Isaac Dominic

I've started asking one thing before I give anyone advice about their product. Do you want me to help you think, or do you want me to tell you what I would do?

They are completely different conversations and most of the time people want one and receive the other.

I have started asking one thing before I give anyone advice about their product. Do you want me to help you think, or do you want me to tell you what I would do?

They are completely different conversations and most of the time people want one and receive the other.

Our callers mix Hindi and English in the same breath: "haan toh mein bol raha tha, why are you calling me?" We assumed language handling was a detection problem. It turned out to be about six separate problems, and we found them one at a time, in production.

1. Detecting a language switch without flip-flopping
A caller says one English word and the bot jumps languages. We settled on a heuristic switch with guardrails you can configure per agent:

• a minimum number of words per turn (default 3)

• the same language for consecutive turns (default 2)

• a dominant-language threshold (0.6) from a fastText classifier

• a reset of the counter on mismatch, so one stray turn doesn't count

• "meta" references ignored, for example someone saying "English" while speaking Hindi

2. Callers who just tell you what they want
"Let's speak in English" shouldn't need two confirming turns. We added explicit request detection, in English and Hindi (e.g. " "). It bypasses the heuristics and switches immediately.