I’m wondering how much of the whole experience I could rebuild using Vercel and Claude Code. Challenge?