Automate Secure Enterprise Code
This challenge focuses on building a sophisticated multi-agent system for secure, automated software development within an enterprise environment. Participants will architect a team of specialized agents using AutoGen to collaborate on a given software development task, from requirements gathering to code generation, testing, and deployment. The core innovation lies in integrating these agents with enterprise systems (e.g., version control, CI/CD, internal knowledge bases) through the MCP. MCP will ensure secure, audited, and controlled access for agents to sensitive enterprise tools and data. GPT-5 will serve as the primary reasoning engine for complex code generation and architectural decisions, employing extended thinking and adaptive reasoning budgets to tackle intricate problems. This challenge emphasizes production-ready agent deployment, security, and seamless integration into existing enterprise workflows.
What you are building
Build an AutoGen multi-agent system using GPT-5 for automated enterprise code generation, integrated securely via Model Context Protocol (Model Context Protocol).
How work is evaluated
The evaluation will assess the completeness, correctness, and security of the generated code, as well as the agents' ability to effectively collaborate and securely interact with simulated enterprise systems via Model Context Protocol (MCP).
Datasets
Public datasets, plus the private datasets you have access to.
Learning goals
Integrate agents with enterprise tools and data securely via the Model Context Protocol (Model Context Protocol).
Demonstrate secure and auditable agent interaction with a simulated enterprise environment.
Leverage GPT-5 with extended thinking and adaptive reasoning budgets for complex code generation.
Design and implement a multi-agent system using AutoGen for automated software development.
Resources
Sample data for 2 tasks
Challenge setup
The evaluation will assess the completeness, correctness, and security of the generated code, as well as the agents' ability to effectively collaborate and securely interact with simulated enterprise systems via Model...
Challenge input
{ 'feature_request': 'Develop a Python function to securely hash user passwords using a specified algorithm and salt.' }
Agent execution
No agent tool is listed for this challenge.
Evaluated output
{ 'generated_code': 'def hash_password(...)', 'unit_tests': 'import unittest...', 'repository_update_log': ['git add...', 'git commit...'] }
- Unit tests pass for the generated Python function.
- Demonstrate that critical enterprise interactions (e.g., repository access, secret retrieval) are routed th...
- The generated code adheres to basic security best practices (e.g., no hardcoded secrets, proper hashing).
- Code Completeness target: 0.9
- Docker 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
- Unit tests pass for the generated Python function.
- Demonstrate that critical enterprise interactions (e.g., repository access, secret retrieval) are routed through MCP.
- The generated code adheres to basic security best practices (e.g., no hardcoded secrets, proper hashing).
Metrics
- Code Completeness · Target 0.9
- Agent Collaboration Efficiency · Target 0.8
Workflow tasks
- Task 1
Input: { 'feature_request': 'Develop a Python function to securely hash user passwords using a specified algorithm and salt.' }
Output: { 'generated_code': 'def hash_password(...)', 'unit_tests': 'import unittest...', 'repository_update_log': ['git add...', 'git commit...'] }
Execution harness: Docker
- Task 2
Input: { 'agent_logs': ['MCP_CALL: git.push ...', 'API_CALL: secrets.get_key ...'], 'mcp_rules': { 'secrets.get_key': {'policy': 'encrypted_audit'} } }
Output: { 'audit_report': [{'event': 'secrets.get_key', 'status': 'compliant', 'justification': '...'}] }
Execution harness: Python
Recipe freeze marker
No recipe freeze time is recorded.