Most RAG demos are graded by an audience that cannot check the answer. Ask a docs bot something, get a fluent paragraph back, nobody in the room knows whether sentence three is invented. The demo lands.
Billing is not like that. When a subscriber asks "why is my bill higher this month" they are holding the invoice. They will check.
We built a WhatsApp assistant for an ISP that answers plan and billing questions. This post is about the two things that turned out to matter, neither of which is "we used CRAG":
A document corpus and a billing API are both called "retrieval" and they fail in completely different ways.
The failure that actually bites is not bad retrieval. It is the model taking correct numbers and narrating them wrong.
Code is from the real system. Comments translated from Spanish, otherwise untouched.
The pipeline
inbound message
↓
state gate ──────────────► human agent active? bot writes nothing
↓
hybrid retrieva
Discussion
Your thoughts matter!
Your input is valuable—be the first to share it!