Uploaded image for project: 'OpenShift Specialist Platform Team'
  1. OpenShift Specialist Platform Team
  2. SPLAT-2083

Develop a bot with determines if stories are refined enough for review

    • shift week! Story refinement bot
    • Future Sustainability
    • 90% To Do, 0% In Progress, 10% Done
    • False
    • Hide

      None

      Show
      None
    • False
    • Not Selected
    • None
    • None
    • None
    • 36

      OCP/Telco Definition of Done
      Epic Template descriptions and documentation.

      <--- Cut-n-Paste the entire contents of this description into your new Epic --->

      Epic Goal

      Develop a bot which helps a team lead with refinement activities such as sizing and story quality. SPLAT is presently approved to perform this analysis.  The current work is published at https://github.com/openshift-splat-team/jira-issue-evaluator

      Why is this important?

      For team leads Ensuring a clean backlog takes time and energy. For team members, it can take time to get feedback on their story quality. For PMs, having some early indication of the size of an effort can help with planning.

      The goal is not perfection, but rather giving earlier indications to stakeholders about the work in the backlog.

      Scenarios

      • Training the bot, presently this is a manual effort of extracting Jira content(description and summary) to a csv file and determining if each story is refined enough or not. As long as a team is refining stories, much of this is going to be determining if the refinement of those stories was good enough and updating the spreadsheet with Y/N.  Likewise, stories should be sized as part of our workflow. If that is the case, the sizing data should already be present.
      • Determine if a story/task is ready for refinement by the team
      • Estimate the size of the story

      Acceptance Criteria

      • Develop automation to ingest issues and train based on a specific set of Jira projects. Training is team or project specific.  Issues should be labeled to enable supervised learning of a project.
      • Define how issues are to be labeled to enable automatic retraining.
      • Develop an agent tool which an LLM can call to determine if an issue is refined or not.
      • Develop an agent tool which an LLM can call to determine the size of an issue.
      • Develop an agent which assesses the state of a given issue.

      Dependencies (internal and external)

      1. ...

      Previous Work (Optional):

      Open questions::

      Done Checklist

      • CI - CI is running, tests are automated and merged.
      • Release Enablement <link to Feature Enablement Presentation>
      • DEV - Upstream code and tests merged: <link to meaningful PR or GitHub Issue>
      • DEV - Upstream documentation merged: <link to meaningful PR or GitHub Issue>
      • DEV - Downstream build attached to advisory: <link to errata>
      • QE - Test plans in Polarion: <link or reference to Polarion>
      • QE - Automated tests merged: <link or reference to automated tests>
      • DOC - Downstream documentation merged: <link to meaningful PR>

              rhn-support-rvanderp Richard Vanderpool
              rhn-support-rvanderp Richard Vanderpool
              None
              None
              None
              None
              Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

                Created:
                Updated: