Three AI Agents That Couldn't Talk to Each Other — So I Made Them a Drupal Content Type
At any given moment I have three AI things running.
At any given moment I have three AI things running.
Last time I wrote about MCP here, the model was on a very short leash. It could read my content, extract what you were asking for, and write you a summary. That's it.
Every time someone says "let's add AI search," the next sentence is usually "so we'll need a vector database." Embeddings, chunking, a RAG pipeline, some new service to host and keep in sync with y
A few weeks ago I got tired of alt-tabbing. I'd be mid-conversation with Claude about a ticket, then switch to KEBOCA to check the status, copy something, come back.
I have a confession. For years I had a Drupal module sitting in a sandbox on Drupal.org that I never properly published. It worked — it shipped on a client site, the client was happy, I moved on.
A few years back I built a small Drupal 8 module to render Angular components in entity view displays using the Page Decoupled Blocks (PDB) framewor
A few days ago I wrote about how I gave my Claude-powered Drupal agent persistent memory using a bank of structured markdown files.
Have you ever noticed how Claude answers the same question differently depending on the day? Not because it's inconsistent — but because it genuinely doesn't remember you.
For a while, my .cursorrules file was doing fine.
I recall a moment when I was working on migrating an old Drupal 7 custom Views filter into a Drupal 11 module.