What I'm looking for

I’m interested in AI you can speak to while showing it what you’re doing. I want to point at something, say “this part,” move the camera, and ask a follow-up without having to explain the whole situation again.

For example, if I’m trying to fix something, I should be able to show what I’m seeing, try a suggestion, and have the AI follow what changed. A lot of the context comes from what we’re looking at together. Being able to refer to that directly makes the interaction much easier.

The details matter here. Can I interrupt it? Does it remember something I showed it a minute ago? Can it tell when I’m still explaining? Does its response arrive while it’s still useful? I’m interested in how people solve those problems and what they can build once speaking and showing things works well.

If you’re building something people interact with live, email me. I’d like to try it.

I really like WHOOP and Google Fit. I'm looking for an AI-first wearable that can do something useful with what it learns about you, without you having to ask every time. A chat window with your data attached doesn't really get there.

Working on glasses made me think a lot about how little of the underlying system the user needs to see. Voice interaction needs to work properly. What you show someone needs to be relevant and direct. Explaining every step the agent takes gets annoying very quickly.

By "invisible," I mean devices you can use without constantly thinking about operating them. I'm interested in what that takes, both in the hardware and in deciding when the AI should do something, ask, or leave you alone.

Building an AI-first wearable? Email me. I'd like to see what you're working on.

My agent should be able to book a table at a restaurant without someone having built an integration for that specific booking platform.

WebMCP is a really good example of where this should go. A website can expose the actions an agent can take, with enough information to actually use them. The restaurant tells the agent how to book a table, and the agent does it.

I think adoption is the bigger problem. Having a way to expose these actions only helps if the services people actually use implement it. That needs to be easy enough for an ordinary business to do, ideally through the tools they already use to build their website.

I've run into similar friction with google-tools-mcp. Finding a tool and using it still involves too much setup. I'd like to meet people making this easier on both sides: for businesses to offer, and for agents to discover and use.

Then there's scale. Discovery, authentication, permissions, and tool calls all have to keep working as more agents and services come online. I'm interested in the infrastructure that makes that possible without someone manually wiring up every new connection.

Building infrastructure for internet agents? Email me. I'd like to hear what you're working on.