Overwing guardrail

Overwing guardrail: check text before you send, post, or act on it. Content moderation, PII detection, confidential leak detection, toxicity, self-harm and severity in ~150 ms. Returns a verdict plus one recommended_action (block / redact / review / allow) with calibrated confidence. Pass context (recipient, channel, owns_contact_info) with the outbound-message set. $0.002 USDC, no account.

Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.

Endpoint

POST https://overwing.ai/api/x402/execute

Our checks, last 30 days

We never call tools that send, buy, move money or file anything, not even without paying.

Example input (from the provider)

{
  "body": {
    "context": {
      "channel": "email",
      "owns_contact_info": true,
      "recipient": "the refunds desk already in this email thread"
    },
    "input": "Reach me at dana@example.com or 555-0142 to sort out the refund.",
    "rule_set": "outbound-message"
  },
  "bodyType": "json",
  "method": "POST",
  "type": "http"
}

Promised output schema (from the provider)

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "input": {
      "additionalProperties": false,
      "properties": {
        "body": {
          "properties": {
            "context": {
              "description": "Facts the rules may use: recipient, channel (email, chat, public post), owns_contact_info (true when the recipient already owns the personal data in the text), sender, purpose. Max 8 KB",
              "type": "object"
            },
            "input": {
              "description": "The text to check: a draft message, a model's output, an incoming message, a post",
              "maxLength": 100000,
              "type": "string"
            },
            "metadata": {
              "description": "Opaque data stored with the evaluation (max 8 KB)",
              "type": "object"
            },
            "rule_set": {
              "default": "content-safety",
              "description": "content-safety: toxicity, personal data, self-harm, sexual content, severity. outbound-message: the same plus unauthorized personal data and confidential leaks, judged against context",
              "enum": [
                "content-safety",
                "outbound-message"
              ],
              "type": "string"
            }
          },
          "required": [
            "input"
          ],
          "type": "object"
        },
        "bodyType": {
          "enum": [
            "json",
            "form-data",
            "text"
          ],
          "type": "string"
        },
        "method": {
          "enum": [
            "POST"
          ],
          "type": "string"
        },
        "type": {
          "const": "http",
          "type": "string"
        }
      },
      "required": [
        "type",
        "method",
        "bodyType",
        "body"
      ],
      "type": "object"
    },
    "output": {
      "properties": {
        "example": {
          "properties": {
            "aggregate_score": {
              "description": "0 to 1, weighted across rules",
              "type": "number"
            },
            "confidence": {
              "description": "Minimum confidence across rules, 0 to 1",
              "type": "number"
            },
            "id": {
              "type": "string"
            },
            "latency_ms": {
              "type": "integer"
            },
            "recommended_action": {
              "description": "The one field to branch on. block: do not send. redact: remove the flagged content and check again. review: ask a human. allow: proceed",
              "enum": [
                "block",
                "redact",
                "review",
                "allow"
              ],
              "type": "string"
            },
            "results": {
              "items": {
                "properties": {
                  "action": {
                    "description": "What this rule asks for when it fails",
                    "enum": [
                      "block",
                      "redact",
                      "review"
                    ],
                    "type": "string"
                  },
                  "answer": {},
                  "confidence": {
                    "type": "number"
                  },
                  "probability": {
                    "type": "number"
                  },
                  "rule": {
                    "type": "string"
                  },
                  "type": {
                    "enum": [
                      "choice",
                      "score",
                      "noul"
                    ],
                    "type": "string"
                  },
                  "verdict": {
                    "enum": [
                      "pass",
                      "fail",
                      "review"
                    ],
                    "type": "string"
                  }
                },
                "type": "object"
              },
              "type": "array"
            },
            "verdict": {
              "description": "fail: a rule matched. review: a rule was unsure. pass: neither",
              "enum": [
                "pass",
                "fail",
                "review"
              ],
              "type": "string"
            }
          },
          "type": "object"
        },
        "type": {
          "type": "string"
        }
      },
      "required": [
        "type"
      ],
      "type": "object"
    }
  },
  "required": [
    "input"
  ],
  "type": "object"
}

This page as JSON