Meter Definitions
The AI Guard service registers four meters under the instrument name ai-guard-server. Three are submitted by clients via POST /metric, and one is generated automatically from classification responses.
Required Attributes
All meters require the following attributes:
| Attribute | Description | Example |
|---|---|---|
agent_id | Unique identifier for the calling AI agent | "my-agent" |
platform | AI platform originating the request | "AMAZON_BEDROCK" |
Supported Platform Values
| Platform | Value |
|---|---|
| Amazon Bedrock | AMAZON_BEDROCK |
| Amazon SageMaker | AMAZON_SAGEMAKER |
| Azure AI Foundry | AZURE_FOUNDRY |
| Databricks | DATABRICKS |
| Google Cloud Vertex AI | GCP_VERTEX |
Meter Reference
ai_guard.agent β Agent Response Time
ai_guard.agent β Agent Response Time| Property | Value |
|---|---|
| Type | Histogram (u64) |
| Source | POST /metric (SDK) |
| Value | Response time in milliseconds (integer string) |
| Required Attributes | agent_id, platform |
Records the response time of the LLM agent. Used to track agent performance and latency trends.
SDK Example:
client.metric(MetricsEvent(
attributes={},
meter=MetricsEventMeter(name="ai_guard.agent", value="1234"),
))Export Statistics (OneTrust exporter):
| Statistic | Description |
|---|---|
AVG | Average response time (sum / count) |
MIN | Minimum response time in the interval |
MAX | Maximum response time in the interval |
P99 | 99th percentile, interpolated from histogram bucket boundaries |
ai_guard.user β User Session
ai_guard.user β User Session| Property | Value |
|---|---|
| Type | Counter (u64) |
| Source | POST /metric (SDK) |
| Value | "1" |
| Required Attributes | agent_id, platform, new_session |
Records user interactions and session starts. Used to track engagement metrics.
| Additional Attribute | Values | Description |
|---|---|---|
new_session | "true" / "false" | Whether this interaction starts a new session |
SDK Example:
client.metric(MetricsEvent(
attributes={"new_session": "true"},
meter=MetricsEventMeter(name="ai_guard.user", value="1"),
))ai_guard.redact β Redaction Event
ai_guard.redact β Redaction Event| Property | Value |
|---|---|
| Type | Counter (u64) |
| Source | POST /metric (SDK) |
| Value | "1" |
| Required Attributes | agent_id, platform, action, actor |
Records redaction and block events. Used to track how often sensitive data is detected and acted upon.
| Additional Attribute | Values | Description |
|---|---|---|
action | "redact" / "block" | The type of action taken |
actor | "user" / "agent" | Source of the classified text |
SDK Example:
client.metric(MetricsEvent(
attributes={"action": "redact", "actor": "user"},
meter=MetricsEventMeter(name="ai_guard.redact", value="1"),
))ai_guard.classification β Classification Count
ai_guard.classification β Classification Count| Property | Value |
|---|---|
| Type | Counter (u64) |
| Source | Auto-generated (per match in classification response) |
| Value | "1" (per match) |
| Required Attributes | agent_id, platform, actor, classifier |
Automatically incremented once per classifier match in a classification response. Tracks which types of sensitive data are being detected most frequently.
| Attribute | Source | Description |
|---|---|---|
agent_id | From request context | Unique agent identifier |
platform | From request context | AI platform identifier |
actor | From request context | "user" or "agent" |
classifier | Auto-set by service | The classifier code that matched (e.g., US_PHONE_NUMBER) |
Not SubmittableThis meter is generated automatically by the service. It cannot be submitted via
POST /metricorclient.metric().
Custom Attributes
The service supports optional additional attribute keys beyond the built-in required keys. These are configured in the metrics.allowed-attributes section of the service configuration:
metrics:
allowed-attributes:
- custom_key
- environmentAttributes not in the allowed set or the required set (agent_id, platform) are rejected with a 400 Bad Request.
What's Next?
- Metrics Exporters β How metrics are exported to AI Governance
- Metrics Overview β Pipeline architecture
- Observability & Metrics (SDK) β Send metrics from your application
Updated about 4 hours ago