Updates

Important changes

Activate and customize managed automations

Category: feature
Importance: high
What changed: The new pre-built automations (Enders) for CSAT and Interaction Intensity can now be activated with a single click, and you can create your own editable copy.
Customer benefit: You can start collecting conversation dynamics data immediately, and easily customize the process if the default configuration does not fit your workflow.
Highlights:

• A 'Create Custom Ender' option provides a fully editable copy of the managed automation for you to modify.
• Running both a managed and a custom Ender for the same purpose will not cause duplicate processing or costs.
• A warning now appears if analytics dashboards are not receiving data because the required Ender is inactive.

Edit and expand Topic calibration examples

Category: feature
Importance: high
What changed: You can now navigate through, edit, and add to a Topic's set of reviewed example conversations at any time.
Customer benefit: This allows you to refine a Topic's accuracy over time by correcting mislabeled examples or adding new ones, without having to start the review process from scratch.
Highlights:

• Use 'Previous' and 'Next' to move through all reviewed samples and change their labels or notes.
• You can add more matching or non-matching conversations even after the initial review is complete.
• Changes are saved instantly, but accuracy is only re-evaluated when you explicitly finish the review.

Introducing in-app product updates

Category: feature
Importance: high
What changed: A 'What's New' popup now shows you the latest product updates directly within the Ender Turing platform.
Customer benefit: You can learn about new features and improvements that affect your work as soon as they are released, without leaving the application.
Highlights:

• The popup appears automatically after a release and can be reopened anytime from the Help menu.
• Updates are available in all supported languages.
• You can follow 'Learn more' links for details or jump to the full public changelog.

Faster chart drill-downs for common groupings

Category: improvement
Importance: medium
What changed: Clicking a chart segment to view its underlying conversations is now significantly faster for data grouped by agent, team, queue, or CRM status.
Customer benefit: You can explore high-volume data sets and get to the specific conversations you need for review or analysis with much less waiting.
Highlights:

• Drill-downs for these groupings can be several times faster, especially on large data sets.
• Large drill-downs by agent, team, or queue are no longer constrained by internal result size limits.
• All other groupings, such as by Tag or Topic, continue to work as they did before.

Correct topic counts and reliable chart filters

Category: fix
Importance: medium
What changed: Charts and conversation lists now report topics correctly for conversations with archived topics and will reject unsupported filter combinations instead of returning incorrect results.
Customer benefit: You can trust your topic-based reports are accurate and get immediate feedback if a complex filter is not supported, preventing analysis of misleading data.
Highlights:

• Conversations with both an active and an archived topic no longer appear twice in topic breakdowns.
• Using text search inside an advanced filter group now shows an error message instead of being silently ignored.
• Bulk operations are also protected from running against an incorrectly interpreted filter.

Other changes

Faster and more stable Analytics charts

Category: improvement
Importance: medium
What changed: Analytics charts and their exports now use system resources more efficiently, especially when multiple users are active.
Customer benefit: Your analytics dashboards load faster and the platform remains responsive for all users, even during peak reporting activity.
Highlights:

• Complex dashboards load faster, with database usage for each chart request reduced significantly.
• Chart figures are calculated from a single, consistent point in time, preventing mid-calculation inconsistencies.
• Excel exports of large charts also complete more quickly.

More reliable and secure file uploads

Category: fix
Importance: medium
What changed: The secure file transfer (SFTP) server for uploading call recordings has been updated for improved security and stability.
Customer benefit: This ensures your call recordings are delivered to the platform through a more protected and reliable channel, with fewer connection issues after maintenance.
Highlights:

• The server's identity is now preserved across maintenance, preventing connection warnings in your SFTP client.
• Automated protection now blocks repeated failed connection attempts from suspicious sources.
• Upload activity logs are now retained longer for better traceability of recordings.

Better defaults and clearer labels for workspace settings

Category: improvement
Importance: medium
What changed: New installations now start with common features enabled, settings have clearer labels, and the outdated interactive onboarding guide has been retired.
Customer benefit: Setting up a new workspace is faster and more intuitive, as key features are ready to use and settings are described in plain language.
Highlights:

• New workspaces have multi-team dashboard selection and scorecard choice during review enabled by default.
• Setting labels in the 'Other' page now describe what each option does in everyday terms.
• The OIDC auto-provisioning setting is now managed on the same page as other workspace options.

Stronger protection for SFTP file uploads

Category: fix
Importance: medium
What changed: The SFTP server for uploading recordings now automatically detects and temporarily blocks repeated failed sign-in attempts from a single source.
Customer benefit: Your automated file uploads are better protected against unauthorized access attempts without affecting your legitimate traffic.
Highlights:

• Legitimate uploads continue at full speed, as protective measures only apply to suspicious activity.
• Connection logs now accurately show the origin of each connection for easier auditing and troubleshooting.

Notification emails are always readable

Category: fix
Importance: medium
What changed: Activity notification emails, such as for mentions or new TODOs, now include a plain-text version of their content.
Customer benefit: You can always read the content of notification emails, even if your email client or company security policy blocks HTML formatting.
Highlights:

• Emails that may have previously appeared blank will now show the full notification content.
• Links to conversations or TODO lists remain usable in the plain-text version.

Conversation Dynamics metrics export into separate columns

Category: improvement
Importance: medium
What changed: When exporting conversation reports, CSAT Dynamics and Interaction Intensity Dynamics metrics are now automatically split into individual columns.
Customer benefit: You can immediately sort, filter, and analyze these metrics in your spreadsheet without needing to manually parse or split data from a single cell.
Highlights:

• Each metric, such as entry score and peak intensity, gets its own column.
• This allows for direct use in pivot tables, formulas, and BI tools.

Customer Satisfaction Index (CSI) in conversation exports

Category: improvement
Importance: medium
What changed: Customer Satisfaction Index (CSI) scores received from your telephony system are now included as a dedicated column in conversation report exports.
Customer benefit: You can analyze and correlate customer-reported satisfaction scores alongside all other Ender Turing metrics in a single spreadsheet.
Highlights:

• The CSI column appears automatically in exports if your integration provides this data.
• Numeric values like CSI and scores are exported as numbers, ready for use in formulas.
• Long identifiers in other columns are preserved and no longer get reformatted by spreadsheets.

LLM cost and token reporting is always available

Category: improvement
Importance: medium
What changed: The reports for LLM cost tracking and provider token usage are now permanently enabled for all authorized users.
Customer benefit: Users with the correct permissions can always access AI usage and spend data without needing an administrator to enable it first.
Highlights:

• This change simplifies system configuration by removing two settings toggles.
• Access to cost data remains controlled by your existing role permissions.

Pre-built automations for CSAT and Interaction Intensity

Category: feature
Importance: medium
What changed: Two new, ready-to-use managed automations for CSAT Dynamics and Interaction Intensity Dynamics are now available in the platform.
Customer benefit: You can use professionally maintained automations to track key conversation dynamics without having to build and tune the underlying prompts yourself.
Highlights:

• These automations appear in your Enders list with a clear 'ET Managed' badge.
• You can inspect the full configuration, but they are protected from accidental edits or deletion.
• Their costs are reported separately, helping with budget attribution.

Easier reading in the What's New changelog

Category: improvement
Importance: medium
What changed: In the What's New dialog, release dates now stay pinned to the top of the screen as you scroll through the list of updates.
Customer benefit: You can always see which release an update belongs to, making it easier to follow changes when catching up on multiple releases.
Highlights:

• The pinned date heading automatically updates as you scroll from one release to the next.
• A 'See all updates' link is now also available at the bottom of the list.

A redesigned 'What's New' popup

Category: improvement
Importance: medium
What changed: The What's New popup has been redesigned to show a scannable summary of all product updates from the last 31 days.
Customer benefit: You can quickly catch up on all recent changes in one place, with compact summaries for easy scanning and expandable details for more information.
Highlights:

• The new format groups updates by release date.
• You can expand any item to read its full highlights without leaving the list.
• The popup opens automatically only when there is something new since your last visit.

Improved import for GlobalBilgi recordings

Category: fix
Importance: medium
What changed: Recordings from GlobalBilgi (Sirius) are now correctly processed even when the filename includes seconds in the timestamp.
Customer benefit: All your calls from this source will now import with the correct start time and complete metadata, such as agent and queue information.
Highlights:

• Affected calls will no longer appear as bare recordings with missing details.
• This ensures calls are accurately timestamped and attributed for reporting and review.

Clearer Topic review and accuracy checks

Category: improvement
Importance: medium
What changed: The screen for managing a Topic's review dataset has been streamlined, with clearer progress tracking and all actions in one place.
Customer benefit: It is now easier to understand your progress when reviewing a Topic's example conversations and to check the accuracy of a definition.
Highlights:

• Progress now shows your status across the entire dataset, such as 'Reviewed 41 of 41'.
• You can re-evaluate a definition's accuracy directly from its score without creating a new version.

More control over Topic accuracy checks

Category: improvement
Importance: medium
What changed: When reviewing example conversations for a Topic, accuracy is now recalculated only when you explicitly click the 'Finish review' button.
Customer benefit: You have full control over when to trigger an accuracy check, allowing you to freely label, revise, and add samples before committing.
Highlights:

• Labeling and adding samples now only saves your work without starting any background processing.
• This prevents unintended accuracy calculations while you are still editing the dataset.

Outdated accuracy warnings for Topic definitions

Category: improvement
Importance: medium
What changed: The system now displays a warning icon next to a Topic's accuracy score if it was calculated before the set of reviewed conversations was last changed.
Customer benefit: You can now immediately see if an accuracy score is out of date, ensuring you don't make decisions based on stale information.
Highlights:

• The warning helps you know when it is worthwhile to re-evaluate a Topic's accuracy.
• This makes comparing different versions of a Topic more reliable.

Important changes

Automatic correction of names in call transcripts

Category: feature
Importance: high
What changed: Agent, company, and brand names that are misheard during speech recognition are now automatically corrected in call transcripts.
Customer benefit: This improves the accuracy of Auto QA checks for agent greetings and brand mentions, reducing false negatives.
Highlights:

• Corrections are only applied when a misrecognized word sounds similar to a known name, and it never inserts words that were not said.
• The original, uncorrected text is preserved, and all correction attempts are recorded in the conversation's activity log.
• Auto QA scorecards for greeting compliance are now more reliable, especially for agents with unique or non-standard names.

Explicit control over topic accuracy evaluation

Category: improvement
Importance: medium
What changed: You can now manually trigger accuracy evaluation for topic review datasets by clicking a 'Finish review' button, instead of it running automatically.
Customer benefit: This gives you full control over when to measure topic accuracy, allowing you to review and revise labeled data without triggering unintended calculations.
Highlights:

• Labeling samples now only saves your work, without automatically starting an evaluation.
• The 'Finish review' action re-measures the topic's accuracy and suggests improvements if enough data is available.
• If an evaluation cannot be started, you receive immediate feedback instead of a false confirmation.

Warnings for outdated topic accuracy scores

Category: improvement
Importance: medium
What changed: The platform now displays a warning on topic accuracy scores that were measured before the underlying review dataset was last changed.
Customer benefit: This helps you immediately identify which accuracy scores are outdated, so you can avoid making decisions based on stale data.
Highlights:

• A warning icon and tooltip explain why the score is outdated and how to re-run the evaluation.
• The warning helps ensure fair comparisons between different versions of a topic definition.
• This check is applied retroactively to all existing topics and their accuracy histories.

Faster loading for the Agent Metrics dashboard

Category: fix
Importance: medium
What changed: The Agent Metrics dashboard now loads faster because it no longer calculates CSAT scores for columns that are hidden by default.
Customer benefit: This allows the main agent performance table to load immediately, avoiding long delays on accounts with large call volumes.
Highlights:

• CSAT scores are now calculated on-demand when you show a CSAT column or sort by it.
• The on-demand calculation runs independently and does not freeze the rest of the metrics table.
• Data exports to CSV or XLSX still contain complete CSAT values as before.

View conversations behind category evaluation scores

Category: improvement
Importance: medium
What changed: You can now click on the result counts in a category's evaluation report to see the list of conversations for that metric.
Customer benefit: This allows you to quickly find specific examples of correct or incorrect classifications, helping you understand and improve the category's performance.
Highlights:

• In the drill-down view, you can see the expected label, the AI's result, and its confidence score for each conversation.
• Quickly identify misclassified conversations without having to manually search for them.
• The list of conversations respects access permissions, so users only see conversations they are allowed to view.

Other changes

Improved reliability for Binotel and Aircall integrations

Category: fix
Importance: medium
What changed: Calls from Binotel and Aircall integrations now process correctly, even when they do not include extra metadata.
Customer benefit: This prevents calls from these sources from getting stuck during import, ensuring all recorded conversations are available for analysis and review.
Highlights:

• Previously stuck calls from these integrations will be automatically recovered and processed.
• This fix helps ensure your reports and dashboards reflect complete call volumes.

More reliable import of Fireflies meetings

Category: fix
Importance: medium
What changed: Meetings from the Fireflies integration now sync reliably, even when participant attendance data is incomplete.
Customer benefit: This ensures that all recorded meetings are imported into Ender Turing, preventing gaps in your conversation history.
Highlights:

• This change prevents a single meeting with bad data from halting the entire sync process.
• Meetings that failed to import previously due to this issue will be included in the next sync.

Consistent results for 'not a repeat call' filters

Category: fix
Importance: medium
What changed: Filters for 'not a repeat call' now return consistent conversation counts across the Conversations list, dashboards, and detailed reports.
Customer benefit: This ensures that reporting on first-contact resolution or non-repeat callers is reliable and consistent everywhere in the platform.
Highlights:

• Conversations with no prior call history are now correctly included when filtering for non-repeat callers.
• Automations based on repeat-call conditions now behave consistently with search and reporting logic.

Important changes

New integration with Binotel

Category: feature
Importance: high
What changed: You can now connect your Binotel cloud PBX account directly from the Marketplace to automatically import call recordings into Ender Turing.
Customer benefit: This provides a self-service way to analyze all your Binotel conversations without manual exports or custom scripts.
Highlights:

• Setup is completed by entering your Binotel API key and secret in the Marketplace.
• The integration automatically skips unanswered or zero-duration calls to keep your data clean.
• Recordings with separate audio for each party provide more accurate speaker separation and transcripts.

Silent Fireflies meetings are now imported

Category: fix
Importance: medium
What changed: Meetings from Fireflies that contain no spoken words are now imported as sessions instead of being skipped.
Customer benefit: This ensures your session counts and activity reports accurately reflect all completed meetings recorded by Fireflies.
Highlights:

• Imported silent meetings retain their metadata, such as duration and participants, so they can still be reviewed.
• This change improves the accuracy of meeting coverage reports and activity statistics.
• It provides a more resilient sync by cleanly handling meetings with malformed data from the provider.

Set a local timezone for Fireflies meetings

Category: improvement
Importance: medium
What changed: A new timezone setting is available for the Fireflies integration, allowing new meeting times to be displayed in your local time instead of UTC.
Customer benefit: This removes the need for manual time conversions and aligns session timestamps with your team's actual working hours for more accurate reporting.
Highlights:

• The setting is configured once in the Fireflies integration settings in the Marketplace.
• If no timezone is selected, the integration will continue to use UTC as the default.
• The selected timezone applies only to newly ingested meetings.

Consolidated usage and cost reporting page

Category: improvement
Importance: medium
What changed: Monthly license usage statistics and LLM cost reports are now combined in a single 'Usage' tab within the System settings.
Customer benefit: This allows administrators to review both platform consumption and AI spending in one location, simplifying cost management.
Highlights:

• The new tab is located under Settings > System > Usage.
• LLM cost data is only visible to users with permissions to manage Automation settings.
• The Gen AI Studio prompt list no longer displays cost columns, creating a more focused interface for prompt management.

Paragraph formatting preserved in Gen AI Studio

Category: fix
Importance: medium
What changed: When you paste multi-paragraph text into the Gen AI Studio prompt editor, the original paragraph breaks are now correctly preserved upon saving.
Customer benefit: This allows you to draft and copy complex prompts from other applications without having to manually reformat them after pasting.
Highlights:

• The fix prevents pasted text from collapsing into a single paragraph with visible '\n' characters.
• This applies to the standard editor; Expert mode behavior is unchanged.
• Prompts saved before this fix can be corrected by re-saving them.

Other changes

Funnel filter menu stays open for faster setup

Category: improvement
Importance: medium
What changed: When building a Funnel step, the filter selection menu now remains open after you add a condition, allowing you to add multiple filters at once.
Customer benefit: This reduces clicks and makes it quicker to define precise, multi-condition steps for your funnels.
Highlights:

• You no longer need to reopen the filter menu for each condition you add to a single step.
• This aligns the Funnel builder's user experience with filtering in other areas like Conversations and Charts.

Improved reliability for Fireflies meeting sync

Category: fix
Importance: medium
What changed: The Fireflies integration now automatically re-checks for meetings whose transcripts are published with a delay, ensuring they are successfully imported.
Customer benefit: This prevents meetings with late-processing transcripts from being permanently missed, improving data completeness for your reports and QA.
Highlights:

• You can now also update your Fireflies API credentials from the Marketplace at any time, even on a healthy connection.
• The save button on the credentials form is now disabled until a change is made to prevent accidental updates.

Optional quick filter for Internal calls

Category: improvement
Importance: medium
What changed: The 'Internal' (agent-to-agent) call direction button can now be hidden from the dashboard's quick filter, which now shows only 'In' and 'Out' by default.
Customer benefit: This simplifies the interface for teams that do not handle internal calls, while still allowing others to enable the filter as needed.
Highlights:

• The setting is controlled per-user via the quick-filter customization panel.
• The direction filter now supports selecting multiple values at once, such as 'In' and 'Out' together.
• Internal calls can always be filtered from the main filter panel, regardless of this setting.