Docs
Terminology
Terminology
Core terms used across AITracer observability, governance, verification, and operational intelligence workflows.
Operational Intelligence
| Term | Definition | Why It Matters |
|---|---|---|
| Cost Attribution | Tracking AI spend by user, workflow, action, or model. | Helps teams identify which features are driving AI costs. |
| Token Efficiency | Measuring how many tokens are consumed for each model interaction. | Helps identify bloated prompts and inefficient workflows. |
| Model Allocation | Distributing workloads across the appropriate model tiers. | Prevents simple tasks from being routed to unnecessarily expensive models. |
| P95 Latency | The response time of the slowest 5% of requests. | Helps teams detect latency spikes before they impact users. |
| Anomaly Detection | Identifying unusual spikes in latency, cost, or model behavior. | Helps teams investigate unexpected operational failures. |
Governance & Risk
| Term | Definition | Why It Matters |
|---|---|---|
| Policy Evaluation | Reviewing AI activity against predefined governance rules. | Ensures workflows meet operational and compliance requirements. |
| Risk Detection | Identifying sensitive data patterns such as credentials, payment data, or PII. | Helps teams prevent risky outputs and compliance violations. |
| Audit Record | A stored record of AI execution activity. | Creates historical accountability for model behavior. |
| Governance Controls | Approval workflows and operational safeguards for high-risk AI activity. | Prevents unauthorized or risky actions. |
Verification & Audit Vault
| Term | Definition | Why It Matters |
|---|---|---|
| Audit Vault | AITracer’s storage layer for execution records. | Centralizes trace history for compliance and investigations. |
| SHA-256 Verification | Cryptographic hashing used to validate record integrity. | Detects unauthorized modifications. |
| Integrity Validation | Recalculating hashes to confirm records remain unchanged. | Proves records remain tamper-evident over time. |
| Execution Record | A complete record of a single AI action. | Captures model usage, latency, cost, policies, and verification metadata. |
Trace Operations
| Term | Definition | Why It Matters |
|---|---|---|
| Trace | A record of a complete AI interaction from request to response. | Helps teams understand what happened during execution. |
| Span | A smaller operation inside a trace. | Helps teams isolate bottlenecks and failures. |
| Model Invocation | A single call made to an LLM provider. | Tracks provider usage and execution behavior. |
| Workflow Execution | A sequence of AI tasks completed across a larger workflow. | Helps teams understand multi-step automation performance. |