NEW New customer satisfaction (CSAT) snippet for email templates

• Added a new feature that allows users to easily insert a CSAT (Customer Satisfaction) snippet into email templates using a dedicated button in the email editor.
• This makes it easier to collect customer feedback by embedding a 5-point rating system within emails.

NEW New feature turn on Voice Transcript per Tenant

• This feature allows global administrators to control voice transcription settings at the tenant level.
• When voice transcription is OFF, the "Call transcript" section in the activity history will be completely hidden.
• By default, this feature is OFF for all tenants.

NEW New Call Recording Playback in historical conversation reports

• Users can now play back call recordings directly from historical conversation reports for better post-call analysis.
• If call recording includes the customer side or both sides, playback will be available.
• If only the agent’s side is recorded, playback will not be available.
• If recording is disabled, the playback button will not be shown.

NEW New multi-language support for conversation summaries via API

• Users can now define the language of the conversation summary when making API requests. The API request must specify the desired language for the generated summary.
• The following languages are supported: English Croatian Serbian Slovenian German Turkish French Italian Romanian Hungarian
• If no language is defined, the summary will default to English.

NEW New enhanced filtering and navigation in conversation insights

• Date filtering now aligns with the tenant's time zone instead of the user's local machine time for consistent reporting.
• All dates and times in insights will be displayed in the tenant’s time zone.
• A notification will appear if the user is viewing data in a different time zone, preventing confusion.
• New main category filter (if categorization is enabled) allows insights to be filtered by conversation category.

RESOLVED Fixed an issue where Spanish translations were displayed incorrectly in the Agent UI.

RESOLVED Fixed an issue where the Agent UI allowed agents to send emails to invalid email addresses from Lookup.

RESOLVED Fixed an issue where the Customer Satisfaction bot name was missing in Power BI.

RESOLVED Fixed an issue where supervisors were unable to create or delete chat templates.

RESOLVED Improved the documentation for the Agent Auto-Logout Mechanism to specify that both .log and .har files are required.

RESOLVED Fixed an issue where the email conversational bot failed when responding to emails with multiple questions from the knowledge base.

RESOLVED Improved the documentation for Campaigns and Statuses. It now specifies that campaigns cannot be deleted if there are unfinished records in the queue. Additionally, the Status Definitions section has been updated to include "Cancelled by Agent" and "Postponed".

NEW New outputs for the Redirect and Time-Based Redirect nodes

• Added an option to enable call transfers from a workflow to multiple phone numbers in sequence. If a transfer fails, the NoAnswer output of the node can be used to connect it to another node.

NEW New enhanced Agent Creation: Optional Microsoft search

• Microsoft Search is now optional, allowing users to manually enter agent details without prompts, providing flexibility and an improved user experience.

NEW New advanced configuration for Conversational Bot

• Added two parameters:
• Temperature: Controls how precise or creative the bot’s responses are (0 = predictable, 2 = highly creative).
• Max Output Token Count: Defines the maximum length of a response (100–3000 tokens).

NEW Automatically Returning Chat conversations to queue on Force Logout

• If an agent is disconnected due to network issues while handling a chat, the system will now automatically return the chat to the queue. The chat will be marked with a preferred agent, meaning it will be reassigned to the same agent.

NEW Live Translation now supports a Text-to-Speech (TTS) option for inbound calls

• Live Translation now includes a Text-to-Speech (TTS) option for inbound calls, improving accessibility and communication.

NEW Improved performance for retrieving email messages by thread ID

• Quicker email conversation loading in the Agent UI, improving the overall user.
• Optimized storage structure to enhance query efficiency.

NEW Improved logging for better system insights

• Standardized log levels for better monitoring and troubleshooting.

RESOLVED Fixed an issue where the documentation did not clearly state that Queue treatments for chat are only available for Webchat. The Queue treatments feature is now explicitly documented as being available only for Webchat, preventing confusion.

RESOLVED Fixed an issue where an issue where auto-accepting tasks for agents in campaigns was not working.

RESOLVED Fixed an issue where the channel number was displayed instead of the customer number after a workflow redirect.

RESOLVED Fixed an issue where chaining multiple conversational bots in a workflow caused the second bot to fail.

RESOLVED Fixed an issue where play recording buttons were inactive in historical reports and the tasks menu.

NEW New CSAT insights added

• New pie chart graphs added showing the customer breakdown.
• New graph showing customer score evaluation.

NEW New languages available in the AUI

• Added the Croatian language to the Agent application.
• Added the Serbian language to the Agent application.

NEW New languages added to Live Translation

• Added the French language.
• Added the German language.
• Added the Italian language.

NEW Croatian language support for Chat Translations

• Agents can now select Croatian as their preferred translation language.

NEW Added a new KPI to the Wallboard data feed

• Conversation Waiting KPI per Queue.

NEW Use Workflow Variables in the Switch Node’s Right-Hand Side

• You can now reference workflow variables in the right-hand side of conditions in the Switch Node. This allows you to create more flexible and dynamic workflows by using variables instead of fixed values.

NEW Knowledge Base search integration for Conversational Bots

• KB Selection in Nodes: A KB can now be selected as an option in the node configuration.
• AI-Driven Search: The KB description is now used as a prompt to guide the AI on when and how to use the knowledge base.
• Portal Update: A tooltip has been added in the portal, clarifying that the KB description serves as an AI prompt.

NEW Added the ability to specify workflow variables for OData

• Allows workflow designers to define and use workflow variables for better data capture and filtering in historical conversation reports.

Improvements​

• Webchat Widget: Links now open in a new tab instead of replacing the current page, ensuring a smoother user experience.

RESOLVED Fixed an issue where the RONA timeout setting was impacting "Redirect to phone" node calls and blind transfers from outbound calls.

RESOLVED Fixed an issue where the transcript button was not displayed in the task history for Asterisk tenants, making transcripts unavailable. This fix ensures transcripts are now accessible as expected.

RESOLVED Fixed an issue where the documentation for the chat editor was missing information about the Customer Identifier. This update ensures the docs now include relevant details for better clarity and usage.

RESOLVED Fixed an issue where WhatsApp channels sometimes became unresponsive, preventing customers from receiving replies when initiating conversations. This fix ensures more reliable message delivery through the Buzzeasy WhatsApp channel.

• We’re introducing voice conversational bots to address the limitations of DTMF-based workflows and enable more advanced scenarios, such as answering customer queries using knowledge base searches. The new node, called Conversational Bot, can be added to a voice workflow and includes a welcome message (text) that plays when customers call, along with an instructions field where designers specify the bot’s purpose and style of response. Users can also select a language for speech-to-text processing (English, Spanish, Serbian, Hungarian, or German) and define dynamic outputs for different outcomes, such as transferring a call to a live agent

• We’re introducing email conversational bots as a new node in the email workflow, which allow users to define free-text instructions outlining the bot’s purpose, capabilities, and response style. The node includes an email template selector that uses an existing template to construct email replies, with a new template variable that can dynamically insert the bot’s response. Once the bot sends the email, the workflow proceeds under an Email Sent outcome, and users can create dynamic outputs for scenarios like transferring to an agent if the customer requests human assistance.

• We’re introducing a new Conversational Bot workflow node for chat, which offers an instructions field where you can specify its purpose, response style, and any limitations or rules it must follow. You can also select an existing knowledge base and grant access to various third-party APIs. Additionally, the node provides dynamic outputs, allowing you to define the names and conditions under which each output should be used, giving you greater flexibility and control over the bot’s behavior.

• We’re introducing the ability to configure automatic conversation categorization rules for voice channels through the portal, allowing administrators to assign a single categorization rule to each voice channel. When the conversation ends and the full call transcript becomes available, the system will automatically apply the corresponding tags based on these rules, using LLM to process the transcript.

• We’re introducing conversation rating insights in the portal under a new Insights menu group, accessible separately for voice, chat, and email. Each media-specific menu will display a rating report containing a pie chart that illustrates the distribution of ratings. Users can filter these insights by date range, providing a clear view of customer feedback trends over time.

• Users can now filter historical conversation reports by media type, channel, workflow, date, or conversation length (above or below a specified threshold), making it easier to locate and analyze specific interactions.

• We're introducing the ability to configure automatic conversation tagging rules for chat, which can be set up via an endpoint or directly in the portal. A new menu, Categorization Rules, will be available under Administration > Categorization Rules
• Each rule can be assigned to a specific channel, and once a chat conversation ends, the system will automatically tag the conversation based on the assigned rule using LLM.
• Conversation tags will have two levels: Main Category and Subcategory

• We’re introducing a first customer answer speed field in the OData feed for outbound chat conversations. Additionally, we will calculate and provide the agent's average speed of answer per conversation, the customer's average speed of answer per conversation, and optionally, the bot's average speed of answer per conversation.
• Please note that these properties will only be calculated for chat conversations that occur after this release. For conversations that were completed before the release, these values will be null. This update will help track response times and improve insights into customer-agent interactions.

• We’re introducing the ability to configure automatic conversation tagging rules for email.
• The rules will include a tag name and a description, which provides an English explanation of what the tag means, when it should be used, and examples. Tags will follow a two-level structure: Main Category and Subcategory, with both fields having a limit of 100 characters.
• When an email workflow node is added, it will automatically tag conversations based on the rule, using LLM to analyze the first email sent by the customer.
• The outputs of the node will be either Successful or Uncategorized, and the main category and subcategory applied will be stored as workflow data. This will allow the data to be used in a switch node for routing decisions.

• We’re adding the ability to record the entire voice call from start to finish, working alongside the existing solution that records only the customer-agent side.
• The complete recording will be accessible in historical conversation reports and will later be subject to categorization rules once transcription becomes available, covering the full conversation, including both customer-bot and customer-agent interactions.
• The option to record the whole call or just the agent task is set by a Buzzeasy global administrator per tenant.

• We’re introducing conversation categorization reports in the portal with visual displays. These reports will show the main topic and subtopic.
• The portal structure will be organized under the Insights menu group, where you will find separate menus for Call, Chat, and Email insights. Within each of these menus, there will be a Categorization tab. The default section will display two visual elements: a Category Distribution pie chart and a Subcategory Distribution pie chart. These visual reports will offer a comprehensive and interactive way to analyze conversation categorization data, with options to filter by media type and date range.