Ensure your agent’s responses maintain safety and brand adherence.
stop_inappropriate
Description: Prevent responses containing offensive language.
Regular Expression: /\b(offensiveWord1|offensiveWord2)\b/i
Say Phrases: TRUE
This setup ensures responses containing “offensiveWord1” or “offensiveWord2” are immediately halted.
flow_redundancy_cutoff
\b(let's start|please hold on|let me check)\b
TRUE
(halts response when detected).flow_redundancy_cutoff
\b(let's start|please hold on|let me check)\b
TRUE
<break>
, <prosody>
, and <emphasis>
in the replacement string.
You may define pronunciation rules using regular expressions and replacements, including support for regex capture groups.
(\d{3})
), you can refer to these in the replacement string using \1
, \2
, etc. This allows you to reformat matched text dynamically.
(651) 359-2923
into:
“six five one [pause] three five nine [pause] two nine two three”Use the following pronunciation rule:
$begin:math:text$?(\\d{3})$end:math:text$?[ -]?(\d{3})[ -]?(\d{4})
\1 <break time="0.5s" /> \2 <break time="0.5s" /> \3
FALSE
/\bLouvre\b/
/ˈluːvrə/
FALSE