Add guardrails and a budget

Add a Prompt Guard element

Under SURFACES in the dashboard sidebar, select LLM, then open the surface you created. The canvas already carries a Prompt Guard node on the request path, between the Access Point and the LLM node, shown greyed out until it’s configured. Select it, switch on Enabled, then select Edit request guards… to open its fullscreen editor. If your appliance offers a partial template that merges a pre-configured guardrails bundle onto an existing surface, you can use that shortcut instead.

In the fullscreen editor, add two rules using the built-in patterns email and credit_card, each set to mask the match.

Select the save icon to save the surface.

Send a request containing PII

Replace <YOUR_APPLIANCE_HOST> and <YOUR_SURFACE_ROUTE> with your values from Create your first LLM Surface:

curl -k -X POST "https://<YOUR_APPLIANCE_HOST><YOUR_SURFACE_ROUTE>/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "messages": [
      { "role": "user", "content": "Draft a reply to jane.doe@example.com about her order." }
    ]
  }'

Replace gpt-5.5 with whichever model your surface’s LLM node is actually configured with, if different.

Prompt Guard matches the email address before the request reaches OpenAI and masks it, so the model never sees the raw value. See Guardrails → and PII protection and NER IDs → for how masking compares to a NER ID pseudonym.

Add a monthly budget

Select the LLM node on the canvas to open its settings panel, then switch on Enforce a usage limit:

Select the save icon in the canvas toolbar to persist the change. The limit is enforced immediately: the next request that would push this surface’s month-to-date spend past $5 is blocked with a 429 response before it reaches OpenAI, rather than being allowed through and billed afterward.