I am facing challenges when it comes to managing a quite wide explore. I want to be able to run a dedicated agent on top of a more streamlined agent. The idea would be for us to receive a very wide table (~ 500 dimensions) in BQ and then build refinements / extends in different Looker models. This is to handle permission management.
Anybody as manage to crack this challenge (permission management), Not even talking about Agent yet
Build a base Explore that contains all the fields that are needed by data analysts to build Looks & dashboards (our largest Explore contains 800 fields!!!)
Create a new Explore that extends the base Explore, and use the fields parameter to restrict the number of fields to 50-75.
The potential problem with this approach is that you now have 2 versions of the Explore for users to select in the Explore menu. You cannot hide the base Explore. Here is the approach I have taken:
To differentiate the extended Explore from the base Explore in the Explore menu, the extended Explore has a group label “Self-Service - <business unit>” so that it is grouped under a different section, and appears towards the bottom of the Explore menu.
The Explore label is “<base Explore label> (Simplified)” to signify that it’s a simplified version.
The extended Explore has an access grant so that only people with the chat_with_agent permission can see it.
Currently, permissions for agents are not very granular. I would say that permission management and observability have been de-prioritised, as the product team seem to be prioritising new features and improvements (fair enough).