Term | Definition |
|---|---|
| Attribute | Key and value pair that describes a trace, a span, or a log. For example, the HTTP method or the service name. |
Term | Definition |
|---|---|
| Collection endpoint | URL to which the metrics are sent. It is dedicated to your environment. |
| Credential | Secret that authorizes the sending of metrics to Sensedia Observability. |
Term | Definition |
|---|---|
| Golden signals | Signals used to follow the health of a service: latency, traffic, errors, and saturation. |
| Guardrail | AI Gateway rule that evaluates AI requests and responses and can mask or reject content. |
Term | Definition |
|---|---|
| Latency | Time between the start and the end of a request. |
| Log | Message that a service records during execution. |
Term | Definition |
|---|---|
| MCP | Model Context Protocol. Standard that allows AI agents to use external tools. |
| Metric | Numeric measure followed over time, such as number of requests, error rate, or latency. |
Term | Definition |
|---|---|
| OpenTelemetry | Open standard for generating and transmitting traces, logs, and metrics. It is the format of the data that Sensedia Observability receives. |
Term | Definition |
|---|---|
| Percentile (p50, p90, p95, p99) | Value below which a share of the measurements falls. A p99 of 2 seconds indicates that 99% of the requests took up to 2 seconds. |
Term | Definition |
|---|---|
| Resolution | Time interval represented by each point of a chart. On the screen it appears as Resolution. |
| Resource attribute | Attribute that describes what generated the data, such as the service, the version, and the environment. On the screen it appears as Resource attributes. |
| Retention | Period during which data stays available for querying. |
Term | Definition |
|---|---|
| Severity | Level of importance of a log: Trace, Debug, Info, Warning, Error, or Fatal. |
| Span | A step of a trace, with a name, start, duration, and status. A span can have child spans. |
| Span ID | Unique identifier of a span. |
Term | Definition |
|---|---|
| Token | Unit of text processed by an AI model. The consumption and cost of calls are measured in tokens. |
| TPOT | Output tokens per second. Measures the speed at which the model generates the response. |
| Trace | Record of the path of a request through the services, made up of one or more spans. |
| Trace ID | Unique identifier of a trace. Links the spans and logs of the same request. |
| TTFT | Time to first token. Time until the model returns the first token of the response. |
We use cookies to enhance your experience on our site. By continuing to browse, you agree to our use of cookies.Learn more