R&D Team for Specialized AI Model Definition
Orchestrate a multi-agent team using CrewAI to simulate an R&D department tasked with defining the requirements and preliminary architecture for a highly specialized AI model, such as one for automating heavy construction equipment. This challenge requires defining distinct roles (e.g., AI Researcher, Robotics Engineer, Project Manager), assigning specific goals, and enabling collaborative problem-solving. Agents must leverage external tools for information gathering and document generation, ultimately producing a comprehensive R&D report detailing the model's purpose, key features, data needs, and architectural considerations. The focus is on complex task decomposition and inter-agent communication facilitated by a shared memory and structured output.
What you are building
Orchestrate a CrewAI multi-agent team to autonomously research, design, and plan a specialized AI model using collaborative roles and external tool integrations.
How work is evaluated
The evaluation will assess the CrewAI team's ability to collaboratively generate a comprehensive R&D report for a specialized AI model, checking for completeness, coherence, factual accuracy, and architectural soundness. Inter-agent communication efficiency will also be considered.
Datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
Report Completeness
Checks if all required sections of the R&D report are present and non-empty.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Coherence and Readability
Verifies that the report is well-structured and easy to understand.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Tool Utilization Trace
Confirms that agents demonstrably used external tools (e.g., web search, Milvus) during their process via LangSmith traces.
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Factual Accuracy Score
Measures the correctness of technical details and factual statements within the report (0-1). • target: 0.9 • range: 0.7-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Architectural Soundness
Evaluates the feasibility and robustness of the proposed architectural overview (0-1). • target: 0.85 • range: 0.6-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Inter-Agent Communication Effectiveness
Assesses the quality and relevance of messages exchanged between agents (0-1), derived from LangSmith traces. • target: 0.9 • range: 0.7-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
Learning goals
Master the CrewAI framework for defining agents with specific roles, backstories, goals, and associated tools.
Implement advanced task decomposition and delegation strategies within a CrewAI workflow, ensuring agents collaborate effectively.
Integrate a vector database like Milvus to serve as a shared knowledge repository for agents, allowing them to store and retrieve research findings.
Develop custom tools for agents, such as a web search tool (e.g., using Serper API) for external information gathering and a document generation tool.
Leverage the Gemini 2.5 Pro model for individual agent intelligence, focusing on its advanced reasoning and problem-solving capabilities.
Utilize LangSmith for comprehensive tracing, debugging, and evaluation of multi-agent interactions, identifying bottlenecks and improving collaboration patterns.
Design a robust output mechanism for the CrewAI team to synthesize their findings into a structured R&D report, potentially using Pydantic for schema validation.
Resources
Sample data for 1 tasks
Challenge setup
The evaluation will assess the CrewAI team's ability to collaboratively generate a comprehensive R&D report for a specialized AI model, checking for completeness, coherence, factual accuracy, and architectural soundne...
Challenge input
{'project_goal': 'string', 'initial_constraints': ['string']}
Agent execution
No agent tool is listed for this challenge.
Evaluated output
{'model_purpose': 'string', 'key_features': ['string'], 'data_requirements': {'sources': ['string'], 'volume_estimate': 'string'}, 'architectural_o...
- Checks if all required sections of the R&D report are present and non-empty.
- Verifies that the report is well-structured and easy to understand.
- Confirms that agents demonstrably used external tools (e.g., web search, Milvus) during their process via L...
- Factual Accuracy Score target: 0.9
- 1 public reference case
- Python execution harness
Shows the first task, up to three tools, and up to three evidence items.
View technical recipe
Configured tools
No tool records are attached.
Evaluation contract
- Report Completeness · Weight 1
- Coherence and Readability · Weight 1
- Tool Utilization Trace · Weight 1
- Factual Accuracy Score · Weight 1
- Architectural Soundness · Weight 1
- Inter-Agent Communication Effectiveness · Weight 1
Metrics
- Factual Accuracy Score · Target 0.9
- Architectural Soundness · Target 0.85
- Inter-Agent Communication Effectiveness · Target 0.9
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: {'project_goal': 'string', 'initial_constraints': ['string']}
Output: {'model_purpose': 'string', 'key_features': ['string'], 'data_requirements': {'sources': ['string'], 'volume_estimate': 'string'}, 'architectural_overview': 'string', 'implementation_plan_summary': 'string', 'risks_challenges': ['string']}
Execution harness: Python
Recipe freeze marker
No recipe freeze time is recorded.