Sandy Suh

We're building an AI that helps organizations track public policy, and we recently had an educational non-profit and a healthcare organization become customers.

We'd love to find more non-profits/organizations supporting good causes to work with. If you know any such organizations where public policy often impacts their operations, we'd love to hear about it and try to help!

I made my first chrome extension using solely Chatgpt. I wanted to see if it was really possible for a non-technical person like me. I was really proud of myself, it inspired me to want to build more! But when I tried to add more features to it, I think the code got too bloated and messy and it just blew up so I just continue to use the extension for the basic need I have to save and organize notes I make on products that are interesting to me without all the bells and whistles I would have wanted. I wasn t trying to make money on it, just something to prove I could do it, and I got to feel what it was like to launch something on Product Hunt - yay!

But I ve also seen alot of posts/comments from more technical folks around the web hating on non technical people for believing that you can go from 0-1 and that these new tools are best to speed up work for technical people who already know how to code, not for newbies who end up with something that works by copying and pasting crappy code spit out by LLMs of their choice.

I ve been working on some AI projects recently things like scheduled agents, API responders, and multi-agent systems that need to run continuously. One of the biggest headaches I ve run into is deployment.

Most cloud platforms (AWS, GCP, etc.) are built for stateless apps or short-lived functions. But for long-running, stateful agents, the kind that need to persist data, auto-recover from crashes, and expose custom endpoints it gets surprisingly messy. I ve spent so much time setting up VMs, Docker configs, and recovery logic than actually writing agent behavior logic.