https://test-website-eight-gray.vercel.app I did use all of the hacks really. Yeah, that is a lot diffrent. Did not really take long time either. Everyting did make sence and its way more fun then I thought this would be

This automation find 20 companys just like the video. - what went wrong and how Claude Code fixed it? A lot haha, I did this almost without a guide. Just me and claude to 99% after I watched the video. It took way to long time but I got it after many attmemts. Had some problem to connect to the server. I had to have a terminal open in VS code but that did some time to figure out. I did learn a lot on this atleast

I did build a A branded infographic generator, did name it infographic builder. and it trigger by slash command or auto detection. I am learning more by each day how I did optimize it? invocation control, prompt template, dynamic brand injection, timestamps, correct skill location,dead import, HTML extraction, intermediate file cleanup, context isolation, auto-open, format variants, Windows shell fix

If you're building AI agents, I'd urge you to create a template for prompting. Two notable builds in the last month as proof: - I've built an AI agent that has handled over 9,000 emails - Another AI agent that's handling 25k customers. But here's the full setup: - A claude.md file that references a prompting guideline file, it tells Claude how to write prompts. - Once a prompt is approved, I write at the top "approved for production" which tells Claude that it should not make big changes. This makes sure that the prompt does not get destroyed by Claude. - Push the changes to my GitHub to keep track of all changes. This last part is where most people go wrong. When they see a mistake, they ask Claude to write an explicit rule to never do that again. The issue is that Claude will only look for that exact case, and if the next case doesn't match it, Claude will skip it. Instead, what I do is write mental models of the idea, what we're trying to do and why. When you do it this way, Claude has to use more reasoning to figure out which mental model makes sense. You're letting Claude think with some constraints. But this system has cut down my prompting time and also increased my reliability ten fold. And the thing is that I can use this wherever AI agents are used. Sales agent, customer service agent, any type of agent. Because the structure is the exact same every single time. Give me the agent and I'll make it reliable.

I did scrape the main website for job application in sweden. Had some problems in the beginning that it would not want to use the tools. but after a while I fixed it. How I can use it for a client is so I can be more reday about the person´s company and how to expend on what they already got and be more prepared.