Bazaar Market Analyst
Low-cost shopping app in emerging markets, presents a fascinating challenge for market entry strategy. This project requires you to build a sophisticated multi-agent system using CrewAI to analyze the competitive landscape, identify optimal product sourcing, and formulate strategic recommendations. The agents will leverage the advanced reasoning capabilities of Gemini 2.5 Pro, including its 'Deep Think' mode for nuanced analysis. The system will dynamically gather real-time market intelligence using Retrieval Augmented Generation (RAG) from various data sources. Crucially, agents will integrate with external market data APIs through the Model Context Protocol (MCP) to access up-to-date e-commerce trends, demographic data, and competitor pricing. This challenge emphasizes robust agent collaboration, hybrid reasoning (instant vs. deep), and seamless tool integration in a practical business context.
What you are building
The core problem, expected build, and operating context for this challenge.
Build a CrewAI multi-agent system using Gemini 2.5 Pro, RAG, and MCP for in-depth market entry analysis of low cost app.
How work is evaluated
The evaluation module assesses the multi-agent system's capability to deliver accurate, comprehensive, and actionable market intelligence and strategic recommendations for app's market entry. It focuses on the quality of analysis, effective tool integration, and clarity of the generated output.
Challenge datasets
Public datasets, plus the private datasets you have access to.
What you should walk away with
Generate strategic market entry and product sourcing recommendations.
Integrate Gemini 2.5 Pro's Deep Think mode for complex, nuanced reasoning.
Utilize MCP for seamless, standardized tool integration with external APIs.
Implement RAG for dynamic data sourcing and real-time knowledge retrieval.
Design a robust multi-agent architecture using CrewAI for market analysis.
Reference links and supporting material
Sample data for 3 tasks
Challenge setup
The evaluation module assesses the multi-agent system's capability to deliver accurate, comprehensive, and actionable market intelligence and strategic recommendations for Amazon Bazaar's market entry. It focuses on t...
Challenge input
JSON: {"target_market": "string", "product_category": "string"}
Agent execution
No agent tool is listed for this challenge.
Evaluated output
JSON: {"market_overview": "string", "key_trends": ["string"], "market_size_estimate": "string"}
- The agent system runs without errors and produces output for all three tasks.
- The output JSON strictly adheres to the specified format for each task.
- Evidence that agents successfully called simulated MCP-enabled tools for data retrieval (e.g., logging of t...
- AccuracyOfMarketInsights target: 85
- Python execution harness
Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.
View technical recipe
Configured tools
No tool records are attached.
Evaluation contract
- The agent system runs without errors and produces output for all three tasks.
- The output JSON strictly adheres to the specified format for each task.
- Evidence that agents successfully called simulated MCP-enabled tools for data retrieval (e.g., logging of tool calls).
Metrics
- AccuracyOfMarketInsights · Target 85
- CompletenessOfCompetitorAnalysis · Target 80
- FeasibilityOfProductRecommendations · Target 75
- ReasoningDepth · Target 70
Workflow tasks
- Task 1
Input: JSON: {"target_market": "string", "product_category": "string"}
Output: JSON: {"market_overview": "string", "key_trends": ["string"], "market_size_estimate": "string"}
Execution harness: Python
- Task 2
Input: JSON: {"target_market": "string", "product_category": "string"}
Output: JSON: {"competitors": [{"name": "string", "strategy": "string", "strengths": ["string"], "weaknesses": ["string"]}], "opportunities": ["string"], "threats": ["string"]}
Execution harness: Python
- Task 3
Input: JSON: {"target_market": "string", "product_category": "string", "budget_per_item": "number"}
Output: JSON: {"product_segments": [{"segment_name": "string", "recommended_products": ["string"], "sourcing_strategy": "string", "pricing_range": "string"}], "value_proposition": "string"}
Execution harness: Python
Recipe freeze marker
No recipe freeze time is recorded.