Operator-ready prompt for reuse, tuning, and workspace runs.
This item is set up for developers who want to inspect the original language, fork it into Workspace, and adapt the evidence model without losing the source prompt structure.
Implementation handoffs, eval setup, and prompt tuning where you need the original structure intact.
Inspect first, copy once, then fork into Workspace when you want variants, notes, and model settings attached to the same run.
Swap domain facts, examples, and any hard-coded entities for your own context.
Tighten the evidence or verification requirement if this is headed toward production.
Decide which failure mode you want to evaluate first before you branch the prompt.
This prompt already carries implementation detail, tool context, and a final-output instruction. Keep that structure intact when you tune it, or your comparison runs get noisy fast.
Open this prompt inside Workspace when you want a live iteration loop.
Copy for quick reuse, or run it in Workspace to keep prompt variants, model settings, and prompt-history changes in one place.
Structured source with 13 active lines to adapt.
Already linked to a challenge workflow.
Sign in to keep private prompt variations.
Prompt content
Original prompt text with formatting preserved for inspection and clean copy.
Using Google ADK, define a 'Product Strategist' agent, a 'Market Analyst' agent, and a 'Creative Lead' agent. The Strategist should use Gemini 3 Flash, the Analyst Gemini 3 Flash, and the Creative Lead Claude 4 Opus. Assign basic goals and initial tools to each, such as a simulated market data access tool for the Analyst and a text-to-text generation tool for the Creative Lead. Use the following structure to initialize your agents: ```python
from google.generativeai.client import get_default_agent_client
from google.generativeai.types import FunctionDeclaration, Tool
import google.generativeai as genai genai.configure(api_key='YOUR_API_KEY') # Define tools
market_data_tool = FunctionDeclaration( name='get_market_trends', description='Retrieves current market trends for a given product niche.', parameters={'type': 'object', 'properties': {'niche': {'type': 'string'}}}, is_core=True
) creative_gen_tool = FunctionDeclaration( name='generate_marketing_copy', description='Generates marketing text based on product features and tone.', parameters={'type': 'object', 'properties': {'features': {'type': 'array', 'items': {'type': 'string'}}, 'tone': {'type': 'string'}}}, is_core=True
) # Initialize agents
product_strategist = get_default_agent_client( model='models/gemini-3-flash', tools=[Tool(function_declarations=[market_data_tool])], display_name='Product Strategist', instructions='You are responsible for overall product strategy and decision-making.'
) market_analyst = get_default_agent_client( model='models/gemini-3-flash', tools=[Tool(function_declarations=[market_data_tool])], display_name='Market Analyst', instructions='Your role is to research market trends and provide data-driven insights.'
) creative_lead = get_default_agent_client( model='models/claude-4-opus', tools=[Tool(function_declarations=[creative_gen_tool])], display_name='Creative Lead', instructions='You generate compelling marketing copy and creative content.'
)
# ... more agent definitions and interactions ...
```Adaptation plan
Keep the source stable, then branch your edits in a predictable order so the next prompt run is easier to evaluate.
Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.
Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.
Check whether the prompt asks for the right evidence, confidence signal, and escalation path.
Copy once for a pristine source snapshot, then move the prompt into Workspace when you want variants, run history, and side-by-side tuning without losing the original.
Prompt diagnostics
Quick signals for how structured this prompt already is and where adaptation work is likely to happen first.
This prompt already mixes executable detail with instructions, so the safest path is to tune examples and interfaces before you rewrite the overall scaffold.
GenAI Unit Launch Strategy with Google ADK Agents and Claude 4 Opus
This challenge tasks you with developing a multi-agent system using Google's Agent Development Kit (ADK) to strategize and simulate the launch of a new AI-powered product. The system will feature specialist agents leveraging large language models like Gemini 3 Flash for strategic planning and Claude 4 Opus for creative content generation. The agents will collaborate to analyze market trends, define product features, draft marketing copy, and simulate initial user interactions. The goal is to demonstrate how an orchestrated team of AI agents can accelerate early-stage product development and strategic decision-making in a dynamic AI market.
Use the challenge page to recover the original task boundaries before you tune the prompt. That keeps your variants grounded in the same evaluation target instead of drifting into a different problem.