Logs provide additional information to review, debug and troubleshoot bot conversations. It provides a self-service platform for the users to proactively analyze the cause of communication interruption if any. Previously, these conversations could only be accessed from the Khoros Care Agent View dashboard or Flow Chat view. With the new Flow Logs, you can view project interactions from the Logs window.  Enabling Flow Logs Flow users with the Logs permissions only can access the Logs feature. To add the Logs permission to a member: Click Profile From the drop-down option, click Members . Select your profile from the member list. Click Logs in the Update roles for window. Click Save Interaction overview The overview of all interactions shows the following info for each interaction: STATE: Whether an interaction is still open, resolved or has a runtime error CREATED AT:   Date when conversation initiated  UPDATED AT:  Date when conversation last activity was updated CHANNEL: Social channel or community on which the conversation was initiated THREAD ID: Conversation thread ID number CONV. ID:  Conversation ID number INTERACTION ID:  Khoros interaction ID number (if applicable) It is also possible to filter the list of interactions by the following:  Name of customer Thread ID or identifier of the customer Care conversation ID You can view the details of the conversation by clicking on any interaction. At a time, you can view 20 interactions in the tab, if you have more interactions you can scroll to use the pagination option to view older interactions.  The interaction overview does not automatically show any new interactions. Use the REFRESH button to update new interactions. Interaction details For each interaction, you can see detailed information about the activities taking place within each interaction. Activities are sorted by date (last updated first).  Actions are grouped by each trigger that has invoked the actions. For example, when a customer has sent some text that got matched by a flow, it returns a message, you can clearly see these grouped together.  You can also sort the activities by the time when they were created using the SORTED BY TIME filter option. The time is by default listed as UTC time. Use the timezone option at the bottom to view the activities in a local timezone.  With extremely long interactions, there is also an option to scroll to a specific time using the JUMP TO option.  For each individual trigger, action or event, you can view additional details by selecting them. Each event might show different contextual information. For example, a matched Flow by intent will also show the intents that got matched. The interaction details do not automatically show any new activities. Use the REFRESH button to update new activities.

This article explains definitions for all the Flow metrics captured in Flow Analytics. Flow Metrics  Flow analytics captures events that take place during user interaction with a chatbot. With each reported event, you can find an agent_id and thread_id . The agent_id relates to the Flow project and the thread_id relates to the interaction with a customer. When considering the Flow event metrics like interaction, handover or resolve, you might see small variants in the reported numbers; this is expected when you compare a metric for a specific period. Sometimes a user interaction can span a longer period than you are currently looking at, ensure that you are considering the correct timeframe.  Flow Analytics Dimensions Analytic events are separated into two dimensions: Thread and Brain events.  Thread events The following events are tagged with the thread events dimension when there is an interaction: Event Definition MESSAGE_IN Flow receives a message Note: This can be either from a customer, a moderator, or an agent (use the originator_role to distinguish). MESSAGE_OUT A reply is sent back by the automation LANGUAGE A language is detected (present in the language field) COUNTRY A country is detected (present in the language field) EVENT_OPENING An opening event is triggered (only supported by certain channels) EVENT_BROADCAST A broadcast is triggered PROJECT A new Flow project has been created ORGANISATION A new Flow organisation is created INTERACTION_NEW When a new interaction is created INTERACTION_UPDATED An existing interaction is updated RESOLVED_BY_BOT An interaction is resolved by the automation RESOLVED_BY_AGENT An interaction has been resolved by an agent TAKEOVER A takeover/handover is applied to an existing interaction TAG_ADD A tag is applied to a user TAG_REMOVE A tag is removed from a user USER_NEW A new user is registered Specific for voice: Event Definition VOICE_CALL_DISCONNECT A call is disconnected VOICE_CALL_HANDOVER A handover is applied for a call VOICE_CALL_CONFERENCE_END A call ends VOICE_CALL_AGENT_JOIN An agent joins a call VOICE_CALL_HOLD_ON A call is put on hold  VOICE_CALL_HOLD_OFF A call is put back from hold VOICE_CALL_AGENT_MUTE_ON An agent puts the call on mute VOICE_CALL_AGENT_MUTE_OFF An agent puts the call off mute Fields Field Description __time Date in a UTC format agent_id Flow project ID channel_id Connected channel or source ID channel_name Type of channel country Two-letter identifier of the region For example: us event_name Type of event  For example: MESSAGE_IN, TAKEOVER, USER_NEW, TAG_ADD language Two-letter language code  For example: en originator_role The originator’s role for the event For example: SYSTEM, EXTERNAL, MODERATOR, etc. tag_name Name of the tag that is applied tag_value Value of the tag that is applied thread_id Conversational thread between the bot and the customer resolution Reason of resolution attachment_event_name Event name that is triggered timestamp UNIX timestamp event_value Related Payload  campaign_id Broadcasted campaign care_conversation_id Care Conversation ID interaction_id Unique id for every interaction Brain events The following events are with the brain events dimension when there is an interaction: Event Definition FLOW_TRIGGERED A specific flow is triggered UNKNOWN_TRIGGERED An unknown message is received SENTIMENT AI estimated sentiment Note: You can find the Sentiment value in the Sentiment field. TAG_CREATED Old form of tags for thread params.  Note: You can find usage of it inside of text replies in the Advanced section in the right sidebar. Fields Field Description __time Date in a UTC format agent_id Flow project ID brain_name AI model flowai for single language model or flowaiv2 for multilingual model channel_id Connected channel or source ID channel_name Type of channel event_name Name of the event that is triggered flow_id Flow ID that is triggered  Note: This can change between versions flow_immutable_id Unique Flow ID that is triggered flow_name Name of the Flow that is triggered intent_id Intent ID that is matched  Note: This can change between versions intent_immutable_id Unique intent ID that is matched intent_label Name of the intent that is matched language Two-letter language code query The text utterance step_id Unique step ID that is matched step_name Name of the step that is matched step_type Type of the step that is matched  For example EVENT, INTENT, ANYTHING, NOTHING, etc.  thread_id Conversational thread between the bot and the customer accuracy AI confidence matched with an intent threshold Confidence threshold used for matching the intent timestamp UNIX timestamp

Through Flow Call Deflection you can re-route the calls to different self-service systems or digital channels automatically based on specific customer requests. Call deflection helps to reduce the number of calls and optimize the bandwidth of the agents in contact centres, help desks or other areas of business for critical inbound inquiries. Khoros Flow supports call deflection for different scenarios.  This article explains the different scenarios to deflect calls that are supported by Khoros. You can either use a Pre-call deflection or an In-call deflection based on the scenarios.  Pre-call Deflection Pre-call deflection guides the customers to a messaging channel for inquiries before making a call. There are different ways this can be achieved:  You can offer a digital messaging system at the entry points.  For example, Apple Business Chat supports a feature called Chat Suggest that detects when an iOS user is about to place a call and gives the option to message instead. Google also offers a similar capability that suggests the customers use Google Business Messaging which is tied into the Google search and Maps apps. You can offer different entry points on existing customer touchpoints to engage using messaging. For example, you can provide a Message Us option on the contact web page. You can disable the call system and exclusively offer digital messaging as the communication channel. Pre-requisites To implement the Pre-call deflection you need an established digital messaging channel for customer support. It should be aligned with your business’s channel strategy or customer journey for optimal results. Determine messaging channels and entry points Add messaging options at entry points Supported channels Apple messages (iOS and Mac) Google search (Android) Google Maps (Android + iOS) Website/ app In-call deflection With In-call deflection, you can deflect the customer’s call to messaging channels when they try to place a call. For example: With every inbound call, you can play a message using an Interactive Voice Response ( IVR) with the expected wait time and an alternative communication channel. If a customer chooses the option to engage using messaging, send a message, and disconnect the call.  In-call deflection can be done at any moment during an ongoing call: For every call: The most optimal way to achieve in-call deflection is by sending a message as a deflect option with every new call.  Based on use cases: You can provide deflect messages through the IVR system for different use cases. For example, financial companies can only support customers using phone calls for specific processes. In this situation, the call-deflect option can be offered at a deeper level in the IVR tree. Based on business hours: If the agents are unavailable you can provide an async messaging system as an alternative communication option. This requires the IVR to be configured as per the business hours or agent availability. Based on business rules: Like with business hours you can also decide to provide call deflection options based on different business rules. For example: During the 48 hours time window for every first call.  Depending on the inbound phone number (for different timezones). Depending on the type of customer (for example, premium customers). Khoros Flow is flexible in terms of the use case; when to provide the call deflection option for the customers.  Pre-requisites To implement In-call deflection the following is necessary: Determine messaging channels  Define the use cases to provide deflection Setup and configure an IVR system For configuring the IVR there are different options or scenarios situations:  Connecting to existing (legacy) IVR: There are two distinct ways to provide call deflection with existing IVR setups: If the IVR supports API calls you can use APIs to deflect calls. Learn more about How to deflect calls to SMS. You can also connect Khoros Flow with IVR using the number or SIP trunk call forwarding option. For this setup, you need to configure and connect the Flow IVR with your existing IVR system. Using Khoros Flow Flow supports Smart IVR technology that can be used to design and build an IVR tree with messaging bots. The Flow IVR can be either connected directly to a phone number or by receiving a SIP trunk. Flow leverages Twilio as a hosted SIP trunk solution. You can use the Flow IVR for the following use cases:  To automate the call deflection using the CX insights If your agents have been receiving an increased number of calls on specific topics  To analyze the valuable information and the nature of the calls  Supported channels The following channels can be supported for deflection: SMS WhatsApp Through the SMS link: Facebook Messenger Brand messenger Telegram Apple Business Chat Google Business Messaging Community  

In addition to the Flow built-in translation workflow, Flow offers a new capability to export all textual bot content (what users will see) to be translated and imported. Often the file is sent to a third party for translation. After the translation is completed, the translator sends the translated file back to the company that can be imported. However, importing the file would overwrite or add the translated content. The Flow Translation Export feature allows the users to export the files easily, this file can then be sent to a third party for translation. Once the translation is completed, the file with actual and translated text can be imported to the project.  File Export and Import  Perform the following steps to export a flow file:  In a Flow project.  Click Configuration Click Languages  Click DOWNLOAD to export the file   Select File Type ( Json or csv ) from the drop-down   Click DOWNLOAD from the pop-up menu The file is stored on your device, you can send this file to a third party for translation.  Perform the following steps to import a flow file once the file is translated:  In a Flow project.  Click Configuration Click Languages  Click UPLOAD to import the file   Click UPLOAD from the Import Language pop-up window Select the file from your device  Click Open  Click Yes to import the file. Note: Verbiage is not auto-translated if no corresponding items will not be found in the file. In case the project has multiple Contexts, each Context is displayed in different columns in the file.  Additional Capabilities:  You can export the file along with the Intents and Context associated with the Flow. You can import the file directly. You can store the imported files as backup using the Flow versions.  You can link the imported file with the original language.  Note: You can export a file with one translated language at a time, currently translation for multiple languages simultaneously is not supported. 

As Khoros Flow already supports system entities system.email or system.date ,  Flow Code Action also extends these system entities with location-based entities such as addresses or postal codes for the developers to trigger the address prompt or choose a location during a conversation. Implementing the System Entities Parameter data format Any extracted system entity should comply with the Flow param format. Example of an extracted system.address entity: {   "your_param_name": {     "address": [       {         "value": "1 Infinite Loop, Cupertino, CA 95014, USA",         "type": "system.address",         "match": "1 Infinte loop, USA",         "address": {           "streetnumber": "1",           "street": "Infinite Loop",           "city": "Cupertino",           "statecode": "95014",           "postalcode": "2083",           "area": "Santa Clara County",           "state": "California",           "country": "United States",           "countrycode": "US"         },         "coordinates": {           "lat": 37.3318641,           "lng": -122.0302537         }       }     ]   } }   If the address service matches with (for example, if the name John Dow matches for email, number, date, etc) the data is added as a param. match : The text that was converted value : Formatted address string location : Object with optional metadata  System entity for address The system.address entity verifies the address of the users by matching the user location stored in the system.  Data format Example of the data format for address: {   "params": {     "address": [       {         "value": "1 Infinite Loop, Cupertino, CA 95014, USA",         "type": "system.address",         "match": "1 Infinte loop, USA",         "location": {           "streetNumber": "1",           "street": "Infinite Loop",           "city": "Cupertino",           "postalCode": "95014",           "postalcodeSuffix": "2083",           "area": "Santa Clara County",           "state": "California",           "stateCode": "CA",           "country": "United States",           "countryCode": "US"         },         "coordinates": {           "lat": 37.3318641,           "lng": -122.0302537         }       }     ]   } } Access Addition Parameter The following parameters can be used for matching the address and postal codes with the system: Country: {{myParam[0].address.country}} Postalcode: {{myParam[0].address.postalcode}}