2 min lesson
Mine the backlog, rank it, then file the tickets
Use the example in "Mine the backlog, rank it, then file the tickets" to explain the main idea in plain words.
Step 1 of 2
Mine the backlog, rank it, then file the ticketsone plan-mode prompt does the triage and the paperwork
The same loop works against your own codebase. Point Cursor's plan mode at the FIXME and TODO comments rotting in a service and let it rank them into a test plan. The docs now label the feature Planning. Plan modeA mode that makes no edits: it researches the codebase and produces an editable plan you review before any code changes. Press Enter for the full definition. searches and retrieves first, then writes a Markdown plan you refine before any code touches the repo, so the ranking is reviewable.
Find all my FIXME and TODO comments in the alerting module. Determine the top five most critical. Create a detailed testing plan to make sure behavior stays consistent, then migrate to the new functionality while making sure nothing else breaks.
Plan modeA mode that makes no edits: it researches the codebase and produces an editable plan you review before any code changes. Press Enter for the full definition. came back with the items already banded P0 to P2, each with a problem statement and a unit-test plan. One read like triage you'd defend: "notification policy reset silently swallows errors, so users think the reset succeeded when it failed." That is severity reasoning on real backlog debt.
Do the plan-mode ranking first, then append a final task that files the work. Through the Atlassian MCPModel Context Protocol. A standard that lets an AI agent pull in context from outside the repo, like Jira tickets or internal docs. Press Enter for the full definition. you can say "based on the to-do comments in the alerting module, create a set of Jira stories," or have it update a Confluence doc off the plan.
If you repeat the process, package it as a skill so the rank-then-file sequence runs the same way every time.
Learn more
Full explanation
Full explanation
"I'd stand up a pipeline: ingest, classify, cluster, rank, brief. Agents handle the labeling and dedup that used to eat my morning. I own the two gates, rank and brief. The agent proposes a repro and a tag; I confirm the repro, keep the severity formula and put my name on the number."
QAn interviewer asks how you'd use agent-assisted tools to prioritize bugs at scale. What's the strongest way to show you understand that, and where do you keep a human in the loop?