In this run I took a crack at a resume and COV generation pipeline. It's a Cron task to check a ClickUp jobs list where I've pasted nothing but the job posting url. Then made it an Agent to scale up the difficulty -Firecrawl scrapes to the page for company and posting information -analyzes and extracts keywords from the Job Posting, -uses a reference file of my resume and builds a new version specific to that job posting along with an optimized COV -updates the ClickUp item with a flushed title, company info, salary details and PDF versions of the generated files This one took me deep with what broke and went wrong. From Unicode formatting in the PDF tasks to context bloating with the resume handoffs. It was a fun build and I like the result, but I'm definitely wanting to be a bit more structured with how I'm building.

Day 2 Done. Built a Lead Gen Scraper with Claude Code + Firecrawl. Here's what I built: What I scraped: I scraped a business directory (goldenpages.ie) and pulled 20 local plumbers in Dublin — names, phone numbers, and business details — all exported automatically into a clean CSV file. Zero manual copy-paste. -One thing that surprised me: I didn't have to tell Claude Code which Firecrawl tool to use. I just described what I wanted — "get me a list of plumbers from this site" — and it read the CHEATSHEET.md and picked the right tool on its own. That's the WAT framework in action: the markdown file acts as the brain, Claude acts as the hands. One use case idea: Selling leads lists as a service on Fiverr. A client tells me their niche and location. I change two lines in the script, run it, and deliver their CSV within minutes. Charging €25 for 50 leads, €50 for 150 leads. The scraper does the work — I just deliver the file. This is Day 2 of the #AISChallenge and it's already generating a real income idea.