Real-time Cyber Incident Response
This challenge tasks you with building a cutting-edge agentic system designed for real-time cybersecurity incident response. Your system will leverage LangGraph to orchestrate a dynamic workflow of specialized agents that can detect, analyze, and mitigate simulated DDoS attacks. This project emphasizes the integration of advanced LLMs like Claude Opus 4.5 for sophisticated threat intelligence analysis and decision-making, alongside MCP-enabled tools that simulate interaction with enterprise security systems (e.g., SIEM, firewall APIs). You will implement adaptive thinking budgets, allowing the agents to prioritize critical alerts and allocate computational resources efficiently for rapid incident resolution. The goal is to demonstrate autonomous, intelligent response capabilities that go beyond static playbooks.
What you are building
The core problem, expected build, and operating context for this challenge.
Build a graph-based multi-agent system using LangGraph with Claude Opus 4.5 and Gemini 2.5 Pro for real-time DDoS threat detection and mitigation, integrated via MCP.
How work is evaluated
The solution will be evaluated based on its ability to autonomously detect, analyze, and mitigate simulated DDoS attacks within a defined time frame, accuracy of threat assessment, and effective utilization of MCP tools.
Challenge datasets
Public datasets, plus the private datasets you have access to.
What you should walk away with
Design and implement graph-based agent workflows using LangGraph for incident response.
Integrate Claude Opus 4.1 for advanced threat intelligence and decision-making.
Develop MCP-enabled tool integrations with simulated enterprise security systems.
Implement adaptive thinking budgets to optimize agent resource allocation during an incident.
Orchestrate a multi-agent system for autonomous DDoS detection and mitigation.
Reference links and supporting material
Sample data for 1 tasks
Challenge setup
The solution will be evaluated based on its ability to autonomously detect, analyze, and mitigate simulated DDoS attacks within a defined time frame, accuracy of threat assessment, and effective utilization of MCP tools.
Challenge input
{ 'scenario_id': 'string', 'attack_vector': 'string', 'target_ip': 'string', 'traffic_rate_gbps': 'integer', 'duration_minutes': 'integer', 'logs':...
Agent execution
No agent tool is listed for this challenge.
Evaluated output
{ 'incident_id': 'string', 'status': 'string', 'detection_time_seconds': 'integer', 'mitigation_actions': ['string'], 'reasoning_path': ['string'],...
- Agent system successfully detects the DDoS incident and reports it.
- Agent system proposes appropriate and effective mitigation actions.
- The solution demonstrates a clear and effective use of LangGraph for workflow orchestration.
- DetectionLatency target: 15
- 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
- Agent system successfully detects the DDoS incident and reports it.
- Agent system proposes appropriate and effective mitigation actions.
- The solution demonstrates a clear and effective use of LangGraph for workflow orchestration.
Metrics
- DetectionLatency · Target 15
- MitigationAccuracy · Target 90
- LLMCostEfficiency · Target 0.03
Workflow tasks
- Task 1
Input: { 'scenario_id': 'string', 'attack_vector': 'string', 'target_ip': 'string', 'traffic_rate_gbps': 'integer', 'duration_minutes': 'integer', 'logs': [{ 'timestamp': 'string', 'source_ip': 'string', 'event_type': 'string', 'details': 'string' }] }
Output: { 'incident_id': 'string', 'status': 'string', 'detection_time_seconds': 'integer', 'mitigation_actions': ['string'], 'reasoning_path': ['string'], 'llm_cost_estimate': 'float' }
Execution harness: Python
Recipe freeze marker
No recipe freeze time is recorded.