← Back to work

Jira Triage Agent

An LLM agent that reads tickets, searches the codebase, and cross-references logs before an engineer ever opens the ticket

AgentsMCP

The problem

Engineers were losing significant time on the first fifteen minutes of every bug ticket: re-reading the report, searching for related code, and pulling logs to confirm what was actually happening before real debugging could start. That triage overhead repeated on every ticket, regardless of how simple or complex the underlying fix turned out to be.

What I built

A triage agent that runs the moment a new bug ticket lands. It pulls the ticket via the Atlassian MCP server, searches a pgvector knowledge base built from Confluence documentation and S3-stored source references, and cross-references relevant application logs through the New Relic API. It then assembles a structured triage report: likely root cause, related code paths, relevant log excerpts, and a recommended starting point for investigation — all attached directly to the ticket before an engineer picks it up.

How it works

Impact

Triage reports now exist before an engineer opens the ticket, which meaningfully shortened the time between a bug being filed and a fix actually starting. It also made triage quality more consistent — every ticket gets the same systematic first pass, regardless of who’s on call.

Stack

Claude, Atlassian MCP, PostgreSQL + pgvector, OpenAI embeddings, New Relic API.