It’s fascinating how building things with Claude AI and Vercel made me forget about my desire to expand my knowledge and experience of Apple Shortcuts. I no longer see the need for that. My wish, though, would be to see Apple bring a way to build Shortcuts using Apple Intelligence.
I see a lot of interest in my experiment with Vercel and Micro.blog if the reactions are any indication. I’m going to do a small write up about this. I didn’t expect my experiment to be successful. Can’t wait to share more details about this on meta.numericcitizen.me.
One of the reasons for building my own web app for posting to Micro.blog: having the title field and categories shown by default 😁🤣
And Now Microblog Poster Web App is Live!
It’s a web app (on Vercel) just for me to use so that I can write blog posts on the go with a clean UI. It’s my second web app on Vercel built entirely with Claude AI.
I made my first Vercel app: a simple form for posting to Scribbles.page. Super lean, super clean. I do have coding experience, but not with Next.js. Claude AI helped me out. Here is the final form. Next up: same thing but for Micro.blog. This time, the title field, the categories will be shown by default! 😅

I’m done with the 2025 editions of The Ephemeral Scrapbook (all editions in one place!). It’s my free newsletter built with care and love and hosted on Ghost. Looking forward to 2026.
When I’m hitting my Claude AI credits allotment, it’s time to do something else. 😅
My n8n exploration continues: now I have both an n8n MCP endpoint and an API endpoint enabled. I can talk to my n8n instance from Claude via either my MCP connection or an API. I can trigger an n8n workflow via the Claude AI MCP connection. Endless possibilities. 🤯
Moving from Apple Keynote to Freeform for my next content creation workflow diagram update. It’s a sneak peek. It was much easier to convert (a simple copy-and-paste was all that was needed to kick-start the process). I also made significant changes to the way certain things are presented.
Who's Right?
Apparently, web analytics is not an exact science. Here are three web analytics versions of the same period: from November 23rd to December 23rd (Top: Ghost Analytics, Middle: Plausible Analytics, and Bottom: Tinylytics). Plausible feels conservative, with about half as many unique visitors as Ghost, while Tinylytics seems to overestimate. The patterns are barely the same, too. Who’s right?