Observability

Here you'll learn about Javelin's Observability features, which give you the deep insights you need to make the most of your AI resources and understand your AI traffic.

Traces

Javelin's observability is built on tracing. A trace is the lifecycle of a single request as it moves through the platform. For every call your application makes, Javelin creates a trace so you can see step by step what happened, when, and why. If you explore a trace further, you can find lots of useful information, like:

• Latency: Spot performance issues by understanding how long a request spent in your application, the Javelin Gateway, and the LLM provider.

• Token Metrics: Anticipate and manage costs by getting an accurate account of token usage.

• Guardrail Usage: Diagnose why a request was modified or blocked by referencing its detailed security audit.

• Payloads: Understand what data led to unexpected behavior by looking at request and response payloads at any stage of the process.

• Metadata: Filter, search, and gather data to investigate incidents and study trends by taking advantage of context-rich tags.

With this level of detail at your fingertips, your developers can resolve issues in minutes rather than hours.

Analytics and Dashboards

Just as traces give you deep insights about individual requests, Javelin's Analytics Dashboards offer a high-level view of your organization's overall AI security health. You can filter by time range, application, route, and other metadata, tailored to whatever view you need. Javelin also provides pre-built dashboards where you can dig into key areas like usage and cost, performance, and type and frequency of threats.

Model Playground

Observability also means testing and experimenting in a managed environment, which is where Javelin's Model Playground comes in. This interactive interface lets you directly test your configured routes.

OpenTelemetry Integration

Javelin's tracing features comply with OpenTelemetry, the industry standard for observability. This integration lets you connect AI performance and security data from Javelin with findings from the rest of your toolkit, giving your teams a single, clear view. You can also easily export your data from Javelin into various enterprise observability tools.

What's Next?

• See in Threat Alerts how security events are reported as alerts.

• Learn in Governance & Reporting how you can use observability data to maintain compliance.