Skip to Main Content
IBM Data Platform Ideas Portal for Customers


This portal is to open public enhancement requests against products and services offered by the IBM Data Platform organization. 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

Post ideas and requests to enhance a product or service. Take a look at ideas others have posted and upvote them if they matter to you,

  1. Post an idea

  2. Upvote ideas that matter most to you

  3. Get feedback from the IBM team to refine your idea


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.

IBM Employees should enter Ideas at https://ideas.ibm.com



ADD A NEW IDEA

Clear

watsonx Code Assistant (general)

Offer an opt‑in premium “Robert mode” that uses higher‑capability model combinations at increased Bobcoin cost.

Enterprise customers are willing to pay materially more for higher reasoning depth, reliability, and autonomy for complex, multi‑repo work, and a premium tier gives teams and consultancies access to stronger model mixes while maintaining cost tran...

Provide a native mode to run Bob as an HTTP server exposing RESTful APIs.

An API‑first deployment allows Bob to be embedded into portals, internal tools, and automated systems, benefiting platform teams and partners orchestrating agent workflows at scale; this should include authenticated REST endpoints for job submissi...

Add hooks support to let customers execute custom logic at defined points in Bob’s lifecycle (pre‑run, post‑run, tool invocation, failure events).

Hooks enable enterprise integration for logging, policy enforcement, approvals, and observability, benefiting platform, DevOps, and security teams embedding Bob into existing pipelines; Bob should expose configurable pre‑run, post‑run, tool‑call, ...

Introduce skills.md support so Bob can load persistent, user‑defined skills and behaviors from the repository.

Skills files allow teams to codify repeatable workflows, conventions, and agent behaviors that improve consistency and productivity across large codebases, benefiting enterprise engineering teams and consultancies; Bob should automatically load sk...

Enable Bob to perform live web searches as a first‑class agent capability.

Without live web search, Bob cannot reliably assist with modern engineering workflows involving fast‑changing libraries, APIs, vulnerabilities, or documentation, limiting usefulness for developers, consultants, and platform teams; Bob should expos...

Add a BobShell configuration option to explicitly disable built‑in tools (e.g., read_file, write_file) at runtime, similar to --disabled-tools flags offered by other agentic coding assistants.

Enterprise customers need deterministic and policy‑compliant agent behavior, and the ability to disable specific built‑in tools allows security, platform, and compliance teams to constrain Bob’s capabilities in regulated, air‑gapped, or controlled...

Getting Server error '500 Internal Server Error'

when user has given prompt, getting Getting Server error '500 Internal Server Error' response: Failed to get a valid response from LLM API: 500: Unable to process LLM request: Server error '500 Internal Server Error' for url ' https://private.us-s...

incorrect conversion from python2.7 to python3.x for the dictionary dict.has_key()

when user has given prompt to convert dict.has_key() from python2.7 to python3.10 Watsonx returned incorrect response as it converted dict.has_key() to get() method correct way is, dict.has_key() should replace with ".in" keyword for dictionary di...

Enhancing Patch Review Efficiency through WCA Model Integration

Objective: Introduce a review capability within WCA that enables developers to assess code patches with contextual clarity, leveraging model-driven insights to improve traceability, understanding, and decision-making. Rationale: Traditional patch ...

Allow user to specify GPU node where LLM gets deployed during installation

Currently there is no way to determine what GPU or what node the LLM uses or gets deployed to. We need a mechanism by which we can specify the GPU node where the LLM gets deployed to. Since WCA is using the SYOM framework to serve the ibm-granite-...