Wrong Responses
Last updated
Was this helpful?
Last updated
Was this helpful?
The Wrong Responses dashboard serves as an in-built issue tracker, similar to JIRA, designed for BotDistrikt chatbots. It allows you to track users who have received incorrect responses and set conditions to manage and resolve these issues accordingly.
To mark a message as a wrong response, navigate to Inbox > Console. In the user activity window there will be a dropdown arrow with the default 'correct' text below the message. Clicking on the dropdown will allow you to mark the message as wrong. To access the Wrong Responses tab, click on the red arrow.
Every time a user receives a wrong response, BotDistrikt tracks the message. The Wrong Responses dashboard includes:
Filter Wrong Responses
Mark Response Status
Acknowledge
Resolving
Resolved
Ignored
Issue Fields
Tags
Agents
Set Due Date
Write Notes
Set Priority Levels
Replay the Response
Export to CSV
Use the Filters on the top of the page to filter records based on several fields. Each field has a specific filter use case.
ID
Finds all wrong responses from a specific ID
Assigned to
Finds all wrong responses assigned to a specific team member
Created by
Finds all wrong responses created by a specific team member
Updated by
Finds all wrong responses updated by a specific team member
Created At
Finds all wrong responses created at a specific time or date
Updated At
Finds all wrong responses updated at a specific time or date
Due At
Finds all wrong responses with specific deadlines
Status
Finds all wrong responses based on their current status
Priority
Finds all wrong responses categorised by urgency or importance
Tags
Finds all wrong responses labeled with specific tags
Notes
Finds all wrong responses with attached notes
Team members can update the status of a wrong response to track its resolution progress.
The available statuses include:
Acknowledge
All wrong responses are automatically marked as "Acknowledged" when logged.
Resolving
Set this status when actions are actively being taken to fix the issue.
Resolved
Mark the response as resolved when the issue has been fixed and verified.
Ignored
Use this status for issues that do not require further action.
The Issue Fields feature allows team members to add specific attributes to the wrong responses. The following types of fields are supported:
1) Notes
This allows team members to attach detailed comments to a response. Notes can include observations, explanations, or instructions for other team members.
2) Tags
3) Assigned to
This enables the assignment of individual team members to manage specific logs or responses.
4) Due Date
This ensures that deadlines are established for resolution.
5) Priority
Priority levels help classify responses based on their urgency and importance ranging from P0 to P3.
P0 - Critical Priority P1 - High Priority P2 - Medium Priority P3 - Low Priority
6) Actions
There are two buttons: Replay Message as well as Delete. Replay Message - Allows team members to simulate the corrected response in the same scenario where the wrong response occurred. Delete - Allows team members to delete the wrong response.
Filter wrong responses by clicking on add filter and selecting the appropriate attribute and function for the search parameter. To export filtered records, click on Select Action and Export rows to CSV.
Export filtered messages to CSV can be done in two ways by using Action > Export to CSV or Export to UAT.
Export to CSV will generate a .csv file with the following fields:
ID
An identifier based on the unique Message ID.
Date [Timezone]
This column reflects the timezone of the user exporting the data. For example, if the export is generated in New York, the column will show 'Date [GMT-05:00]'.
From
The source or type of user initiating the interaction such as user or bot.
From ID
A unique identifier for the sender such as user ID or bot ID.
From Name
Displays only the sender's display name.
Message
The content of the message exchanged during the interaction.
Reached Fallback
Indicates whether the interaction triggered a fallback response where "Y" stands for yes or "N" for no.
Story ID
A unique identifier for the story associated with the interaction.
Story Name
The name or title of the story.
Sentiment Value
A numerical score representing the sentiment of the user's message ranging from -1 for negative, 0 for neutral, and 1 for positive.
Sentiment
The sentiment category derived from the sentiment value such as positive, neutral, or negative.
Channel
The platform or medium through which the interaction occurred.
Widget ID
Only applies to Website Bot Widgets and cannot be used for Messaging Apps.
Chat History Link
A URL or link to access the complete chat history for the interaction.
Export to UAT will generate a .csv file with the following fields:
ID
An identifier based on the unique Message ID.
Description
The name or title of the story.
Message
The content of the message exchanged during the interaction.
Memory
This refers to the bot’s memory context and can be used to simulate data that the bot remembers from the user’s conversation.
User
This refers to the user context, enabling simulation of an existing user on BotDistrikt or a new user with attributes defined via variables.
Refresh
This acts as a caching identifier. When a response is retrieved, it is cached for 10 minutes. Changing this value forces the cache to clear and recompute the response.
Expected Response
The anticipated output or behaviour from the bot for the given input and context.
Actual Response
The actual output or behaviour observed from the system during the test.
Actual = Expected? (Y/N):
A validation field to confirm if the actual response matches the expected response.
Developer Comments
Additional notes or observations from the developer regarding the test case or discrepancies found.
provide a way to categorize and organize responses by assigning descriptive labels.
