Response Compliance Overview
Updated
Introduction
Since brands are engaging on multiple channels every day, this engagement should be compliant with the community guidelines to avoid crises for your brands and manage risk. The AI-powered legal compliance check ensures that each brand response adheres to - Brand Guidelines, Non-Profanity, Relevance, Semantics, Tonality, and Unbiasedness. If your response belongs to either of these 6 categories, it will generate a red flag.
In Sprinklr, with the support of smart compliance, the response has to check compliance when a brand community manager is engaging with the customers.
Note:
Users must have Enable Response Compliance permission to use this capability.
Currently, the model is supported for the English language and built based on our internal guidelines. However, customizing the model based on your guidelines/definition of categories is totally possible. We can also create a model in other languages, including German, Portuguese, French, Spanish, and Arabic, provided we have sufficient data in that particular language.
To learn more about getting this capability enabled in your environment, please work with your Success Manager.
Use Cases
This capability helps you to produce content that performs better based on the past performance of the brand and industry content. With this feature, AI generates a compliance score for your content with a detailed checklist of which parameters met and which did not. This capability helps brands to:
1. Engage appropriately with their customers
2. Improve their customer satisfaction score
3. Manage crises situations and risks
4. Maintain their reputation
Response Compliance Categories
The categories for determing whether the response sent by the agent adheres to the compliance standard are as follows:
1) Biased Content - This check flags the responses if the response is discriminatory along the lines of race/religion/gender/age/person or has opinionated content which could be controversial in nature.
2) Profanity - This check flags the responses if the response contains abuses, slurs, and/or adult content.
3) Relevance - This AI-powered checks the response on the relevance – whether the response is a relevant one based on the prior conversation. As a brand, you would never like to write a response that would be irrelevant to the conversation.
4) Tonality - This check flags the response on the basis of your tone. If the tone shows aggressiveness or lacks warmth and empathy, the response is flagged.
Customized Parameters - To get the following compliance checks enabled, please reach out to support at tickets@sprinklr.com.
Incorrect Salutation: The salutation at the starting of the conversation should have a personalisation while addressing the customer.
Hey user, Hi customer - Wrong ❌
Hi Cathy, Hello Mr. Smith - Correct ✅
Business Jargon/Abbreviations: The industry specific jargons and business words are difficult for customers to understand and will be flagged.
Hi, your dob is mentioned as 12/07/2001 - Wrong ❌
Hi, your date of birth is mentioned as 12/07/2001 - Correct ✅
Empathy: A distressed/frustrated customer expects some sort of empathy in the agent’s response, so this flag will be shown to the agent when the customer is distressed and the agent has shown no empathy in their response.
You're not supposed to do it that way - Wrong ❌
I understand what you’re going through - Correct ✅
Any other parameters specific to the business use case.
Why Sprinklr?
The accuracy of our model ranges from 80% to 90%.
The model works equally well for all industries.
We also provide customized models to suit the specific requirements of a client belonging to a particular industry vertical.
We constantly monitor and retrain our model on new datasets. We have relevant datasets from all industries to easily retrain the model so that the accuracy never falls below the desired level.