Skip to Main Content
Shape the future of IBM watsonx Orchestrate

Start by searching and reviewing ideas others have posted, and add a comment (private if needed), vote, or subscribe to updates on them if they matter to you.

If you can't find what you are looking for, create a new idea:

  1. stick to one feature enhancement per idea

  2. add as much detail as possible, including use-case, examples & screenshots (put anything confidential in Hidden details field or a private comment)

  3. Explain business impact and timeline of project being affected

[For IBMers] Add customer/project name, details & timeline in Hidden details field or a private comment (only visible to you and the IBM product team).

This all helps to scope and prioritize your idea among many other good ones. Thank you for your feedback!

Specific links you will want to bookmark for future use
Learn more about IBM watsonx Orchestrate - Use this site to find out additional information and details about the product.
Welcome to the IBM Ideas Portal (https://www.ibm.com/ideas) - Use this site to find out additional information and details about the IBM Ideas process and statuses.
IBM Unified Ideas Portal (https://ideas.ibm.com) - Use this site to view all of your ideas, create new ideas for any IBM product, or search for ideas across all of IBM.
ideasibm@us.ibm.com - Use this email to suggest enhancements to the Ideas process or request help from IBM for submitting your Ideas.

Status Under review
Created by Guest
Created on Apr 21, 2025

Expanding agent routing mechanisms

Feature Request: Expanding AI Agent Routing Mechanisms

To enhance the flexibility and intelligence of AI agent orchestration, we propose adding support for multiple routing strategies. These should include semantic routing, rule-based routing for simple conditional flows, keyword-based routing for quick pattern matching, intent classification using lightweight machine learning models, and LLM-driven function calling or tool selection for dynamic, context-aware decisions.

Hybrid routing that combines these methods would offer a robust solution for scaling across diverse user inputs and agent capabilities.

Idea priority High
  • Guest
    May 15, 2025

    One example could be to deterministically select the target agent based on what channel type or channel ID a request is coming from. A simple business rule would be much more efficient and possible to certify test case compliance for as compared to "LLM guessing". Now, with the new agentic chat in Q2 onwards, it is even more important to automate the top level agent selection based on many things, like individual user preference, user role, internal/external/partner etc.

  • Admin
    Laurent Tillette de Clermont-Tonnerre
    Apr 30, 2025

    this is likely rendered obsolete by the new agentic chat coming this Q where agents will be set to collaborate with each other through LLM-planning.

    Can you shoare examples of use-cases where needing one routing vs the other?