Automated Financial Modeling
This challenge tasks developers with building a sophisticated multi-agent system using CrewAI to automate complex financial modeling, due diligence, and report generation processes traditionally performed by investment bankers. The system will feature specialized agents (e.g., Data Analyst, Valuation Specialist, Report Writer) collaborating via the A2A (Agent-to-Agent) Protocol. Participants will leverage Claude Opus 4.1 for its advanced reasoning and contextual understanding, implementing a hybrid instant/deep reasoning approach to handle both quick data queries and intricate financial calculations. The agents will integrate with external data sources through RAG, simulating access to market data and company financials, ultimately producing a comprehensive investment analysis report.
What you are building
The core problem, expected build, and operating context for this challenge.
Orchestrate a CrewAI multi-agent system with Claude Opus 4.1 for automated financial modeling and reporting, using A2A protocol for collaboration.
How work is evaluated
The solution will be evaluated on the accuracy and completeness of the generated financial analysis report, the effectiveness of agent collaboration via A2A, the correct application of financial tools, and the robustness of the RAG system. The overall workflow's efficiency and reasoning quality will also be assessed.
Challenge datasets
Public datasets, plus the private datasets you have access to.
What you should walk away with
Implement the A2A Protocol for structured and efficient agent-to-agent communication.
Deploy Claude Opus 4.1 for sophisticated reasoning in a hybrid instant/deep reasoning architecture.
Design and orchestrate role-based multi-agent teams using CrewAI for complex business processes.
Integrate RAG mechanisms to provide agents with up-to-date and context-specific financial data.
Reference links and supporting material
Sample data for 1 tasks
Challenge setup
The solution will be evaluated on the accuracy and completeness of the generated financial analysis report, the effectiveness of agent collaboration via A2A, the correct application of financial tools, and the robustn...
Challenge input
{"company_profile": "String", "financial_data_stub": {"revenue": "List", "net_income": "List", "cash_flow": "List"}, "market_context": "String", "r...
Agent execution
No agent tool is listed for this challenge.
Evaluated output
{"executive_summary": "String", "valuation_analysis": {"method": "String", "value": "Float", "justification": "String"}, "risk_assessment": "String...
- Checks if all required sections of the report are present.
- Verifies that the agent communication log indicates interaction between agents.
- Assesses if the valuation rationale aligns logically with the provided (stubbed) financial data.
- RAGUtilisationScore target: 0.8
- 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
- Checks if all required sections of the report are present.
- Verifies that the agent communication log indicates interaction between agents.
- Assesses if the valuation rationale aligns logically with the provided (stubbed) financial data.
Metrics
- RAGUtilisationScore · Target 0.8
- ReportClarity · Target 4
Workflow tasks
- Task 1
Input: {"company_profile": "String", "financial_data_stub": {"revenue": "List", "net_income": "List", "cash_flow": "List"}, "market_context": "String", "rag_docs_stub": ["String"]}
Output: {"executive_summary": "String", "valuation_analysis": {"method": "String", "value": "Float", "justification": "String"}, "risk_assessment": "String", "recommendation": "String", "agent_communication_log": ["String"]}
Execution harness: Python
Recipe freeze marker
No recipe freeze time is recorded.