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 Future consideration
Created by Guest
Created on Apr 3, 2026

When using forms in Flow, allow users to control whether form input data is inserted into the context

We have confirmed that, as of a certain version, form fields that are used within workflows have come to be included in the LLM’s context.

We understand that making input information within a flow understandable to the LLM can be useful in certain cases, particularly for the purpose of enabling the model to correctly interpret user-provided inputs.

However, we are very surprised and concerned that form input information—which was not previously inserted—has suddenly begun to be included in the context as a result of this update.

In particular, when using a ReACT agent, the LLM is generally expected to produce outputs according to a predefined structure such as:

Thought → Action (or Answer / Collect)

That said, form input information does not adhere to this format. By inserting such information directly into the context, the LLM is placed in a situation where information that does not follow the expected format is mixed in, potentially causing confusion or unintended behavior.

To reiterate, we do not consider the functionality of including form input information in the context itself to be unnecessary. We acknowledge that there are use cases in which this capability can be effective and beneficial.

Nevertheless, for a feature that directly affects LLM behavior and context interpretation in this way, we believe it should be provided in a manner that allows users to explicitly enable or disable it.

In particular, for specification changes that impact the context, we strongly request that such features be released in a state where users can clearly choose whether or not to use them.

We sincerely appreciate your consideration of this matter.

Idea priority Medium