Personality protocol for a chatbots platform. How to share personalities among different layers and components. At the end of the day is customization and parametrization of LLM instructions, however an interesting topic to explore.
I agree with many points, however, it depends on the abstraction that you need and the abstraction depends on the architecture you are adopting.
For example, if you are doing DDD and your repository implementation is about SQL, adding another layer of abstraction is not worth. But if your design is less sophisticated, or you are in an early stage of the project, you may find appealing to use that abstraction.
It's so hard to say because of all the noise and hype around the issue. If what the AI evangelists are saying is true, then no -- this is a very different thing than those, and none of this applies to them.
reply