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?

My wife and me quite extensively used a group conversation in ChatGPT to help us face some health-related issues. It was beneficial to a visit to the hospital and still is after the visit yesterday. It is so much more helpful than having to google things and try to figure out what is going on.

Keeping track of all those services API keys, authorization tokens, API and MCP endpoints, their respective level of authorization is starting to feel cumbersome. 🥴

Consuming AI Can Be Expensive

While experimenting with n8n and LLM services, I realize that using artificial intelligence can become a very costly hobby. The fact that the consumption of these services relies on two separate offerings — the subscription to the interactive service and on-demand billing for APIs — requires careful management and wise choices of providers.

Currently, I use ChatGPT and Claude AI in interactive mode, but I also need a provider to access AI via APIs. This latter mode of consumption is particularly expensive if you’re not careful.

Woke up this morning and appreciated the results of my first n8n automation: a Craft Daily note with a list of topics for the day automagically created for the current day. I did use Craft Templates before, but I prefer the programmatic route because it enables much more powerful content creation by consuming different sources via APIs. For now, my automation doesn’t, but I’ll iterate on that.

My Learning Approach

Still exploring n8n, slowly but systematically. Because I’ll be using all sorts of external services like Craft, Micro.blog, Ghost, Inoreader, my strategy is to do individual integration tests instead of trying to build a biggy workflow and find all sorts of errors. Each of these micro experiments is forming the building blocks of something bigger. This approach is not different from the one I used for building iPhone apps and learning Objective-C and Interface Builder back in the day. I guess I’m a bottom-up kind of guy when it comes to understanding this kind of stuff.