Back to Prompt Library
planning

Google ADK Project Initialization and Agent Roles

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

Linked challenge: Cyber Threat Intelligence Agent with Google ADK and Qwen 3

Format
Code-aware
Lines
3
Sections
1
Linked challenge
Cyber Threat Intelligence Agent with Google ADK and Qwen 3

Prompt source

Original prompt text with formatting preserved for inspection.

3 lines
1 sections
No variables
1 code block
Set up a new Google ADK project in Vertex AI. Define an 'Intelligence Analyst' agent and a 'Tool Scout' agent. The 'Intelligence Analyst' will interpret policy and synthesize reports, while the 'Tool Scout' will focus on researching specific technologies. Use Qwen 3 as the primary model for both agents. Provide Python code for initial ADK agent definition. ```python
from google.generativeai.agents import Agent, # Assuming Vertex AI client setup is handled externally def create_intelligence_analyst_agent(): return Agent.from_function( name="IntelligenceAnalyst", description="Interprets cybersecurity policies and synthesizes intelligence reports.", model="qwen3", # Or appropriate model ID for Qwen 3 in Vertex AI # ... add tools later ) def create_tool_scout_agent(): return Agent.from_function( name="ToolScout", description="Researches and identifies specific cybersecurity tools and technologies.", model="qwen3", # ... add tools later ) # You would then orchestrate these agents within a larger ADK flow.
```

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.