agents

/goal

/goal is a Claude Code command that lets you define a clear objective and have your AI agent work toward it autonomously, so it keeps going instead of stalling and waiting on you.

/loop

/loop keeps your AI agent working on a repeating task in the background, prompting itself each round, so it babysits the boring jobs instead of you.

Credential brokering

Give an AI agent access to real systems without ever handing it the real API key, by putting a proxy in the middle that checks permissions and injects the secret for it.

Critique loop

Have a second, separate model review and critique your AI's work before you accept it, which reliably beats trusting the first draft or running lots of agents in parallel.

Local vs cloud AI

Why a desktop AI tool can do things a browser one can't, and the tradeoff you're making when you pick one over the other.

Remotion

How can I make polished, animated videos with AI if I'm not a video editor?