Our startup has been building agents inside of a workspace for the past few months. We had our first version about nine months ago, and the UI looks almost identical to OpenAI's.
That said, it's going to be very interesting to see if one AI Agent platform becomes the standard, or if people end up having different AIs for different platforms.
On our end at least, we are planning to keep our agent builder, even if we end up using OpenAI on the backend. At the very least we will at least maintain the agency to utilize another platform if we want.
I’m not sure exactly what you mean by data requirements, but we’re using Lang chain and still calling to GPT on the backend.
We’re building agents that are a little bit less autonomous than what is popular right now, mostly using them as chat bots that can interface with a workspace or chained into a type of workflow. Basically everything in our workspace will be accessible to the agents.
We will be publishing the github repo in the next couple of weeks. As you can imagine this is happening in real time and we want to cross check few things before we publish the repo.
I will reply to this thread once that has happened.
That said, it's going to be very interesting to see if one AI Agent platform becomes the standard, or if people end up having different AIs for different platforms.
On our end at least, we are planning to keep our agent builder, even if we end up using OpenAI on the backend. At the very least we will at least maintain the agency to utilize another platform if we want.