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

    Securely passing context from my web application to Agent

    Watsonx Orchestrate (wxO) Agentic currently has a single select feature, however, the usability of the selection list diminishes as the list grows in length. Some customers are dealing with lists that are hundreds or thousands of items long, so a ...
    9 months ago in  0 Not under consideration

    VSAM insight AI agent on IBM Z

    Client expressed interest in a VSAM agent (similar to Db2 Agent that is in-plan) for watsonx assistant for Z. Client indicated that VSAM databases on IBM Z holds critical business data, yet extracting actionable insights from them remains a challe...
    9 months ago in  0 Under review

    Human readable reasoning trace in the chat

    Reasoning trace helps the end-user discover the thinking steps and agent took to answer a prompt. But, there are downsides to the current implementation: End user is shown a technical JSON file that's low on readability The reasoning trace is ...
    9 months ago in  0 Future consideration

    Disable reasoning trace for agents from the Agent Builder

    Some customers don't want end users to see the reasoning trace, as they don't want to show things like the tools called, or what is happening under the covers to get the response back to the user Note that the trace can already be disabled through...
    9 months ago in  0 Future consideration

    Allow change version of automation services

    Currently we can specify version of automation service such as BAW workflow only when we add skills. if we release a newer version of automation service, we have to re-define skill again. it is convenient if we can update version after initial dep...
    about 3 years ago in  3 Not under consideration

    Standardize Teams integration behaviour

    The behaviour of Watsonx Assistant differs from Web to the Teams integration, while we would expect it to have the same behaviour (i.e. replicate what we have during preview). The support case (CS4233476) linked show the issue details, which is su...
    over 1 year ago in  0 Under review

    Ability to edit the knowledge generation configuration in the UI

    I have found that the formatting of agent responses can only be achieved effectively through the generation configuration knowledge settings in the ADK, rather than through the behavioural prompts or guidelines. This means live demos are always go...
    9 months ago in  0 Needs more information

    Add Teams loading icon when agent is "thinking" for Microsoft Teams

    In Microsoft Teams there is no teams loading icon when agent is "thinking", when using the built in channel deployment feature. This would be helpful to our customers in order to get some sort of status when it comes to the thinking phase during a...
    10 months ago in  0 Under review

    Allow the results of AI-guided actions to be stored in a session variable

    To enable more complex use of AI-guided actions, it would be interesting to allow the capture of its results in a session variable. Additionally, a final step could involve redirecting to a custom-built action for further validations/steps.
    over 1 year ago in  1 Not under consideration

    Request to add agents export option in ADK

    Using ADK 1.15, exporting an agent includes every single connection in the service instance which is time-consuming and not useful. We request to add an export option in "orchestrate agents export" command to selectively export connections based o...
    10 months ago in  1 Functionality already exists

    By clicking the "Post Comment" or "Add Idea" button, you are agreeing to the IBM Ideas Portal Terms of Use.
    Do not include IBM confidential, company confidential, or personal information in any field.
    Having problems accessing this portal? Describe the problems in an email to ideasibm@us.ibm.com.