You are viewing an Archived item in your Knowledge Base, it is not publicly accessible.

Contact Us

If you still have questions or prefer to get help directly from an agent, please submit a request.
We’ll get back to you as soon as possible.

Please fill out the contact form below and we will reply as soon as possible.

  • Go to Haptik Website
  • Contact Us
  • Home
  • Bot Building
  • Essentials

How does the feedback collection mechanism work?

Written by Soham Amburle

Updated on November 17th, 2021

Contact Us

If you still have questions or prefer to get help directly from an agent, please submit a request.
We’ll get back to you as soon as possible.

Please fill out the contact form below and we will reply as soon as possible.

  • Getting Started
    Build Deploy Analyse Manage Account Bot Deactivation
  • Bot Building
    Essentials Smart Skills Steps User Messages Bot Responses Entities Connections Customisations User feedback collection Testing Whatsapp Bots NLU Bot Maintenance
  • Smart Agent Chat
    Set up Admin Settings MyChats Section (Agent Inbox) Live Traffic Section Teams Section Archives Section Analytics Plans on Smart Agent Chat
  • Conversation Design
    Design Basics Design Guides Designing for Platforms Designing WhatsApp Bots
  • Developer Guides
    Code Step Integration Static Step Integration Shopify Integration SETU Integration Exotel Integration CIBIL integration Freshdesk KMS Integration PayU Integration Zendesk Guide Integration Twilio Integration Razorpay Integration LeadSquared Integration USU(Unymira) Integration Helo(VivaConnect) Integration Salesforce KMS Integration Stripe Integration PayPal Integration CleverTap Integration Fynd Integration HubSpot Integration Magento Integration WooCommerce Integration Microsoft Dynamics 365 Integration
  • Deployment
    Web SDK WhatsApp Facebook Instagram Sunshine Conversation LINE Google Business Messages Telegram MS Teams Bot as an API iOS SDK Android SDK
  • External Agent Tool Setup
    Zendesk Chat Salesforce Service Cloud Freshchat Zoho NICE CXOne Gorgias
  • Analytics & Reporting
    Intelligent Analytics
  • Notifications
    SMS Notifications Success Measurement
  • Commerce Plus
    Catalog Integration Bot Building Guide Channel Deployments Unified ML Pipeline Documentation
  • Troubleshooting Guides
    Error Messages FAQs
  • Release Notes
+ More

Table of Contents

What is CSAT?What is a good CSAT rating?How does the Feedback module get triggered?How does the Feedback collection mechanism work?Editing the Feedback Smart SkillWhat are the benefits of Feedback collection?Where can we check the Feedback Analytics?What to do if your Feedback ratings are low?

User Feedback is an asset

User feedback is very critical for any business. It tells you how your bot is performing, and it lets you know if the bot is functioning well or not, whether the bot is able to solve user's queries or not. It gives you an overview of every single aspect with respect to your bot. Though we have numbers on Intelligent Analytics like Bot Automation, Query Completion, Funnel Completion Rate, User Feedback comes directly from the user and is not an induced number thus a better way to make improvements in the bot. 

Every new bot that is created on the Conversation Studio tool, will by default have this Feedback Skill in it, with the name Collecting User Feedback - CSAT.

What is CSAT?

CSAT is short for Customer Satisfaction, which is a commonly-used key performance indicator used to track how satisfied users are with your organization's products, in this case, bots. It shows the percentage of satisfied users.

CSAT is an important metric that lets you see what your end users are thinking about the bot.

This metric perfectly compliments the other metrics like “Bot Automation” and “Query Completion” because where these metrics showcase the performance of the bot’s NLU and the conversation flow designs, CSAT at the same time lets you know if the bot is actually helping the end-user or not. The union of these 3 ratings thus gives you a holistic idea of the bot’s actual performance.

CSAT is calculated by -

Here, the positive responses mean a total number of 4 and 5 ratings received. 

The responses from the users are collected in the following way, as shown -

What is a good CSAT rating?

  • A good CSAT rating varies from industry to industry, as claimed by ACSI (American Customer Satisfaction Index)
  • A few examples of good CSAT ratings across industries are -
    • Airlines: 75%
    • Ambulatory Care: 74%
    • Apparel: 77%
    • Athletic Shoes: 79%
    • Hospitals: 69%
  • Since we do not specify a certain category for our bots, we can say that on average, above 70% of CSAT is a good CSAT.

How does the Feedback module get triggered?

Feedback is triggered at the logical end of any query. Once the user has reached the logical end of the conversational journey, we ask the user to provide feedback. 

You can denote the logical end of the query by marking the step as an End step, or Context-clear step, or End step+ Context-clear step. 

On reaching any of these steps, the feedback message "Was I able to help you? Yes or No?" is sent by the platform. If the user replies with a yes or no, the feedback journey gets triggered and the user is taken through the next steps as per the feedback flow.

Delete

Can we change the "Was I able to help you?" message?

  • No, it comes from our pipeline and it is hardcoded, so you cannot change it. 
  • You can change the further subsequent replies given by the bot though.
  • You need not add it for every step.

If your Bot is multilingual, the language equivalent of Was I able to help you? will be sent. It is a system message, meaning you need not add it for every step. 

You can also configure the time delay, for the system message to be triggered through Business Manager > General Settings > User Feedback.

How does the Feedback collection mechanism work?

The bot would ask Was I able to help you?, and the answer to this would be either Yes or No.
 

If the user messages No, we take feedback as 1. The bot was not able to help so the rating is 1. Further, the bot tries to take qualitative feedback (comments) from the user, as shown.

Delete

Note: 

  • CSAT cares only about the percentage of Satisfied (Yes) ratings.
  • After a user has clicked on "No" as an answer to "Was I able to help you?" it is evident that they are not satisfied with the bot's responses, so rather than annoying the user further by asking to rate on a scale of 1-5, if they have said No, we take it as a "non-satisfied user", and the rating could either be 1,2 or 3, but default 1 makes the most sense logically. 
  • Ideally, for a bot, if the user asked a question, to which the bot gave an answer and then for the bot’s question “Was I able to help you?” the user’s reply was “No”, then for the bot, it has failed which is why we take the rating as 1. 

If the user messages Yes, the bot would ask the user That's good to know. On a scale of 1 to 5, how would you rate the overall experience?

For every rating, that the user gives, there is a response available with the bot, so as to maintain the flow for collecting the feedback. 

Now, if the user gives a 4 or 5 rating, the bot would respond in the following way -
 

If the user gives a 3 rating, then the bot would respond as follows -

If the user gives a 1-2 rating, the bot would respond apologetically, and the flow would be as follows -

Basically, on every touchpoint, we take quantitative feedback on a scale of 1 to 5 and then, we try to take qualitative feedback through the responses. This maintains the conversation flow. 

Editing the Feedback Smart Skill

  • In order to edit the Feedback smart skill, you can change the flow in the Conversation Studio tool, or you can also add agent handover depending on your business requirements. 
  • Other than that, you can make changes in the following domains - 
    • You can add Steps as required.
    • You can edit the User Messages and the Bot Responses within the steps. 
    • You can make changes to the connections too, you can -
      • Add/Remove a connection between steps.
      • Change the conditions present in the connection. 
    • You can also add a Skill if required.
Delete

Warning:

Editing the Feedback Smart skill has one limitation, which is - 

  • If any bot responses are changed, then some entities might not get captured. This is because each of the feedback entities contains previous context tags.
  • What that means is, while changing the bot response,  if you remove the statement which the entity expects (as per its previous context tags section), then that entity will not be captured.

The workaround for this is, the bot-builder should be made aware of the fact that before changing bot responses of any steps that contain a feedback related entity, they should first check the "Previous context tags" and then only accordingly alter the bot responses. The goal is to ensure that even with the modified bot response, the substring from the entities' section is maintained as it is.

What are the benefits of Feedback collection?

  • With the Feedback journey, we noticed that the feedback collection rate increased.
  • It is omnichannel. Since it is a journey, it would work on any channel where the bot gets deployed.
  • You can add new flows within the journey, you can also alter the Bot Response.
  • You can add agent handovers, at an instance where the users give a poor rating.

Where can we check the Feedback Analytics?

Now that we have seen how feedback will be collected within the bot flow. Let's take a look at how the collected feedback will be viewed on Intelligent Analytics

You need to visit the Intelligent Analytics of your bot and visit the CSAT section. There you will get to see all the ratings your bot has received from the users, as shown -


Delete

If a user replies to "Was I able to help you?" with a Yes, and abandons the chat, by default the rating is captured as 5. 

In your bot's analytics, you would see this rating with a default message, and the purpose of this message is to let you know that this rating has been generated since the user did not stay on the chat post replying to the feedback message. 

Why is the default rating been captured as 5, in this scenario?

  • As we have seen above, we register the CSAT rating as 1 if the user responds with No. If we do not default Yes to anything then the total number of 1 feedback i.e negative CSAT rating increases.
  • This not only negatively tilts your CSAT, but it is also a false representation of CSAT since there were many people who said "Yes" but just did not leave a rating.
  • From studying the data, we have observed that 52% of people who clicked on "Yes" gave a 5-star rating, whereas 24% left a 4-star rating. The remaining percentages of 1,2 and 3 ratings are minimal. However, the positive ratings after clicking on "Yes" are always the dominant majority. Hence if a user clicks on "Yes" and leaves without giving any rating, we default the CSAT rating to "5"

What to do if your Feedback ratings are low?

If you are receiving a poor CSAT rating, you can start looking for the following points

  • Identify the "skills" that are majorly getting a low rating from users.
    • The first point to start looking from is the "skillset" column.
    • Going over this column should give you an idea of what is the most common starting "skillset" where the feedback is low.
  • Go through the comments to get a pattern of common problems.
    • Now that you have identified the popular "skillsets", the next thing is to look at them separately and go through the comments to get a general idea of what the overarching problem could be.
    • Example: In the Order bot, users had feedback on the Track my order status, i.e. when users would request for the order status, they would receive a very static message, like your order will be delivered in a week, from the day of purchase. Here, the users did not get real-time tracking data. Hence, they would give poor ratings. 
  • Checking comments do help you understand where the problem lies. 
    • Go through the chat links to get a detailed understanding.
    • Finally, for each "skillset", click on the chat link to go through the conversation that leads the user to leave the low feedback to get a complete idea of what went wrong.
Delete

Point to note: 

When the user ends his chat with the bot, he would see the feedback collection mechanism, wherein the feedback would be collected in the conversation flow, as seen above.

But, on the other hand, when the chat is transferred to an agent, and at the end of the chat when the feedback is being collected for an agent, the user would see the Agent feedback module where they can provide star ratings between 1 to 5 and add comments.

Also, if the agents ask for feedback via {feedback} smart action, you can check the feedback by clicking on the Email CSAT Report button on the CSAT page. You will receive a CSV on your email, which will show you which feedback is assigned to the agent and which one is assigned to the bot. 

Another way to check the feedback for agent and the bot is by hovering on the ratings as shown in the image below - 

To know more about how to check the CSAT score, click here.

Was this article helpful?

Yes
No
Give feedback about this article

Related Articles

  • What are Smart Skills?
  • How to check the CSAT?

Platform

  • Conversation Studio
  • Smart Skills
  • Advanced NLU
  • Intelligent Analytics
  • Omnichannel
  • Smart Agent Chat
  • Enterprise Security
  • Integrations

Solutions

  • Conversational Commerce
  • Lead Generation
  • Customer Care
  • WhatsApp
  • Conversational IVR
  • Google Business Messages

Industries

  • Retail/ E-Commerce
  • Financial Services
  • Travel & Hospitality
  • Telecom

Knowledge

  • ROI Calculator
  • Reports & Research
  • Case Studies
  • Webinars
  • ISAT
  • Tech Blog
  • Business Blog
  • Resources
  • Haptik v/s Yellow
  • Haptik v/s Liveperson
  • Haptik v/s IBM Watson
  • Haptik v/s Verloop
  • Conversations on AI

Company

  • Why Haptik
  • About Us
  • Careers
  • News & Media
  • Awards & Recognition
  • Contact Us
  • Partnerships
  • Investor Relations

Subscribe

Sign up to recieve the latest updates

Find us on

  • Twitter-footer
  • Linkedin-footer
  • YT-footer
  • Insta-footer
  • G2-footer
  • Facebook-footer

Knowledge Base Software powered by Helpjuice

Copyright © jio Haptik Technology Limited 2021 | Data Security & Privacy Policy | GDPR

North America | Asia Pacific | Africa | enterprise@haptik.ai

Definition by Author

0
0