Awesome!
In the "Protocol Handshake" section of what's happening under the hood - it would be great to have more info on what's actually happening.
For example, more details on what's actually happening to translate the natural language to a DB query. How much config do I need to do for this to work? What if the queries it makes are inefficient/wrong and my database gets hammered - can I customise them? How do I ensure sensitive data isn't returned in a query?
One thing I am having a hard time wrapping my head around is how to reliably integrate business logic into a system like this. Just hook up my Rails models etc. and have it use those?
Let’s say I’ve got a “widgets” table and I want the system to tell me how many “deprecated widgets” there are, but there is no convenient “deprecated” flag on the table—it’s defined as a Rails scope on the model or something (business logic).
The DB schema might make it possible to run a simple query to count widgets or whatever, but I just don’t have a good mental model of how these systems might work with “business logic” type things.
Sounds like you may want an MCP server for your Rails API instead of connecting directly to db.
This is exactly what I've been trying to figure out. At some point the LLM needs to produce text, even if it is structured outputs, and to do that it needs careful prompting. I'd love to see how that works.