[modichika]

Summary

This KEP proposes the implementation of an agentic kfp-generator skill within the kubeflow-mcp-server. This tool allows AI agents to translate natural language user prompts into functional Kubeflow Pipeline (KFP) v2 Python code.
It adds a kubeflow pipelines skills where an agent takes a prompt from a user(developer, data scientist, etc..), writes the Python code, tests the compilation, catches any errors, and feeds them back into itself until it successfully generates a valid pipeline file.
it introduces an agentic skill, that will help users to get a verified, evaluated pipeline(YAML files) with natural language.

It is Co-authored-by: @droctothorpe

Motivations

Why this KEP is needed?

• writing kubeflow pipelines python file or YAML file is notoriously difficult, and data scientists often miss the syntax needed to write the pipeline files like YAML.

• an agentic AI skill that will automate this process, will come in handy and useful removing the friction of writing bolierplate codes.

What we built?

• Built the Self-Correction Loop: Set up the feedback mechanism (Prompt → Code → Catch Error → Fix) so it runs non-interactively without needing human input.

• Added Demo Prompts: Tested the agent against the specific scenarios we wanted for a solid demo, including the Iris classifier and MNIST datasets, churn_prediction, image_anamoly_detection, time_series_forecasting.

Details

• design : module structure, tables
• mitigations, and the testing plan , is in the KEP doc.

Status

Open for review from maintainers before implementation.

Related Issue

Fixes kubeflow/pipelines#13423

Checklist

• I have read the CONTRIBUTING guide
• Tests pass locally (make test-python)
• Linting passes (make verify)
• Documentation updated (if applicable)
• My commits are signed off (git commit -s)

cc: @jaiakash , @abhijeet-dhumal , @andreyvelich

[google-oss-prow]

[APPROVALNOTIFIER] This PR is NOT APPROVED

This pull-request has been approved by:
Once this PR has been reviewed and has the lgtm label, please assign kramaranya for approval. For more information see the Kubernetes Code Review Process.

The full list of commands accepted by this bot can be found here.

Details

Needs approval from an approver in each of these files:

• OWNERS

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

[github-actions]

🎉 Welcome to the Kubeflow MCP Server! 🎉

Thanks for opening your first PR! We're happy to have you as part of our community 🚀

Here's what happens next:

• If you haven't already, please check out our Contributing Guide for repo-specific guidelines and the Kubeflow Contributor Guide for general community standards
• Our team will review your PR soon! cc @kubeflow/kubeflow-sdk-team

Join the community:

• Slack: Join our #kubeflow-ml-experience Slack channel
• Meetings: Attend the Kubeflow SDK and ML Experience bi-weekly meetings

Feel free to ask questions in the comments if you need any help or clarification!
Thanks again for contributing to Kubeflow! 🙏

[Copilot]

Pull request overview

Proposes a kfp-generator skill for generating and validating KFP v2 pipelines through the Kubeflow MCP server.

Changes:

• Defines generation, compilation, and correction workflows.
• Proposes module architecture, validation tests, and governance.
• Documents risks, mitigations, and future caching.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[modichika]

Closing this PR for now, reference for future works once PipelineClients gets added in kubeflow/sdk here's the ongoing pr:
kubeflow/sdk#591