Skip to content
anythingai.space
Conversational AIintermediate12 min · 9 steps

NLU and Dialogue State

How a classical bot turns a sentence into an intent, entities and sentiment, then tracks what it knows across turns and fills the slots a task needs.

required slots filled0/3
intent confidence—
raw textINPUT: FREE TEXTIneedahotelinParisnextweekUserNLUintent + entitiesDialogue managerBooking APIbook_hotel(...)?
errorrequestdatasignalresponsetool call
metrics are illustrative
1 / 9
ProblemStep 1 of 9

An API can't read a sentence

The user types “I need a hotel in Paris next week.” The booking API needs book_hotel(city, check_in, nights). Between the two sits a gap: free text on one side, typed parameters on the other.

The classical pipeline closes that gap in two moves: understand the sentence (NLU), then track what's known and what's missing (dialogue management).

Lesson 2 of 8 in Conversational AI