Back to Prompt Library
planning
Agent Design & Safety Protocol
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Build a Constrained Conversational AI for Empathetic Voice Support
Format
Text-first
Lines
1
Sections
1
Linked challenge
Build a Constrained Conversational AI for Empathetic Voice Support
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Design the core Langroid agent architecture, including its memory, persona, and initial state. Define a detailed safety protocol for handling sensitive user inputs related to mental health, outlining keywords, response triggers, and redirection strategies. Detail how DSPy will be used to enforce these safety protocols robustly.
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.