Claude Agents SDK Network Switch Diagnostics Engine with Neurolink
Unannounced industrial switch failures erode operator situational awareness and compromise safety logic. Construct an autonomous network diagnostics agent using Claude Agents SDK and Neurolink to analyze switch packet drops and PLC logic alarms. The solution must identify safety-critical switch failures and isolate fault roots with 95% accuracy.
What you are building
The core problem, expected build, and operating context for this challenge.
Deploy Claude Agents SDK extended thinking with Neurolink stream analysis to trace industrial network switch failures affecting safety controls.
How work is evaluated
Evaluates the agent's root-cause accuracy and fault detection speed across simulated OT switch topology failures.
Challenge datasets
Public datasets, plus the private datasets you have access to.
How submissions are scored
These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.
critical_fault_identification
Ensures all critical safety loop impacts are correctly identified
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
root_cause_accuracy
Percentage of correct root cause diagnoses • target: 0.95 • range: 0-1
This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.
What you should walk away with
Configure Claude Agents SDK extended thinking for complex network topology reasoning
Integrate Neurolink for real-time packet loss and industrial Ethernet log parsing
Differentiate between physical switch failures and malicious network traffic disruptions
Generate actionable operator recommendations to maintain situational awareness
Reference links and supporting material
Network event log repository capturing industrial switch degradation, port dropping, and correlated PLC safety trip flags.
Challenge setup
Evaluates the agent's root-cause accuracy and fault detection speed across simulated OT switch topology failures.
Challenge input
JSON containing syslogs, port status tables, and PLC alarm state transitions
Claude Agents SDK
Assigned framework for reasoning over complex system topologies.
Neurolink
Assigned tool for processing high-velocity stream events.
Evaluated output
JSON with root_cause_device (string), fault_type (string), impacted_safety_loops (list), severity (string)
- Ensures all critical safety loop impacts are correctly identified
- Percentage of correct root cause diagnoses • target: 0.95 • range: 0-1
- Benchmark: OT Network Resilience Benchmark
- Root Cause Accuracy target: 0.95
- 1 public reference case
- Python execution harness
- Python sandbox (unavailable on Versalist)
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
- Neurolink · Required
- Claude Code · Optional
- Claude Code · Optional
- Claude 4.1 Opus · Optional
Evaluation contract
- critical_fault_identification · Weight 1
- root_cause_accuracy · Weight 1
Metrics
- root_cause_accuracy · Target 0.95
Benchmarks
- OT Network Resilience Benchmark
- security
Reference cases
- 1 public reference case
Workflow tasks
- Task 1
Input: JSON containing syslogs, port status tables, and PLC alarm state transitions
Output: JSON with root_cause_device (string), fault_type (string), impacted_safety_loops (list), severity (string)
Execution harness: Python
Evaluation tools
- Claude Agents SDK · Agent Framework
- Neurolink · Agent Systems / Log Parser
Recipe freeze marker
No recipe freeze time is recorded.