John Campbell

The goal used to be raising capital.

Now it s generating MRR.

Thanks to AI and no-code tools, solo builders are pulling in $10K, $50K, even $100K/month no team, no funding, no gatekeepers.

They re not reinventing the wheel.

When it comes down to hardware my X feed is filled with two types of designs.

• Retro/nostalgic 2000's hardware that was defined by Gameboy translucent purples, Colorful macs, Sony's beautiful eclectic electronics, and embracing colors that pop like pink, purple, and orange.

• Sleek, modern, simple designs like the @Humane AI pin, @Limitless, @Friend, or the @omi.

I personally miss the fun days where consumer tech was wacky. Think Tamagotchi, Mini Clips, PSPs, and clear-shelled devices. I do see some like @Burner that have brought back some fun design but I'm curious... what does everyone think?
Should we bring back the weird or embrace the sleek, simple, and modern?

So here are 3 problems that I'm working to solve in the development of our agentic systems.
Any help would be truly appreciated.
1) How to prevent the agent from leaving the loop in between tool calls, saying it's "going to move on to the next step", or to ask the user for confirmation.

2) How to make the agent manage it's tokens autonomously and intelligently, by identifying and discarding messages or context that are no longer relevant.

(Important in particular for when there's this one gigantic piece of content among the messages that keeps getting sent back in each new API call, making the token count grow exponentially)

- One path that I'm exploring is to have the one task or step in a different agent, so the main agent calls the agent that executes this task, so the context stays separate.