Back to Prompt Library
planning

Initial Agent Design Prompt

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Build an MCP-enabled Proactive Threat Management Agent

Format
Text-first
Lines
1
Sections
1
Linked challenge
Build an MCP-enabled Proactive Threat Management Agent

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Design a Langroid-based agent named 'ThreatHunter' that can continuously monitor simulated security logs. Define its core persona, goals, and initial tools. How will it distinguish between critical alerts and routine events? Outline the initial state machine or core loop.

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.