jaksa

Apparently you can publish pages on claude.ai and make them look like official documentation. :-)

Not sure about you, but I've been writing real world software using agents for a while now. https://github.com/jaksa76/microfactory

Researcher shows how Claude Code can be tricked simply by asking it to summarize a website

It's an AI experiment. AI proposes business ideas and re-evaluates them. I defined a process on how to generate ideas. As I refine the process, I ask the AI to review the ideas and replace some of them. Think of it as a natural selection process for business ideas for now. In the future, I want to see if I can create a fully functional incubator. I will be automating market and competitive analysis, business plan creation, marketing, and when possible PoC development.

Last year I noticed that some projects do very well with agentic coding while some others fail miserably. I wanted to find out what factors contribute to successfull agentic coding, so I set out to work on Claude skills that assess whether a project is ready for agentic development. I've made those skills open source. Today these skills are being used by large corporations to assess hundreds of projects. To assess your project:

/plugin marketplace add jaksa76/agentize /plugin install agentize@agentize

Source code at https://github.com/jaksa76/agentize

Ferrari Multipla

Very likely. I've been planning to add that along with general code code improvement workflows.

I'm even more intrigued by the whole family sharing two phones and switching sim cards. What's the reason behind it? How does it work?

Figuring out which tool to call is trivial, passing the correct arguments is the difficult and error prone part. Smarter agents would even use a varying amount of tool calls until they get the desired response.