I had to keep this one a bit short, so I wont be deploying this site specifically (already familiar with vercel deployment). Here's a quick mock-up site I created with the dummy agency branding Ive created so far. The screenshot hack was awesome to use. spending time on front end design is probably my least favorite activity so I'm a huge fan of that.

Trying to decide which paid community to focus on. Looking to build an AiOS and and automated Content Creation (IG, LinkedIn, YT Shorts & Longform) & Meta/Google Ads... Is the AIS+ like last year or has it been overhauled into agentic step by step?

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.

Just finished Day 3. I went back into my AI Exec Assistant from the first video I watched. I added the frontend-design skill, excalidraw, and infograpic skills. During execution I found that the firecrawl skill I added was being invoked to create reference docs for the skills, which was causing a TON of unneeded crawling and markdown files. I shut off model invocation for the Firecrawl skill and kept to pre-sighted web-page references in docs to get the needed tools. My original infographic didn't have branding so I added it on this one with a fake automations company branding sheet I made and like the test run so far!

Scraper built and complete! Since I'm between jobs right now, I went with a job posting scraper for one of the titles I'm shooting for. With this build, not using the WAT framework or developing skills, it was easy to see how carried away with token use this can get. not building skills and tools for the types of scrape, data cleaning or for building the output files had Claude Code running bash python for all of those, which generated on the fly has to be costly. This scraper can easily fit into a personal tool for job-hunting I'm thinking about. Goal would be to scrape for jobs, refine results slightly, then scrape job description for key-words, employer website for context, and generate a new resume version with those keywords in ATS alignment, plus cover letter.