Week of Jan 15th 2025
Updates include: Secure forms upgrade to V3, Copilot Rewrite & Summarization
Enhancements
Configure the number of retries for Rewrite
Administrators can configure the number of retries available for Rewrite to the agents in the Management Console. By default, it is set to 3 retries. Admins can configure it from min:1 to max:3.
Updated User Interface (UI) for Prompt Library in Management Console
We have updated the UI for the Prompt library in the Management Console for Copilot Summary and Rewrite. The new interface (Prompt Library v2) is shown below. To learn more about Prompt Library features, please refer here.
Fixes
Improved error messages when Rewrite fails
If the Rewrite action in Agent Workspace fails, now we have more detailed error messages displayed to the agent so that it's clearer and more actionable.
Fixes
Test/Tune configuration for summaries will ignore private messages
The Summarization Test module in the Management Console previously did not exclude private messages that are typically ignored when generating conversation summaries. With this fix, the test module now properly excludes private messages, ensuring brands see accurate summarization results during testing.
Enhancements
Secure Forms Studio, upgrading from V2 to V3
LivePerson is excited to share that we are transitioning to Secure Forms Studio V3, now available as part of the LE → Engage → Secure Forms Studio suite. In February, the previous version of Secure Forms Studio, accessible from LE → Management Console → Secure Forms Studio, will be retired as we move forward to this upgraded version.
For more information on Secure Forms Studio V3, please click here.
Fixes
Conversation List Sorting
In the Conversation List area, the sort function was not working correctly for certain metrics. This issue has been resolved, and the sort function now works as expected for all metrics.
Enhancements
LivePerson is enhancing the Generative Insights output format to deliver more natural and detailed responses. These improvements allow users to better understand insights without needing to review conversation transcripts.
Key updates include the removal of the 10-item list limit and refinements to prompts, resolving several issues such as mismatched headers and list contents, insufficient list items, or repeated/hallucinated entries. These changes ensure more accurate and valuable insights for users.
Change Example:
Question: What are customers complaints?
Pre change:
Post-change:
Update GPT Models
As for today, Generative Insights is running with the following models:
Gpt-35-turbo
- Gpt-35-turbo-16k
- Gpt-4
Azure plans to retire the above models in early February. Following the retirement we are updating the Generative Insights to the following models:
- Update models to GPT-4o-mini (from gpt-35-turbo and gpt-35-turbo-16k).
- Update model to gpt-4o (from gpt-4 in APAC and EMEA). Note: gpt-4o is not yet available in APAC