Used the same example Nate has given on day 2 to get job posting details from dailyremote.com. I have set up my project with FireCrawl API and managed to get the specific job posting, initially the basic info, and then a drill-down version to get actual company names and full job descriptions. One thing I learned is that with the quick instructions, Claude was able to easily add the MCP for FireCrawl to support the scrapping. After the basic version, just asking next, it provided the requested detailed version. This can be easily used to get leads' info from sites to do outreach.

Done the day 1 task and produced a newsletter in HTML by just using Claude and Gmail to send the email. one thing I learned is that yes other platform mentioned will give better results but even with Claude you can still do this task. this is a good idea for someone to use and produce a weekly newsletter.

Whether you’re building automations between diaper changes or sneaking in a YouTube tutorial after bedtime, we see you. Hope you get a little time to relax today and enjoy some time with the family!! Take the day off from the agents. They’ll still be running tomorrow. - Nate

framework to check if this automation worth to build 📋 Use this checklist to find automation opportunities: [ ] Does it repeat? (Same thing same way every time) [ ] How many people/times? (More = more valuable) [ ] How much time saved? (Multiply by hourly rate) [ ] Can it be fully automated or just partially? (Full = better) [ ] Does the process stay the same? (Yes = automatable) [ ] Would they pay for it? (Yes = build it) [ ] Are there 5+ potential customers? (You need a market) [ ] Can you find them? (LinkedIn, Facebook, referrals) SCORING: 7-8 checkboxes = GOLD (build this first) 5-6 checkboxes = GOOD (build this second) 3-4 checkboxes = MAYBE (research more) <3 checkboxes = SKIP (find better opportunity) I use this framework to evaluate every automation idea. When I spot something that hits 7+ boxes, I know it's worth building. Try it this week: - Find 3 processes that repeat in your world - Run them through this checklist - See which scores highest Drop your highest-scoring opportunity in comments 👇 add pdf of this point with example !! Questions: - 1.what you think about this framework?? 2.any add-ons?

I switched Claude Code over to GLM 5.2 and ran it all day. It's a 756 billion parameter open source model you can route straight into the Claude Code harness for about five times cheaper than Opus, and for most of my knowledge work it held up fine. In this one I show you what it can build, where it beats Opus and where it doesn't, and exactly how to set it up so you can switch between models per project. Here's the config I use. Drop this into your .claude/settings.local.json and swap in your own Z.ai key: "env": { "ANTHROPIC_BASE_URL": "https://api.z.ai/api/anthropic", "ANTHROPIC_AUTH_TOKEN": "your-z-ai-api-key-here", "ANTHROPIC_API_KEY": "", "API_TIMEOUT_MS": "3000000", "ANTHROPIC_DEFAULT_OPUS_MODEL": "glm-5.2", "ANTHROPIC_DEFAULT_SONNET_MODEL": "glm-5.2", "ANTHROPIC_DEFAULT_HAIKU_MODEL": "glm-5.2", "ANTHROPIC_SMALL_FAST_MODEL": "glm-5.2", "CLAUDE_CODE_SUBAGENT_MODEL": "glm-5.2" }