SUPERWISE Sentinel · Live demo
Guardrails in real time
Pick or type a prompt and see Sentinel intercept secrets, PII, and toxic content before they reach the model. Every verdict below comes from a real gateway, not a recording.
Gateway status is read from the SUPERWISE control plane every 30 seconds.
What this demo shows
The demo sends a prompt through a live SUPERWISE® Sentinel gateway and shows two things side by side: the prompt you wrote and the prompt the model receives. Sentinel checks the text before it leaves, replaces sensitive values with placeholders such as <EMAIL>, <PHONE>, and <API_KEY>, and blocks a request outright when it should not be sent at all. You can send the result to Anthropic Claude Haiku, OpenAI GPT-4o mini, or Google Gemini 2.5 Flash and read the answer, which still makes sense without the private data.
The three scenarios
- API key in a prompt. An engineer pastes a config file to debug an AWS call that keeps returning 403. Sentinel finds the AWS access key and the alert email address, swaps each for a placeholder, and the model still explains the error.
- Customer record. A support lead pastes a customer’s email address, phone number, and card number to draft an apology for a late refund. Sentinel replaces all three, and the model still writes the apology. The order number and refund amount pass through unchanged.
- Toxic reply. An agent is asked to send a hostile reply to a customer. Sentinel flags the toxic language and blocks the request, so it never reaches the model.
You can also type your own prompt and see what Sentinel does with it.
What Sentinel detects
Secrets such as API keys and access tokens; personal data such as email addresses, phone numbers, account and card numbers, and government IDs; and toxic language. The same checks run on your own machine, on every prompt your team sends to ChatGPT, Claude, and coding agents, and Sentinel logs every request for audit. When the live gateway cannot be reached, this page shows prepared examples and says so.