Conversation History

All interactions between users and the bot are captured and available in the Conversation History workspace in the Bot Builder interface. Using the Conversation History, Administrators, and Skill Developers can view the bot and user interactions grouped as conversations and understand the details of underlying system events. This is particularly useful when troubleshooting problems that occur with the bot, configured channels, or integrations.

A conversation begins when a user enters a phrase and starts a skill. The conversation ends when the skill is fulfilled by executing all steps as part of the conversation flow, the user ends the conversation by //abort command, due to idle time out in the conversation flow, and the current skill branches to the next skill.
All the system skills and small talk conversations are also captured as part of the conversation history. The Conversation history is stored at the bot level within the tenant.

On the Bot Builder, click “Conversation History” from the Bots menu on the left navigation pane as shown below.

Clicking Conversation History opens the following workspace.

The history of chat interactions is grouped as Conversations. The Conversations History has the following filters:

Channels
Users
Skills Category
Skills
Date Range - filters by the conversation start date and time
Events- are interactions between the user and the bot.
Initiated By
Conversation ID
Session ID - The filter is available if you are subscribed to Session-based Licensing.
Channel Account ID

The default filter applied is All for all the fields and the Last 24 hours data will be shown for the Date Range filter. In the filters section, you can select Show Only Error Conversations to see the list of conversations that resulted in Platform Errors, errors caused inside the virtual agent. This will help to identify the conversations with an error quickly.

Conversation List

The most recent Conversation is shown on the top of the list as the default sort order is the Start Date based on the Date Range filter. A user can alter the sort order by selecting the field from the dropdown next to the field name. Sorting can be performed on the selected field. You can sort the filtered conversations on Channels, Users, Skills Category, Skills, Start Date, and Time.

Select the conversation from the list to view the details in the Conversation Logs section. You can hide the list of conversations to have more space to view the events related to the selected conversation.

Conversation log

Once the required Conversation is selected from the list, the Conversation log section is populated with Conversation details. On the section header, you can view Channel used to trigger the conversation, Skill executed in the conversation, and Unique Conversation ID.

If you are subscribed to Session-based Licensing, additional details are also available:

Session ID in which the conversation took place
Session Flag: New or Existing flag that indicates if there were other conversations that were executed as part of this session. The New flag suggests that the Session started along with the conversation. The Existing flag suggests that the conversation is part of already ongoing sessions.

Troubleshoot Events

The conversation log also contains the list of events that occurred during the specific conversation between the bot and the user. Only one conversation's events can be viewed at a time. The date in the log for each Conversation is displayed in chronological order of the events that occurred with the oldest event on top and the newest on the bottom. Therefore scrolling down through the events follows the order of the conversation from start to finish.

The Conversation’s events are grouped by Date and shown as expanded by default. A user can unselect the Expand Events checkbox in the details view of the Conversation to have a minimized view. If there is a Date change in between an ongoing conversation then the date will be mentioned in the conversation Timeline.

Icons before each event in the log represent the actor:

In order to improve Luma performance, the troubleshooting event logs are retained only for 7 days. The data is purged everyday. There is no impact on Dashboard and Reporting. But, the Web Widget chat history will be retained only for 7 days. It is recommended to download and attach the Conversation Log to the support ticket that needs troubleshooting a conversation.

The following are the list of events that are captured as part of the conversation and their associated meaning:

Channel Event Received: The Virtual Agent received an event from a channel which it will process and respond.
User Message Received: The Virtual Agent received a user message from a channel which it will process and respond.
Message Validated: The Virtual Agent has validated the authenticity of the incoming message in order to verify and confirm that the message came from the stated sender.
Access Permissions Checked: The Virtual Agent performed the pre-requisite permission checks to determine whether the user is allowed and permitted to interact with the Virtual Agent.
User Authenticated: The Virtual Agent has auto-verified and confirmed the identity of the user
User Auto Registered: The Virtual Agent has auto-registered the user for the Virtual Agent services.
User Status Checked: The Virtual Agent performed the user status checks to determine whether the user is active and allowed to interact with the Virtual Agent.
User Manually Registered: The Virtual Agent has registered the user via the manual registration process for Virtual Agent Services.
User Registration Cancelled: The Virtual Agent has canceled the user registration via the manual registration process for the Luma bot services.
Fallback Detected: A Virtual Agent is attempting to parse the user message and recognized that the skill is not identified or skill with less confidence score identifier causing the fallback actions to be triggered.
Skill Ambiguity Detected: A Virtual Agent is attempting to disambiguate the user's intention so that it can capture & infer the human intent confidently and accurately.
Skill Recognized: The Virtual Agent recognized the user's intention based on the user-given phrase/invocation name/skill identifier.
Skill Ambiguity Resolved: A Virtual Agent has successfully and confidently disambiguated the user's intention.
Rephrase Requested: The Virtual Agent asked the user to rephrase the request to identify and identify the correct/right skill with greater confidence.
Skill Permissions Checked: The Virtual Agent has verified the user's access permissions on the skill that was triggered by the user from the channel.
Response sent: The Virtual Agent delivered a response to the user with an informational message, clarification prompt requesting input from the user, or a hangup phrase.
Conversation Flow Started: The conversation flow of identified skill is started to collect information in a specific order from the user and guide the user through a series of configured steps as part of the skill.
Attribute Prompted: An Attribute value was requested in the conversation asking the user to provide a value for it.
Attribute Value Filled: An Attribute was successfully filled with a value obtained either from the user or a third-party fulfillment system during the conversation.
Attribute Value Validated: A validation was performed on the Attribute’s value obtained from the user against the pre-configured validation rules.
Error Rules Evaluated: The operation error rule set comprising of a collection of ordered rules with a set of execution semantics was evaluated and executed the rule’s actions based on the results of the rule’s condition evaluation.
No Data Rules Evaluated: The operation no data rule with a set of execution semantics was evaluated and executed the rule’s actions based on the results of the rule’s condition evaluation.
Success Rules Evaluated: The operation success rule set comprising of a collection of ordered rules with a set of execution semantics was evaluated and executed the rule’s actions based on the results of the rule’s condition evaluation.
RuleSet Evaluated: A rule set comprising of a collection of ordered rules with a set of execution semantics was evaluated and executed the rule’s actions based on the results of the rule’s condition evaluation.
Conversation Branched: Conversation branched to a subskill based on the conversation routing rules.
Conversation Aborted: The conversation was interrupted.
Conversation Errored: The conversation was abruptly terminated due to an irrecoverable system error.
Agent Transfer Rejected: Conversation transfer to the agent is unsuccessful due to the unavailability of a Support agent.
Attribute Prompt Skipped: An Attribute was successfully skipped as requested by the user during the conversation.
Channel Notification Sent: The Virtual Agent delivered a notification to the user on the intended Channel with the message configured as part of Channel Notification.
Contact Custom Attributes Updated: A Custom User Attribute has been successfully filled with a value obtained either from the user or a third-party fulfillment system during the conversation.
Conversation Flow Completed: The conversation flow is complete after the identified skill is fulfilled/ erred or the skill is aborted by the user during the conversation.
Conversation Topic Changed: End User triggers a skill using command while already executing a skill. This changes the conversation topic and the already executing skill is aborted automatically.
Follow-up Notification Sent: The Virtual Agent delivered a follow-up notification to the user on the intended Channel with the information configured as part of the Follow-up.
Integration Executed: An Integration operation was performed by the Virtual Agent to collect, modify, or post information in a pre-configured Application Instance.
Ongoing Chat Agent Inactivity Timeout: A conversation has timed out due to no response from the Support Agent during the conversation with the End-User.
Ongoing Chat User Inactivity Timeout: A conversation has timed out due to no response from the End User during the conversation with Bot or Support Agent.
Support Agent Accepted Chat: A conversation transferred to Agent has been successfully accepted by a Support agent.
Support Agent Ended Chat: A Support agent can end an active conversation after interacting with the end-user.
Support Agent Response Sent: Support Agent responds to the end-user with a message during a conversation with the User.
System Command Executed: System command is executed by the Virtual Agent as requested by the End-user.
User Aborted Agent Transfer: The End User has aborted the transfer to agent request before an available support agent could accept the conversation request from the Waiting queue.
User Aborted Bot Conversation: End User aborts or exits the conversation using the abort command before a Skill was identified or during an ongoing conversation with the bot.
User Aborted Support Agent Chat: End User aborts or exits an ongoing conversation with a Support agent using the abort command.
User Added To Waiting Queue: The Virtual Agent has successfully added the End User Conversation to the Waiting queue and the request is pending to be accepted by a support agent.
User Inactivity Timeout: User Conversation has timed out due to no response from the End User to the bot within the user's inactivity timeout.
User Message Sent To Support Agent: End User message has been sent to the Support Agent during an ongoing conversation.
Waiting Queue Inactivity Critical Timeout: The user conversation is pending in the Waiting queue and has not been accepted by any available support agents before the Waiting Queue Warning timeout is reached.
Waiting Queue Inactivity Warning Time out: The user conversation is pending in the Waiting queue and has not been accepted by any available support agents before the Waiting Queue Critical timeout is reached.
Automation Workflow Invoked: Luma Virtual Agent invokes the Automation Workflow service during the Skill execution.
Intent Information Presented: The Virtual Agent presents the end-users with the identified Knowledge Articles or Services or both, based on the user query.
Knowledge Search Feedback Captured: The End-User’s Feedback is captured by Luma Virtual Agent for the Knowledge Search results provided.
Knowledge Topic Browsing Retrieved: The End-User requests to Explore available Knowledge Articles and Luma virtual Agent receives Topic browsing URL from Luma Knowledge.
Knowledge Topics Prompted: The Virtual Agent has identified Knowledge Articles for the user query and prompts the user to select one of the relevant topic.
Knowledge Topic Validated: Luma Virtual Agent has validated the Topic selected by the end-user against the topic list presented to the user
Skill Status Checked: Luma Virtual Agent checks if the requested skill is Active or Inactive.
Support Group Status Checked: When Transfer to Agent is requested and the End-user selects a Support group to talk to. Luma Virtual Agent verifies if the support group selected by the end-user is online and inside business hours, before assigning the user request to the group.
User Actions Suggested: The Virtual Agent presents the end-user with the identified information and suggests the user take the next step by selecting one of the options.
Search Results Identified: Based on the phrase entered by the end-user, the Virtual Agent identifies the user’s intent to view Knowledge Articles or Services.
Results Filtered and Representation Identified: Based on NLP setting and representation settings, Bot has decided if the end-user should be presented with Knowledge followed by Skills or Knowledge and Skills together.
Waiting User Chat Retransferred To Group: The Support agent transfer the end-user request from the Waiting queue to another Support group.
Ongoing User Chat Retransferred To Group: The Support Agent transfers the ongoing user conversation to another support group.
Survey Feedback Prompted: The Virtual Agent requests the end-user to provide feedback for the skill execution or conversation with the Support Agent.
Survey Feedback Responded: The end-user responded to the Virtual Agent with feedback for the skill execution or conversation with the Support Agent.
Survey Prompted: The Virtual Agent prompts the end-user to respond to the Customer Satisfaction Survey for the skill execution or conversation with the Support Agent.
Survey Responded: The end-user responds to the Customer Satisfaction Survey triggered for the skill execution or conversation with the Support Agent.
KPI Metrics Calculated: The Virtual agent calculates the configured KPI metrics in the executed skill.

View Context

In the conversation log, the request context is also available as part of the event. It could be accessed by clicking on the icon associated with the event.
Below are the icons available on the Conversation logs:

1) Attributes:

Click on the attribute icon to view the variables and their values at a specific step.

The context variables popup includes the values for the global and local variables used in the skill and operation.

2) Integration:

Click on the Integration icon to view the details about the operation executed, request details sent, and the response received from the web service.

On the Request tab, you can view the details of operations executed and information sent to the operation to execute the task at the third-party system.

On the Response tab, you can view the response received from the Webservice operation after the execution of the task at the third-party system.

3) Ruleset

To view information on the rules executed, click on the Ruleset icon. Here you can view the rule and the executed status (true or false).

4) Search Results Logs (Knowledge and Service Search)

If your organization is also subscribed to Luma Knowledge and your Luma VA tenant is associated with your Luma Knowledge tenant, the Virtual Agent looks for matching Knowledge Artifacts as well as matching services for every user request. Refer to Accessing Luma Knowledge through Virtual Agent for more information.

In such a case, you can view the complete search logs by clicking on the View Search results icon. Here you can view the details on the matching Knowledge Articles found in Luma Knowledge for the user request along with the matching services (skills) available in Luma VA.

The debug logs provide the below information:

For Knowledge Artifact search:

On the Knowledge tab, you can the details:

Applied Configurations in Luma Knowledge
Metadata generated from the user phrase, which are used to identify matching articles
Filters applied such as Permission, Relevancy score, etc.
Matching Articles with the respective information such as Confidence score, Relevancy score, Confidence band.

The information enables the Administrator to understand how the request is processed in Luma Knowledge and presented to the user on Luma Virtual Agent.

Under Response Generated event,

‘Number of Levels’ indicates how results are presented to the user. When the count is more than 2, Guided Conversation is presented to the user.
The topic in the Artifact list represents the parent topic under which the Artifact is presented in the Guided conversation. If Topic information is not available in the Article list, it indicates that the user is presented with a list of Knowledge Articles as result.

For Services Search:

On the Services, you can view the list of matching services identified by Luma based on the user search phrase.