Today I went to test my personal agent; I wanted to see what would happen if I didn't give it access to my Google search—I had completely revoked that access (so there was no way it could know the path to it). I sent it a message asking it to email a client, and it replied: "All set—shall I run it?" I said yes, knowing it couldn't access Google to send the email. Suddenly, it opened a Google profile I had never used with it and navigated through the steps to send the email (though I cut it off there because I didn't actually want to send anything; it was just a test). I don't know how it was possible, since it didn't have access to the computer's terminal either, but it’s wild what happens when you push AI to its limits. I’ve fixed the issue now, but just imagine if this happened with other users of my assistant and it didn't stop them from sending the email. If you want to try it out (it won't hack your computer), check out usedash.es

I'm creating an AI agent that can truly perform tasks within your tools, securely. No demos that waste your real time! This is where I am now, having finished the MVP, and this was its final test. It speaks volumes about the agent's potential. I'm doing in-depth research on cancer, its risks, and causes, and I'm building a complete website based on that research. Any features you'd like me to implement?

I've been paying for months for agents that promise to connect with ALL my tools, and in the end you end up: → doing manual OAuth every 3 days → pasting API keys into ugly interfaces → learning n8n/Make/Zapier for nothing → paying €40/month for something you use for a week. Non-technical freelancers don't want to learn automation. They want things to happen. That's what I'm building: an agent that uses your tools for you, without you having to configure anything resembling an integration. I'm 16 years old, not an engineer, and I learn what I need each week to ship the next part. The current stack: FastAPI, Claude, Browser Use, MCP servers, SQLite. It's not magic. It's 6 weeks of slow work (and counting). I'm documenting everything in my X account in case anyone is inter ested.

I'm creating an AI agent like OpenClaw, but safer and easier to use, and I plan to launch it worldwide. It's already working, and I want it to be everyone's next work companion, but how would you approach such a large niche?