This looks really cool! Tools like Retool are great, but they tend to be yet another thing to maintain in the long run, adding to the cognitive load.

Would there be a means of limiting which services and functions each query can call manually to impose more specified guardrails? and how is the “human in the loop” thing enforced?

Thanks!

> Would there be a means of limiting which services and functions each query can call manually to impose more specified guardrails?

By default, all functions which are registered are available for use in a Run. It is also possible to explicitly attach a subset of functions to any given "agent".

> how is the “human in the loop” thing enforced?

It is possible to return what we call an Interrupt from within your function code [1]. When this is received, the run is paused until it has been satisfied. Inferable's control plane handles this not the model in case it isn't clear.

[1] https://docs.inferable.ai/pages/human-in-the-loop

Thank you!

from someone who has never made a Chrome Extension and never used TypeScript