Skip to Main Content
IBM Sterling


This portal is to open public enhancement requests for IBM Sterling products and services. To view all of your ideas submitted to IBM, create and manage groups of Ideas, or create an idea explicitly set to be either visible by all (public) or visible only to you and IBM (private), use the IBM Unified Ideas Portal (https://ideas.ibm.com).


Shape the future of IBM!

We invite you to shape the future of IBM, including product roadmaps, by submitting ideas that matter to you the most. Here's how it works:

Search existing ideas

Start by searching and reviewing ideas and requests to enhance a product or service. Take a look at ideas others have posted, and add a comment, vote, or subscribe to updates on them if they matter to you. If you can't find what you are looking for,

Post your ideas
  1. Post an idea.

  2. Get feedback from the IBM team and other customers to refine your idea.

  3. Follow the idea through the IBM Ideas process.


Specific links you will want to bookmark for future use

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 May 13, 2026

AI Chatbot should provide Natural Language Input and Contextual Prompting for all relevant actions

1. AI chatbot should provide natural language input and contextual prompting. (Please see the screenshot attached for examples)

2. AI chatbot should provide contextual hint on relevant screens:

When a CSR navigates to a specific action screen (e.g. Issue Appeasement, Issue Reship), the chatbot shall display a contextual example sentence showing how the CSR can complete that entire action in a single typed input. The hint shall only appear on screens where natural language input is applicable and shall not appear on the home screen 

3. Single-sentence natural language parsing:

When a CSR types a free-text request into the chat input bar (e.g. "Issue $25 appeasement for shipping delay on order CUP1939201 as merch card"), the chatbot shall parse the input and automatically extract the relevant fields — including order number, dollar amount, reason code, appeasement type, and any notes — without requiring the CSR to navigate through multiple screens. The chatbot shall support common variations in phrasing (e.g. with or without the word "appeasement", abbreviated order references, different dollar formats) and route the request to the correct workflow

4. Inline prompting for missing required fields:

When a CSR submits a natural language request that is missing one or more required fields (e.g. order number, amount, or reason code), the chatbot shall display a pre-filled confirmation card showing all successfully parsed fields alongside inline input controls for only the missing fields. The CSR shall be able to complete the missing fields inline and confirm without restarting the flow. Required fields shall be visually highlighted in red; the card shall not allow submission until all required fields are filled.

5. Prompting for optional fields before confirmation:

When all required fields are successfully parsed but an optional field is absent — specifically the case note — the chatbot shall surface an amber-highlighted note input field on the confirmation card with a guiding placeholder (e.g. "e.g. Customer waited 2 weeks for order — compensating for inconvenience"). The CSR shall be able to add the note inline before confirming. If the CSR proceeds without a note, the action shall still complete. The note, if provided, shall be included in the auto-drafted case note appended to the transaction record