This might be a dumb question, But are people still using N8N to make workflows or just using claude code to make the workflows for them?

1. What I scraped [Insert your CSV screenshot or extracted data here] I managed to extract clean CSV data from my target website without writing a single line of code! 2. One thing I learned I was blown away by how flexible Claude Code is. I didn't have to specify endpoints or configure any API settings manually; it just understood my plain English and picked the best Firecrawl tool (like Map or Extract) completely on its own. Also, seeing its "agentic self-healing" in action was incredible. When the first attempt failed and returned empty results, it didn't crash—it immediately identified the issue, switched up its approach, and successfully got the data. 3. One use case idea When building prototypes for my personal projects or apps, instead of wasting time hardcoding fake mock data, I want to use this to instantly pull real-world product listings or user reviews from actual websites into clean structured data (JSON/CSV) and feed them directly into my app!

What I scheduled - On the Claude Code desktop app, I scheduled a task, hourly, using the GitHub repo from the previous Trigger.dev workflow from day 4 I believe, to deliver me a summary of new leads from ClickUp if there was any. As for what was on a loop, I simply set like a reminder eveery 5 minutes (it auto-adjusted to 20 when I set up improvements* on it though) to remind me to look away from the screen and stretch and whatnot. *Improvement file screenshot attached to the post. Scheduled task or loop? - I used both. I found that there is good in both and there may be practical purposes in using both of them... or just one of them. One suprise - I didn't think I had any suprises with regards to how the agent runs in it of itself... but what still does amaze me is how smart Claude Code is. Like it's ridiculously intelligent... and I do feel as if the limit is simply set by what's ultimately preordained. It's a ludicrously smart tool.

I've been curious about scraping, but have never done it previously, and this lesson did a great job of explaining how it works and how to use it within Claude Code. It did not work perfectly on the first try. I hit a wall at one point, but that ended up being one of the most valuable parts of the exercise. Claude adjusted the approach and switched to using the website’s direct MCP to get the job done. That was the real lesson for me today: the tool matters, but knowing how to troubleshoot and change direction matters even more. This project gave me a clearer picture of how AI agents can collect, organize, and use live web data in practical ways.

Hi everyone, this is my day 2 built. I was able to successfully scrape 10 jobs from a website. One thing I learned was that you can tell Claude to save everything globally so that it can just fetch it when I start another project. I can use the web scraping tool on a client if we were to ever have our first meeting, so that I would know about his business and I could expand on what he might need and where I can help the client.