Week of November 6th
New updates include: Conversation Assist & Report Center Enhancements
Features
Recommendations are more flexible and better quality [launching soon]
In this release, we make two major changes to improve the quality of recommendations and the overall experience for your agents.
Change 1 gives you control over where recommendations are offered
In both knowledge base rules and bot rules, there’s a new setting for specifying where the recommendations should be offered.
There are 3 options:
- in conversations and in On-demand widget
- in conversations only
- in On-demand widget only
See a quick animation of usage of both locations.
Change 2 raises the quality of answer recommendations
In knowledge base rules (only!), there’s a new setting named “enhance user’s query using conversation context.”
This setting applies only to recommendations offered in conversations.
Often the user’s query doesn’t include enough context to retrieve a high-quality answer from a knowledge base. To solve this, you can turn on this setting if you want the system to gather additional conversation context (conversation turns) and use it to rephrase the user’s query before searching the knowledge base.
This setting also does one more thing: When it’s on, recommendations are not offered in response to queries that are only small talk (chitchat). But remember that, as mentioned above, this setting applies only to recommendations offered in conversations. Your agents can continue to use the On-Demand Recommendations widget to search for responses to queries that are only small talk.
Language limitation
Queries that are not in English are not enhanced using the conversation context. The original query is always used to retrieve answers for recommendation.
Call to action
LivePerson regards this new setting as a gamechanger for raising the quality of answer recommendations. So, for optimal performance, we recommend that you turn on this new setting in the rule’s add-on.
That said, if your solution is not in English, it doesn’t make sense to turn on the new setting because queries that aren’t in English are never enhanced.
However, some brands support multi-lingual queries, such as English and Spanish queries against English knowledge bases. In such a case, go ahead and turn on the setting, so you can take advantage of query enhancement in cases where the query is in English.
Features
LivePerson have enhanced the Report Center to align more closely with our brand needs and to elevate the customer experience within the LivePerson analytics ecosystem. Our goal is to make the Report Center the go-to tool for our brands, offering seamless access to real-time data and insights. We aim to empower more brands to leverage these analytics for smarter, faster decision-making.
New features
1. Public and Private dashboards: Brands will have increased control over report center usage by agent managers. Newly created dashboards will be marked private (Owner/Creator view only) and can be shared with View Only access to all agent managers. A second phase by February-2025 will have enhancements that lets certain Agent Managers with an enabled permission (RC: Share private to public dashboard) access share report center dashboard functionality (Both View Only and Edit). A video can be found in our report center user guide here.
2. Auto save of your filters and filter values for each RC dashboard. Auto-saved filters enhance the ability of brand users to toggle between dashboards and perform effective analysis. Saved filters will be unique for each user and dashboard.
3. Bot Analytics: New metrics for bot performance have been released and you can find more information on the metrics here.
4. Copilot Assist: A new template with additional metrics for reporting is released. You can find details on metrics and definitions here.
5. Copilot Rewrite: A rewrite template and metrics release was completed in our September release. More details about rewrite metrics can be found here.
Enhancements and bug fixes
1. UI fix for Data Transporter and Report Center integration.
2. NPS/CSAT: Transcript viewer update of NPS or CSAT value as per customer survey response. Skipped response added to the transcript viewer.
3. NPS: New NPS category added. Detractors for conversation NPS raw values (0 - 6), Neutrals for conversation NPS raw values (7-8), Promoters for conversation NPS raw values (9-10)
4. Export: All key metrics (e.g., copilot assist, bot analytics, rewrite, customer satisfaction) are now included in the export file when downloading data from the conversation list location.
5. Keyword Search: We've enhanced the text search functionality in the Report Center to deliver faster, more efficient results by limiting response to 1000 conversations.
6. Charts: Sparkline, pie, and table charts have all duration format changed to show in the hh:mm:ss format instead of decimal.
7. Transcript Viewer: Conversation Start-time, End-time, Status and Device added to conversation details of Transcript Viewer. The order of the details have been changed to support brand requests.
8. Bar Chart: In Advanced Option in the Edit pane, you can use Hour of Day and Day of week time grouping. The legends will be correctly sorted for Hour of Day and Day of Week time dimensions.
For more information, please see the Report Center User guide.
Fixes
Core widgets are created when a brand user navigate to night vision.
Current issue
- Due to bug in the code, all core widgets are created with an order of 1, rather than a consecutive sequence from 1 to 8.
Solution
- The fix will run a DB script to re-order all the widgets
- Set the order of core widgets incrementally from 1 to 8 for each brand/site.
- This issue has now been resolved