Back to Prompt Library
planning
Initialize Google ADK Agent
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Multimodal Flood Resilience Agent with Google ADK and Llama 3.3 70B
Format
Text-first
Lines
1
Sections
1
Linked challenge
Multimodal Flood Resilience Agent with Google ADK and Llama 3.3 70B
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Using the google-adk, define an agent named 'ResilienceAuditor'. Configure it with a Vertex AI model (Gemini 1.5 Pro) for visual analysis and define a tool that calls Llama 3.3 70B via a Vertex endpoint for technical text extraction. Set the system instruction to focus on West Virginia flood resilience standards.
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.