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.

ADD IDEA

All ideas

feature in watsonx Orchestrate that can restrict or block model usage once a predefined token usage limit has been reached.

This feature is needed in the control plane of watsonx Orchestrate to provide centralized governance and usage management capabilities.It enables administrators to set token-based usage limits and automatically control model access when thresholds...
3 months ago in  1 Under review

Enable a parallel text chat stream while using the voice experience, allowing users to see the conversation in real time while interacting via voice

Currently, when voice mode is enabled in watsonx Orchestrate, the user enters a voice-only interaction that behaves like a phone call with the virtual agent. During this experience, the textual conversation is not visible in real time within the c...
4 months ago in  0 Future consideration

Runtime library UI Enhancement

Customers would like to have a category-based agent and tool catalog on Runtime library UI of watsonx Orchestrate, similar to the area highlighted in the red box in the image. They are planning to develop and deploy hundreds of agents within the y...
3 months ago in  1 Under review

NVIDIA B300 GPU support on-premises

We are preparing an on-prem deployment proposal including watsonx.ai, watsonx.orchestrate (WXO), and watsonx.data for a major financial-sector customer. The customer plans to deploy their AI infrastructure on NVIDIA B300 (Blackwell Ultra) GPUs. Ho...
6 months ago in  1 Under review

How to deploy WXO on edge device or an SNO with minimal hardware footprint?

We are using IBM Watsonx Orchestrate (wxo) for many defense and aerospace and industrial clients. For most of them edge solution is super important. However with current design wxo needs openshift and especially an ODF with an enormous hardware fo...
7 months ago in  3 Under review

watsonx Orchestrate, watsonx.ai and watsox Discovery to support vGPU running on virtualized environments on OpenShift (private hybrid cloud)

We need watsonx on prem to support vGPU on virtualized environments on OpenShift (private hybrid cloud). Customer is forced to deploy watsonx components on promise using vGPU. Passthrough is not an option (internal policy for many italian customer...
over 1 year ago in  2 Under review

Support XLSX file for TEXT&DOC EXTRACTION NODES

[Request] I would like to request wxO to support XLSX files for both FILE UPLOAD, and TEXT AND DOCUMENT EXTRACTION NODE. Currently, wxO onlly allow us to upload XLSX files via FILE UPLOAD NODE, however, the content is recognized as binary file as ...
7 months ago in  1 Under review

Security concern with default model with data going outside IBM Cloud DC

Customer doesn't want inference to be done outside IBM Cloud Frankfurt. Orchestrate default model includes GPT-OSS-120B -groq inference (in finland). Customer want the capability to choose default model in Orchestrate to ensure by default select c...
12 days ago in  0 Submitted

add a verbatim pass-through option for native collaborator agents

the ability to add a native WxO collaborator (that is a separate agent doing its thing) to an WxO agent than when returning an answer to show this answer directly to the user instead of passing the answer through the Orchestrator LLM.
22 days ago in  0 Submitted

First-class way to represent externally executed enterprise actions

Enterprise agents often should not execute directly. They should decide, then delegate execution to governed systems like BAW, Decisions, ITSM, ERP, or partner platforms. This could be enabled by supporting an delegated/no-op tool concept which th...
5 months ago in  0 Under review