This website uses Cookies. Click Accept to agree to our website's cookie use as described in our Privacy Policy. Click Preferences to customize your cookie settings.
Hi Team,I have a CX agent which asks series of questions(like 10) to the
user which are of yes/no type. At the end of the conversation, we are
trying to show a conversation summary to the user. Currently im
utilizing Generators to create a summarizat...
Hi Team,In my cx agent, i have few intents like (speakToAgent,
confirm.yes, confirm.no). In one of the page, we have entry fulfillement
as (was i helpful?). Here i have these 3 intents as route transitions.
User might say any of these three. As a fal...
Hi Team,I was trying the find the exact schema structure for data store
responses. I have a data store that's been configured with FAQ and
unstructured documents. By default, in the agent responses, we get
"$request.knowledge.answers[0]". I logged th...
Hi Team,I'm using CX v3beta1 detect intent api call. In the return
response from CX, I dont find "currentFlow - displayName" within
queryResult object[documentation]. At the same time, i've enabled Cloud
Logging for my agent. While analyzing the resp...
Hi Team,I have a CX agent which is connected to a Conversation App(which
is linked to a data store -> cloud storage, where I have a csv file).
This CSV file has 60+ FAQs and its in the correct format (question,
answer). Assume, below is my csv file(G...
@xavidop , one general question. when its suggested to select Standard
nlu and when to have Advanced Nlu. And what’s the minimum confidence
score and max confidence score we should stick to?
confidence score of 0.7 works best. For 0.8, nlu matching is too strict.
For instance, there's an utterance "connect to agent". If user says "can
you immediately connect me with an agent" -> this utterance falls to
no-match for 0.8 confidence score. ...
Its 0.5765. Also i don’t understand how this phrase has such score when
its not related and trained.similar to that utterance, if i say “i want
to take additional course”, this too triggers speakToAgent intent