Ack on the guardrail analogy.
On fireworks - do you just run serverless or do you take their dedicated instance. My question is how do you ensure that the model is not being manipulated to getting stuff it shouldn’t be.
I meant for a model. Like agents could be many within an organization, instead of patching up each agent with a security solution, wouldn’t it be easier to build one that wraps around the model ?
So my first thesis that I want to prove is - are all enterprises going to start self hosting open source models ? If yes, then one will need to deploy a solution around the models to act as a firewall. A firewall fine tuned for the context that’s coming in and coming out of a model. Way different from how microservices work today.
Love the launch, is there a way to add observability tools like langtrace into this so that we know what kind of prompts and inputs are going into the flows?
Looking forward to understanding the second part of this.
In fireworks - how does one build guardrails or it does not matter to companies hosting their models on fireworks?