The October 16th release for Now Assist in Virtual Agent brings changes that will affect customers who upgrade to Yokohama Patch 8 or Zurich Patch 2.

• If customers do not upgrade to the latest patches, there are no changes.

• If a customer upgrades to YP8/ZP2 and the latest corresponding plugins for Now Assist in Virtual Agent (v12.x) and GAIC (v11.2), and if the customer has the “AI Agents” skill checked for their assistant setup, you will expect the following changes as part of “fully agentic Virtual Agent":

  • The default LLM model is switching to GPT-4.1. Customers who use NowLLM will switch to using GPT-OSS.
  • Multi-intent is supported and will appear in responses
  • AI Agents are prioritized in Virtual Agent responses by default, but this is configurable via a system property (see KB below).
  • Improved performance and latency - see the stats and video below!
    
    • ~20-41% faster synthesized response speed with 3rd party models
      
    • ~40-52% faster synthesized response speed with NowLLM
      
    • ~27% reduction in E2E run time for OOB agentic workflows and AI Agents
      
    • More improvements expected in Q4 release and beyond [Safe Harbor]
  • UI updates to in-chat processing messages

• Customers who enable fully agentic mode in VA will not be able to turn it back off. If you do not wish to automatically uptake these changes when upgrading, please uncheck the “AI agents” skill in assistant setup before upgrading (via Assistant > Now Assist skills).

The full KB for these changes can be found here (for customers): KB2548818.

Fully agentic Now Assist in Virtual Agent - speed comparison video

Screenshot of multi-intent in action