Story (Required)

This story involves development of a Large Language Model (LLM)-powered autonomous agent that is fine-tuned with the repository's source code, README, documentation, and contribution guidelines. The agent will read incoming GitHub issues along with associated comments, and then autonomously perform the following actions with minimal or no human intervention:

Actions:

1. Categorization: Automatically classify the issue (e.g., bug, feature, question, docs, support) using semantic understanding of the content.

1. Autonomous Resolution:

• • If the LLM has high confidence, respond directly in the issue comment with a possible solution, referencing the code or documentation.

• • Tag the issue creator and request confirmation if the solution resolves their query.

1. Maintainer Escalation:

• • If the LLM's confidence is below a defined threshold, tag a project maintainer to review and take appropriate action.

This system aims to reduce maintainer fatigue, shorten issue resolution time, and improve contributor experience by ensuring faster and more accurate triage of issues.

Background (Required)

Open source repositories often face a large volume of GitHub issues, ranging from bug reports and feature requests to configuration help and usage questions. Efficiently triaging, responding to, and resolving these issues is time-consuming for maintainers and core contributors.

A proof of Concept of this solution was demonstrated during Pipelines 2025 F2F Hackathon.

Out of scope

<Defines what is not included in this story>

Approach (Required)

<Description of the general technical path on how to achieve the goal of the story. Include details like json schema, class definitions>

Dependencies

<Describes what this story depends on. Dependent Stories and EPICs should be linked to the story.>

Acceptance Criteria (Mandatory)

<Describe edge cases to consider when implementing the story and defining tests>

<Provides a required and minimum list of acceptance tests for this story. More is expected as the engineer implements this story>

INVEST Checklist

Dependencies identified

Blockers noted and expected delivery timelines set

Design is implementable

Acceptance criteria agreed upon

Story estimated

Legend

Unknown

Verified

Unsatisfied

Done Checklist

• Code is completed, reviewed, documented and checked in
• Unit and integration test automation have been delivered and running cleanly in continuous integration/staging/canary environment
• Continuous Delivery pipeline(s) is able to proceed with new code included
• Customer facing documentation, API docs etc. are produced/updated, reviewed and published
• Acceptance criteria are met