Connect your applications
Zero-code instrumentation of AI apps using proxy environment variables
An application in the Sentinel ecosystem refers to any piece of code, automated agent, or internal tooling that leverages AI models and resources.
Applications come in many forms, including:
- Internal tools: Developer utilities like
claude-codethat leverage remote, public Anthropic models. - Customer-facing bots: User-facing agents or customer service systems running on top of private, custom OpenAI-compatible models (like a local GPUStack or vLLM instance).
The easiest way to intercept and protect your application's data streams with Sentinel — without changing a single line of your code — is by redirecting standard model provider environment variables to point to your gateway proxy.
Most AI frameworks and official SDKs (OpenAI, LangChain, Anthropic, etc.) respect default environment variables to determine where to route their API traffic. By overriding these base-URL variables to point to your Sentinel gateway, all application traffic is automatically instrumented. There are two ways to do this:
- Environment-variable instrumentation — set the provider base-URL variables yourself, per terminal or in your app config.
- Sentinel CLI proxy — let the Sentinel CLI manage those variables globally with a single on/off toggle.