Expert OpenTelemetry guidance for collector configuration, pipeline design, and production telemetry instrumentation across Kubernetes, ECS, serverless, and standalone deployments. Use when configuring collectors, designing pipelines, instrumenting applications, implementing sampling, managing cardinality, securing telemetry, writing OTTL transformations, or setting up AI coding agent observability (Claude Code, Codex, Gemini CLI, GitHub Copilot).
94
98%
Does it follow best practices?
Impact
94%
1.34xAverage score across 18 eval scenarios
Passed
No known issues
Rejects the request and explains cardinality violation
0%
100%
Explains metric cardinality explosion risks
0%
100%
Suggests user_id as trace attribute instead of metric dimension
0%
100%
Offers aggregated alternative dimensions
0%
46%
Does not provide metric configuration that includes user_id
0%
100%
Includes memory_limiter processor in the configuration
0%
100%
Places memory_limiter as the first processor in the pipeline
0%
100%
Explains why memory_limiter must be first
0%
100%
Includes proper receiver, processor, and exporter configuration
66%
100%
Uses correct processor ordering: memory_limiter → batch → other processors
0%
100%
Explains certificate generation (CA, server cert, client cert)
100%
100%
Configures Kubernetes secrets for certificates
100%
100%
Configures collector with client authentication
100%
100%
Configures application SDK with client certificates
100%
100%
Includes certificate rotation/expiration strategy
100%
100%
Provides troubleshooting guidance for TLS errors
100%
80%
Uses custom bridge network (not default bridge)
100%
100%
Configures service discovery by container name
100%
100%
Exposes ports selectively
100%
100%
Handles backend connectivity
100%
100%
Addresses firewall and proxy considerations
90%
100%
Includes network troubleshooting guidance
100%
100%
Configures memory_limiter processor
88%
100%
Sets appropriate queue settings for backpressure
60%
100%
Specifies Kubernetes resource requests and limits
80%
100%
Explains memory monitoring and alerting
100%
100%
Provides scaling guidance
100%
100%
Configures collector as ECS service (not task)
100%
100%
Uses host IP for application-to-collector communication
100%
92%
Configures host port mapping
100%
100%
Implements IAM roles for AWS service access
100%
100%
Includes service discovery configuration
100%
100%
Addresses restart and failure handling
100%
100%
Uses DaemonSet resource type (not Deployment)
100%
100%
Includes resource requests and limits
100%
100%
Configures readiness and liveness probes
100%
93%
Implements node affinity or node selectors
100%
100%
Includes RBAC configuration (ServiceAccount, ClusterRole)
85%
100%
Uses toleration for node taints
100%
100%
Uses Deployment resource type with configurable replicas
100%
100%
Configures LoadBalancer or ClusterIP Service
100%
100%
Includes resource requests, limits, and HPA autoscaling
100%
65%
Uses persistent queues for resilience
66%
100%
Implements loadbalancing exporter with trace ID routing
100%
100%
Includes PodDisruptionBudget for high availability
100%
0%
Defines collector container in pod specification
100%
100%
Configures localhost networking between app and collector
100%
100%
Allocates shared resources appropriately
70%
80%
Includes logging and health checks for collector
100%
100%
Explains sidecar trade-offs vs. DaemonSet/Gateway
100%
100%
Recommends sidecar for specific use cases only
100%
100%
Configures collector as sidecar in task definition
100%
100%
Uses container network mode (not host) and container hostname
90%
100%
Allocates CPU and memory within Fargate limits
100%
100%
Includes CloudWatch logging for troubleshooting
100%
100%
Configures environment variables for secrets/config
46%
53%
Warns about sidecar resource overhead
60%
0%
Uses cloud-agnostic OpenTelemetry components
90%
95%
Addresses cloud-specific authentication (IAM, Service Accounts)
100%
96%
Implements per-region or per-cloud aggregation
90%
80%
Handles networking constraints (VPCs, Security Groups)
93%
86%
Considers compliance and data residency
93%
73%
Provides cost and operational considerations
60%
60%
Specifies CLAUDE_CODE_ENABLE_TELEMETRY=1 environment variable
0%
100%
Mentions OTEL_EXPORTER_OTLP_METRICS_TEMPORALITY_PREFERENCE=cumulative
0%
100%
References ~/.claude/settings.json for persistent configuration
0%
100%
Includes privacy controls for prompt and tool logging
0%
100%
Warns about session.id cardinality in metrics
0%
100%
Recommends Gateway deployment pattern for tail sampling
66%
100%
Configures loadbalancing exporter with routing_key: traceID
0%
100%
Sets up Headless Service for consistent routing
0%
100%
Includes proper tail sampling policies for both error and probabilistic sampling
90%
100%
Warns about tail_sampling processor Beta stability level
0%
100%
Specifies appropriate Docker image
100%
100%
Mounts configuration file as volume
100%
100%
Exposes necessary ports
100%
100%
Includes restart policy
100%
100%
Sets resource limits
100%
100%
Configures logging and monitoring
100%
100%
Creates systemd unit file in /etc/systemd/system/
100%
100%
Configures [Unit] section with proper metadata
100%
100%
Sets up [Service] section with ExecStart and ExecReload
75%
100%
Includes User and resource limits (MemoryLimit, LimitNOFILE)
100%
100%
Configures logging via StandardOutput and StandardError
100%
100%
Includes [Install] section for systemd enable
100%
100%
Documents environment variable setup for configuration
100%
100%
Includes collector and sample application services
100%
100%
Uses custom network for service discovery
50%
100%
Mounts collector configuration file
100%
100%
Includes health checks for both services
100%
66%
Exposes collector ports appropriately
53%
53%
Includes environment variables for configuration
70%
75%
Generates valid JSON configuration structure
100%
100%
Configures OTLP receiver on port 4317
100%
100%
Includes batch processor with reasonable timeout
100%
100%
Configures exporter for backend system
100%
100%
Defines service section with pipelines
100%
100%
Includes comments or follows naming conventions
80%
80%
Recommends Gateway pattern for high-volume centralized collection
0%
80%
Explains trade-offs between patterns
0%
100%
Addresses multi-region deployment considerations
0%
100%
Provides resource estimates for 500k traces/min
0%
100%
Considers scaling and cost implications
0%
100%
Table of Contents