Genesys Cloud - Main

 View Only

Sign Up

  • 1.  AI with Architect

    Posted 20 days ago

    Hello,

    Has anyone integrated Architect with AI services (such as OpenAI or other LLMs) through Data Actions?

    I'm curious about:

    • Practical use cases
    • Response times
    • Security considerations
    • Customer experience improvements

    I'd enjoy hearing real-world implementations.


    #ArchitectandDesign

    ------------------------------
    Fausto Brito
    ------------------------------


  • 2.  RE: AI with Architect

    Posted 14 days ago

    Following! 



    ------------------------------
    Lucas Santana
    Pre-Sales Consultant at Solve4ME
    ------------------------------



  • 3.  RE: AI with Architect

    Posted 14 days ago
    Edited by Bogdan Simaciu 14 days ago

    In my view this is too complicated and you can achieve only linear flows. You would also not be able to achieve a real conversational level.

    Market trend and also Genesys current (development) focus is LAM with A2A and MCP support. When A2A (3rd party -external) will be available you would be free to utilize external agents and have bi-directional communication between the Genesys VA and any 3rd party agentic AI.



    ------------------------------
    Bogdan Simaciu
    ------------------------------



  • 4.  RE: AI with Architect

    Posted 14 days ago

    Am I correct in thinking you are talking about a single-turn inference using a Data Action,  rather than a multi-turn conversation with an LLM? 

    In the past I have created a multi-turn integration to an in-house custom conversational agent using Genesys's Bot Connector, and performed bespoke classification of emails using a Data Action (backed by an LLM).

    Response Times

    In both instances the response times varied greatly based on the task, model & guardrails. So it would be hard to give a precise answer to this.

    Security considerations

    Without knowing your precise use-case this is hard to say, but here are some of our considerations:

    • Model-based content safety parameters - the model we are using has the ability to tweak the sensitivity of its own guardrails around the response
    • Guardrails -  We use an external system on both inbound and outbound messages to flag attends to manipulate the output etc
    • Online evaluations - These are passive evaluations run against the output, which produce both metrics and LLM-as-a-judge based metrics
    • 'Banning' feature - Multi-turn jailbreaking can be difficult to prevent, so we limit this risk by tracking it across turns/interactions. 

    Customer experience improvements

    This is entirely dependant on your use-case, so it's hard to offer any suggestions - other than frequently reviewing interactions .

    Hopefully that was of some help.



    ------------------------------
    Lucas Woodward
    Winner of Orchestrator of the Year, Developer (2025)

    LinkedIn - https://www.linkedin.com/in/lucas-woodward-the-dev
    Newsletter - https://makingchatbots.com
    ------------------------------