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 Sep 23, 2025

Newer Model Support in Assistant Builder Features

Per the official documentation only four models can be used for the watsonx Orchestrate Assistant Builder features (e.g., Conversational Search Answer Generation, Conversational Search Query Rewrite, Conversational Skills, and Custom Action Information Gathering).

Of the four models, only one has not yet been deprecated by watsonx Orchestrate.

The remaining model, llama-3-2-90b-vision-instruct, is more than one year old. Many clients, including Verizon, have long since moved on to llama 3.3 series models (9+ months old) and llama 4 series models (5+ months old), and newer models will continue to be released. Therefore, this Idea request is for select newer models to be supported for Assistant Builder features going forward. This need is particularly important (and urgent) for clients who were early watsonx Assistant adopters, built a large number of Assistants, and then migrated (at IBM's instruction) from watsonx Assistant to watsonx Orchestrate, as they need to continue to use their existing Assistants, in on-premises software deployments of watsonx Orchestrate, with newer models going forward (until the Assistants are eventually transitioned to Agents down the road).

Given that obviously not all models will be suitable for the Assistant Builder features, no specific model's support is requested. Restrictions on which newer models will be supported are reasonable and expected. This Idea is requesting that some newer models be supported in general, both immediately and in the ongoing future, and that IBM publish a list of these models for clients to pick from to continue to leverage Assistant Builder features on newer models.

N.B., As seen in the attached screenshot, we are aware that there may be additional models that could work for these features currently that are not in the official documentation. However, only one additional model in this list, llama-3-3-70b-instruct, which is 9+ months old, is not already on the deprecated list, so the situation remains the same. And, as time goes on, the issue will become more severe as newer and yet newer models are released. A long-term solution is requested.

Idea priority Urgent
  • Guest
    Sep 23, 2025

    If it is necessary for Verizon to "nominate" a "this one first" model to add support for, so long that it's clear that that isn't the whole of the Idea and that a comprehensive, non-model-specific, long-term-solution is required, the first model to add--if deemend suitable for these features by the watsonx Orchestrate QA team-- would be OpenAI/gpt-oss-120b.