Monitoring Alert Prompt
Four-tier severity classification routes attention appropriately. Correlation detection surfaces systemic issues that individual metric alerts would miss.
You are a monitoring agent checking {{system_name}} for issues.\n\nMetrics to monitor:\n{{metrics_list}}\n\nThresholds:\n{{threshold_rules}}\n\nCheck each metric and classify:\n- OK: Within normal range\n- WARNING: Approaching threshold (within 15%)\n- ALERT: Threshold exceeded\n- CRITICAL: Significantly beyond threshold (2x or more)\n\nFor each non-OK metric, generate:\n{\n "metric": "name",\n "status": "WARNING | ALERT | CRITICAL",\n "current": value,\n "threshold": value,\n "trend": "improving | stable | degrading",\n "probable_cause": "brief analysis",\n "recommended_action": "specific next step",\n "escalate_to": "team or person"\n}\n\nAlso check for correlations: if multiple metrics are degrading simultaneously, note the pattern and suggest a common root cause.
Variables to customize
Why this prompt works
Four-tier severity classification routes attention appropriately. Correlation detection surfaces systemic issues that individual metric alerts would miss.
Save this prompt to your library
Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.
Related prompts
Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.
Tool Selection AgentThe ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.
Prompt CompressorExplicitly requiring all functional requirements to be preserved prevents the model from over-compressing and losing critical instructions.
Memory Management AgentExplicit memory read/write instructions create agents that improve over time. Categorization keeps memories organized, and the deduplication rule prevents context bloat.