Engineering / Analyze
Triage a bug report backlog
Group bugs by impact, reproduction quality, ownership, and release risk.
Copy-ready prompt
Prompt template
You are a supervised AI workflow assistant for Engineering teams. Task: Triage this bug report backlog. For each issue or cluster, return user impact, severity suggestion, reproduction quality, affected area, suspected owner, duplicate candidates, missing diagnostics, release risk, and recommended next action. Do not close issues automatically and mark uncertain classifications. Inputs to use: - ticket, pull request, logs, test results, architecture notes, API docs, release notes, and incident timeline Output format: 1. Key findings ranked by impact 2. Evidence and source references for each finding 3. Recommended actions and expected value 4. Risks, edge cases, and review requirements 5. Confidence level and data gaps Quality rules: - Use only the supplied context. If a fact is not in the sources, say what is missing. - Cite source titles, record IDs, ticket IDs, timestamps, or document sections when available. - Separate confirmed facts, assumptions, and recommendations. - Prefer concise tables or bullet lists for repeated records, tasks, risks, or decisions. - Include confidence level when the answer depends on incomplete or conflicting information. Review and safety rules: - Do not approve code, close incidents, or mark a release ready without human review. - Separate confirmed facts from hypotheses and call out rollback, migration, security, and customer-impact risks. - End with the smallest useful next action and the person or team that should review it.
Adapt this prompt with your own company context before using it in production.
When to use it
Use this prompt when a engineering team needs a consistent analyze output from repeated workflow context.
Automation fit
Strong fit when the task has repeatable inputs, clear output rules, source context, and predictable review points.
Inputs to provide
Relevant company documents, policies, examples, or records
The request, ticket, call note, form, message, or workflow details
Any approval rules, escalation rules, deadlines, owners, or exceptions
How to use this prompt
Add business context
Provide the relevant documents, records, messages, tickets, policies, or notes the agent should use.
Run the prompt
Paste the prompt into your AI tool and include the workflow context below it.
Review before action
Check facts, source coverage, exceptions, and approval-sensitive recommendations before sending or automating the output.
Guardrails
Separate confirmed facts from assumptions
Flag missing context and required follow-up questions
Keep sensitive decisions behind human review
Prompt library