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 agent loop works against your own codebase, not just the inbox. Point Cursor's plan mode at the FIXME and TODO comments rotting in a service and let it produce the ranked test plan you'd otherwise spend a meeting arguing about. 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. runs search-and-retrieval first, then writes a Markdown plan you refine before any code touches the repo - so the ranking is reviewable, not a black box.
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-P2, each carrying a problem statement and a per-item unit-test plan - the kind of line that reads like triage you'd defend: “notification policy reset silently swallows errors, so users think the reset succeeded when it failed.” That is severity reasoning, written for you, 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. Anything you'd do by hand creating a ticket, you can outline to the agent.
If it's a process you repeat, 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 - and let agents do the labeling and dedup that used to eat my morning. But the severity formula and the final call stay mine. The agent proposes a repro and a tag; I confirm the repro and own the number.”
QCursor's JD asks you to “drive automated bug prioritization at scale using agent-assisted tools.” In an interview, what's the strongest way to show you understand that - and where do you keep a human in the loop?