Crypto Token Due Diligence
This challenge tasks you with building a robust, multi-agent system for automated due diligence on emerging crypto tokens. Utilizing CrewAI, you will orchestrate specialized agents- such as a Market Researcher, Financial Analyst, and Risk Assessor -to collaborate using the A2A Protocol. The system will leverage Gemini 2.5 Pro's Deep Think mode for quantitative analysis and Claude Opus 4.1 for nuanced qualitative assessment, performing comprehensive research from diverse sources to generate an investment-grade report.
What you are building
The core problem, expected build, and operating context for this challenge.
This challenge tasks you with building a robust, multi-agent system for automated due diligence on emerging crypto tokens. Utilizing CrewAI, you will orchestrate specialized agents- such as a Market Researcher, Financial Analyst, and Risk Assessor -to collaborate using the A2A Protocol. The system will leverage Gemini 2.5 Pro's Deep Think mode for quantitative analysis and Claude Opus 4.1 for nuanced qualitative assessment, performing comprehensive research from diverse sources to generate an investment-grade report.
Shared data for this challenge
Review public datasets and any private uploads tied to your build.
What you should walk away with
Master CrewAI for orchestrating dynamic, goal-oriented teams of specialized agents, defining clear roles, goals, and backstories for robust collaboration in complex research tasks.
Implement A2A (Agent-to-Agent) Protocol for secure, structured, and cross-platform communication between agents, ensuring data integrity and efficient information flow in a decentralized research process.
Deploy Gemini 2.5 Pro in Deep Think mode for advanced quantitative analysis, complex financial modeling, and in-depth risk assessment of blockchain projects, tokenomics, and market dynamics.
Integrate Claude Opus 4.1 for sophisticated qualitative analysis, discerning market sentiment from unstructured text data (e.g., social media, forums, project whitepapers) and evaluating the credibility and feasibility of project claims.
Build a RAG system to aggregate real-time data from diverse sources including blockchain explorers, crypto news APIs, project whitepapers, social media platforms, and financial databases for comprehensive and up-to-date research.
Design adaptive reasoning workflows where agents dynamically adjust their 'thinking budget' or depth of analysis based on the complexity or criticality of the information being processed, optimizing resource use and response time.
How this agent runs
The system will be evaluated on the completeness, accuracy, and depth of its due diligence report for a given crypto token. This includes correctly identifying key project details, assessing financial viability, pinpo...
Challenge input
{'token_name': 'string', 'whitepaper_url': 'string', 'initial_investment_thesis': 'string'}
Agent execution
The configured agent processes the input under the challenge policy.
Evaluated output
{'project_overview': 'string', 'tokenomics_analysis': 'json', 'market_sentiment': 'string', 'risk_factors': ['string'], 'investment_recommendation'...
- Ensure all required output fields are present and non-empty.
- Verify if at least 3 plausible risk factors are identified in the report.
- Analytical Depth target: 4
- Python execution harness
View technical recipe
Configured tools
No tool records are attached.
Evaluation contract
- The evaluation module defines the checks.
Recipe state
This is a preview. The configuration can change before the evaluation recipe is locked.
Run this agent on your dataset and AI stack
Bring your dataset, model providers, and success criteria. We will scope the right managed run for your team.
Scope a managed run[ok] Wrote CHALLENGE.md
[ok] Wrote .versalist.json
[ok] Wrote eval/examples.json
Requires VERSALIST_API_KEY. Works with any MCP-aware editor.
DocsFind another challenge
Jump to a random challenge when you want a fresh benchmark or a different problem space.