V 3.6

V 3.6

Release date: 12-05-2025

Key Highlights

Platform Enhancements

  1. Metrics:

    1. Widget in the dashboard has been changed

    2. More elements are measured now like (Output guardrails time, RAG filter time, LLM section time, etc.)

    3. LLM metrics are move to a separate LLM Statisics tab

  2. It's now possible to automatically switch language in the platform with LLM’s or without.

    1. Ie. if you speak to a bot in in Italian, the language get's detected and switches the default language

    2. You can switch the language via the API / Websocket

  3. LLM is now an integrated service in the platform, improving the latency

  4. The test widget in the platform has been improved:

    1. New UI

    2. Can test Text To Speech engines

    3. Switch which channel you want to test (production, test or BCR)
  1. New settings TTS on language (better voice selection). You can now select you preferred dialect per language.

  2. Improve UX for inviting users

  3. You can create bots without NLU engine (LLM only)

  4. Split of Text and Voice via API / Websocket 

  5. Setence splitting

  6. Improved handling of Websocket, Directline and Rest API

  7. Improved password requirements

  8. Improved conversational logs

  9. Additional voices added for ElevenLabs

  10. Async guardrails

Bug Fixes

  • Issues on multi-language not correct
  • Fix on websocket sometimes not responding


UX Improvements

  • Various small visual improvements