I finally had the courage — or the ignorance — to open up the project I’ve been building to test, mainly, n8n flows. A good part was built in Lovable and another part in Claude Code.
I find n8n’s “Evaluations” feature very limited, and now, in this vibe-coding world, tests have become even more important. Here I built what I was missing in n8n and in this kind of code:
- Testing many at once, with batch size and wait time.
- Having AI as a judge, like we have in LangSmith and similar tools.
- Having test sequences.
That last one is saving me when I test happy paths to simulate a WhatsApp conversation. If you want it, it’s at https://lnkd.in/dA8Vvw_h
Comments and improvements are more than welcome. :)
The original post includes four images.
Originally written in Portuguese and published on LinkedIn on April 22, 2026. I translated it into English with the help of AI (Claude): it let me bring my LinkedIn posts to people who don’t read Portuguese without rewriting each one from scratch. I reviewed the translation to keep my original meaning and tone.