I built a prototype showcasing how I think AI assistants will interact with existing software during an OpenAI Realtime Hackathon this weekend. Won 2nd place and $15k in credits. (skip to 1:00)

I built a prototype showcasing how I think AI assistants will interact with existing software during an OpenAI Realtime Hackathon this weekend. Won 2nd place and $15k in credits. (skip to 1:00)

https://hirebellhop.com

Circumnavigated earth by train and ship while building tech companies
|| 
New York <-> Tokyo
|| 
reustle.org

Important clarification: everything is happening on the client side except for the the audio being proxied to OpenAI, then receiving tool calls back.

memebuilding • prev manifold.xyz, twilio.com

There are a few routes to go down w/ that.

What I've been brainstorming for a few weeks, heavily related to MCP, is how to essentially let these agents go hunt down the API docs for the service & your API key when logged in, then it can do most (?) things w/out fumbling w/ the browser.

Pretty slick.

Think this could work without a formal integration? As in, login to a saas it’s never seen, invoke it and have it discover what it can do.

Risk @Stripe prev: wallets @bitski, search @airbnb | https://www.castsense.xyz/ 

Thanks! 3 in parallel, 4o realtime audio model (basic listening) + whisper model (transcripts) + o3-mini (double-checking regularly)

super cool. is this using CUA model from openai?

Thank you for sharing your work! As someone just starting out, I’m really inspired by how you’ve integrated AI assistants with existing software. Congrats on the win 🥳🎉

This is an interesting project. Well deserved chad

Very underrated, beautiful execution. This will go from “let’s see where we can take this idea from here” to a multi-B product acquisition. Any boutique hotel in the world is already a customer.