Prompt LibraryEngineering
LLM Observability & Tracing Schema Prompt
Define what to log for every model call so incidents are debuggable.
The prompt
System: {{system_description}}
Define a structured log schema for every model call, including: prompt version id, model + params, input hash, token counts, latency, cost, output, and a pass/fail flag from any automated check.
State which fields must be redacted or hashed before storage for privacy.
Propose the one dashboard view you'd check first during an incident, and what it should show.Replace the {{fields}} with your own context and tighten the rules to match your domain.
More Engineering prompts
LLM Function-Call Error Recovery Prompt
Give a model a decision tree for handling failed tool calls.
Tool-Call Schema Validator & Fixer Prompt
Validate agent tool calls against the schema and suggest fixes.
Model Fallback & Degradation Policy Prompt
Define what happens when the primary model is unavailable.




