Back to Prompt Library
planning
Define Colang Safety Policy with NeMo Guardrails
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Implement a Safety Interlock Guardrail Agent using OpenAI Agents SDK and NeMo Guardrails
Format
Text-first
Lines
1
Sections
1
Linked challenge
Implement a Safety Interlock Guardrail Agent using OpenAI Agents SDK and NeMo Guardrails
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Create a Colang rail definition `safety_rules.co` in NVIDIA NeMo Guardrails that defines safety envelopes for process parameters (e.g., max pressure = 350 PSI, max temp = 200°C). Block any user query that attempts to exceed these limits.
Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.
Tune next
Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.
Verify after
Check whether the prompt asks for the right evidence, confidence signal, and escalation path.