---
updatedAt: 2026-10-12T12:56:54.000Z
agentTools:
projectIndex: https://docs.superwise.ai/llms.txt
---
# What is Sentinel?
SUPERWISE® Sentinel is an AI firewall: a single control plane to secure and standardize decentralized AI operations. It sits in front of your LLM traffic as a lightweight proxy, enforcing guardrails at the edge and giving you full visibility, without your prompts or responses ever leaving your environment.
Prompts and responses stay between you and the model provider you chose — only operational metadata reaches SUPERWISE. See [Data privacy](https://docs.superwise.ai/docs/data-privacy).
## How does a request flow through Sentinel?
```mermaid
flowchart LR
tools["Your AI tools
Claude Code, your own apps,
ChatGPT and Claude in the browser"]
gateway["Sentinel gateway
on your PC or in your network
checks the prompt and
replaces sensitive details"]
provider["The model provider you chose
OpenAI, Anthropic, or Gemini"]
log["Live activity
the request's metadata is recorded"]
tools -- "prompt" --> gateway
gateway -- "cleaned prompt" --> provider
gateway -. "what was checked and replaced" .-> log
```
1. **Your AI tools send the prompt to the Sentinel gateway.** The gateway runs on your PC or in your network, and the tools reach it instead of the provider. There is no SDK, wrapper, or code change: the Windows app and the CLI point supported tools at the gateway, and your own apps reach it through the provider's base URL.
2. **The gateway checks the prompt against your [guardrails](https://docs.superwise.ai/docs/guardrails).** Secrets and personal data are replaced with a placeholder, `{{REDACTED}}` by default, and a request that should not be sent at all is blocked.
3. **The cleaned prompt goes to the model provider you chose,** such as OpenAI, Anthropic, or Gemini, as it would without Sentinel. The response comes back to your tool unchanged.
4. **The request's metadata is recorded.** Which guardrails ran and what they did appear in [Live activity](https://docs.superwise.ai/docs/activity-log). SUPERWISE receives this operational metadata, never the prompt or the response.
Nothing changes in how your team works.
## Where does Sentinel run?
* **On a Windows PC**, as the [Sentinel for Windows](https://docs.superwise.ai/docs/sentinel-for-windows) app. No Docker, no Python, and no secret to copy.
* **From the terminal** on Windows, macOS, or Linux, with the Sentinel CLI. See [Install on macOS and Linux (CLI)](https://docs.superwise.ai/docs/install-cli).
* **As a team gateway** in your own cloud on AWS, GCP, or Azure, or in any Kubernetes cluster with the Helm chart. See [Deploy a gateway](https://docs.superwise.ai/docs/deploy-a-gateway).
Prompts and responses never pass through SUPERWISE's cloud. Each gateway reports only operational metadata (request counts, which guardrail fired, and latency) to the SUPERWISE control plane, and pulls its policy from it. See [Data privacy](https://docs.superwise.ai/docs/data-privacy).
## Which AI tools does Sentinel cover?
Tools running on the machine are covered by the [Sentinel for Windows](https://docs.superwise.ai/docs/sentinel-for-windows) app or the [Sentinel CLI](https://docs.superwise.ai/docs/sentinel-cli-proxy); coverage depends on the tool and the OS, as below. Chat sites are covered through the browser extension, which is in **preview**.
### On the machine
Terminal agents, desktop apps, and the apps you build.
| Tool | Windows | Mac & Linux |
| ---------------------------------------------------------------- | ----------- | ----------- |
| Claude Code | Supported | Supported |
| Codex CLI | Supported\* | Supported\* |
| Antigravity (agy) CLI, Google's coding agent | Supported\* | Supported\* |
| Your own apps and agents (OpenClaw, LangChain, or any framework) | Supported | Supported |
| Claude Desktop | Supported | Supported |
| ChatGPT / Codex desktop app | Coming soon | Supported |
| Antigravity / Gemini desktop app | Coming soon | Coming soon |
\*The Codex and Antigravity CLIs are covered when they authenticate with an API key, not when signed in with a ChatGPT or Google account. On Mac and Linux, the [Sentinel CLI](https://docs.superwise.ai/docs/sentinel-cli-proxy) configures Codex and Claude Desktop for you.
### In the browser
The browser extension is in **preview**, so all browser coverage here is preview. It works in Chrome and Edge, on Windows only for now, alongside the [Sentinel for Windows](https://docs.superwise.ai/docs/sentinel-for-windows) app.
| Chat site | Status |
| ------------------------------------------- | ------------------- |
| Claude (claude.ai) | Supported (preview) |
| ChatGPT (chatgpt.com) | Supported (preview) |
| Gemini, Copilot, Grok, Perplexity, DeepSeek | In development |
## What does Sentinel not cover?
Sentinel replaces the identifiers its guardrails recognize, listed in [PII redaction](https://docs.superwise.ai/docs/pii-redaction) and [Secret & credential detection](https://docs.superwise.ai/docs/secret-credential-detection). It does not cover names, street addresses, other dates, or unlabeled record numbers, so names and most dates still reach the model. It acts only on the tools marked Supported or Preview above.
Sentinel works by base-URL redirection: a tool is covered when its provider base URL points at the gateway. It does not sit in front of all network traffic, and a tool that calls the provider directly is not checked. On the requests it receives, the gateway checks the text-generation routes, OpenAI `v1/chat/completions`, Anthropic `v1/messages`, and Gemini `generateContent`, and passes every other route through unchecked. Guardrails run on the prompt; the model's response comes back unmodified. See [Architecture](https://docs.superwise.ai/docs/architecture#failure-modes-and-limits).
## See also
* [Get started](https://docs.superwise.ai/docs/getting-started): install Sentinel and run your first check.
* [Architecture](https://docs.superwise.ai/docs/architecture): how the control plane and gateways fit together.
* [Data privacy](https://docs.superwise.ai/docs/data-privacy): what stays on your side and what reaches SUPERWISE.