Predictive Analytics Agents for Strategic Insights
This challenge tasks you with building an advanced agentic AI system for e-commerce financial analysis and strategic recommendation. Using AutoGen, you will orchestrate a team of specialized agents (e.g., 'Data Analyst', 'Market Strategist', 'Forecasting Expert'). Claude Opus 4.1 will be utilized for its sophisticated reasoning in interpreting complex financial data, identifying subtle market trends, and generating high-quality business narratives. GPT-5 will provide advanced predictive modeling and scenario planning capabilities. A key requirement is robust MCP-enabled tool integration to simulate access to diverse enterprise data sources (e.g., sales databases, marketing spend, supply chain metrics) and external market data APIs. The agents must employ extended thinking with adaptive reasoning budgets to explore various 'what-if' scenarios and provide nuanced, data-driven strategic insights and revenue forecasts, aligning with modern business intelligence demands.
What you are building
The core problem, expected build, and operating context for this challenge.
Orchestrate an AutoGen multi-agent system with Claude Opus 4.1 and GPT-5 for e-commerce predictive analytics and strategic insights, featuring MCP-enabled tool integration and adaptive reasoning.
How work is evaluated
The evaluation will assess the system's accuracy in financial forecasting, the depth and relevance of strategic recommendations, the effective utilization of MCP-enabled tools, and the clarity of agent collaboration and extended thinking.
Challenge datasets
Public datasets, plus the private datasets you have access to.
What you should walk away with
Utilize GPT-5 for advanced predictive modeling and 'what-if' scenario generation.
Implement MCP-enabled tool integration for accessing simulated enterprise and market data.
Integrate Claude Opus 4.1 for sophisticated financial data interpretation and reporting.
Develop agents with extended thinking and adaptive reasoning budgets for complex financial forecasting.
Design and implement an AutoGen multi-agent team for financial analysis and strategic planning.
Reference links and supporting material
Sample data for 1 tasks
Challenge setup
The evaluation will assess the system's accuracy in financial forecasting, the depth and relevance of strategic recommendations, the effective utilization of MCP-enabled tools, and the clarity of agent collaboration a...
Challenge input
{ "historical_data": { "Q1_revenue": "float", "Q1_gmv": "float", ..., "Q3_revenue": "float", "Q3_gmv": "float" }, "market_trends": [{"name": "strin...
Agent execution
No agent tool is listed for this challenge.
Evaluated output
{ "q4_revenue_forecast": "float", "q4_gmv_forecast": "float", "key_growth_drivers": ["string"], "strategic_recommendations": [{"title": "string", "...
- Verifies that the output is valid JSON and matches the specified schema.
- Confirms that MCP-enabled tools were clearly invoked and their outputs contributed to the recommendations (...
- Forecasting Accuracy target: 4
- 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
- Verifies that the output is valid JSON and matches the specified schema.
- Confirms that MCP-enabled tools were clearly invoked and their outputs contributed to the recommendations (e.g., 'tool_used' populated in reasoning path).
Metrics
- Forecasting Accuracy · Target 4
- Strategic Recommendation Quality · Target 4
- Extended Thinking & Scenario Analysis Depth · Target 4
Workflow tasks
- Task 1
Input: { "historical_data": { "Q1_revenue": "float", "Q1_gmv": "float", ..., "Q3_revenue": "float", "Q3_gmv": "float" }, "market_trends": [{"name": "string", "impact": "string"}], "simulation_constraints": { "marketing_budget_increase_cap": "float", "inventory_lead_time_months": "int" } }
Output: { "q4_revenue_forecast": "float", "q4_gmv_forecast": "float", "key_growth_drivers": ["string"], "strategic_recommendations": [{"title": "string", "description": "string", "projected_impact": "string", "reasoning_path": [{"agent": "string", "step": "string", "tool_used": "string (optional)", "output_summary": "string"}]}], "scenario_analysis_summary": "string (e.g., 'If X happens, Y is expected.')" }
Execution harness: Python
Recipe freeze marker
No recipe freeze time is recorded.