Agent Output Verifier by SarnAI

Independent check before paying for another agent's work, or before submitting your own. Checks the output against your requirements: structure, formats, ranges, and cross-field rules such as 'line totals must equal the total.' Returns pass/fail, % of checks passed, fix hints, and an Ed25519-signed attestation and receipt you can show as evidence of why you paid or refused. $0.02 per check, small next to the payment it protects. Free during launch: 1000 checks a day (MCP and REST).

{
  "type": "object",
  "properties": {
    "task_id": {
      "description": "Your own identifier for this verification. 1-200 printable characters, no control characters and no lone Unicode surrogate; a request outside that range is rejected (422), not truncated.",
      "maxLength": 200,
      "minLength": 1,
      "pattern": "^[^\\x00-\\x1f\\x7f]+$",
      "title": "Task Id",
      "type": "string"
    },
    "expected_schema": {
      "additionalProperties": true,
      "title": "Expected Schema",
      "type": "object"
    },
    "submitted_output": {
      "title": "Submitted Output"
    },
    "agent_id": {
      "anyOf": [
        {
          "maxLength": 200,
          "minLength": 1,
          "pattern": "^[^\\x00-\\x1f\\x7f]+$",
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional label identifying the agent that produced submitted_output (for example, the seller), used for /reputation and the trust score: records and scores belong to the producer, not to whoever calls this endpoint. It is an unauthenticated label. agent_ids starting with 'test-' are reserved for testing: the verification runs normally but is never recorded, so it cannot affect any reputation or trust score. 1-200 printable characters (same rule as GET /score/{agent_id}); a longer or malformed value is rejected (422), not truncated.",
      "title": "Agent Id"
    },
    "strict_content_check": {
      "default": false,
      "description": "Opt-in. When true, any string in submitted_output containing control characters (e.g. null bytes) or embedded HTML/script markup makes the result 'fail'. When false (default) this is not checked at all.",
      "title": "Strict Content Check",
      "type": "boolean"
    },
    "bounds": {
      "anyOf": [
        {
          "additionalProperties": {
            "$ref": "#/$defs/Bound"
          },
          "maxProperties": 50,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional per-field min/max, keyed by dotted path with '[]' array wildcard (e.g. 'items[].price'). Numbers or ISO-8601 dates. Violations are reported as informational flags unless enforce_rules is true.",
      "title": "Bounds"
    },
    "rules": {
      "anyOf": [
        {
          "items": {
            "$ref": "#/$defs/ConsistencyRule"
          },
          "maxItems": 50,
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional cross-field rules: sum_equals, gte, lte, exists_in, unique (duplicate detection). Violations are reported as informational flags unless enforce_rules is true.",
      "title": "Rules"
    },
    "enforce_rules": {
      "default": false,
      "description": "Opt-in. When true, every configured bound and consistency rule must hold, or the result is 'fail' (like strict_content_check), with an 'enforce_rules: ...' entry in errors. That includes a rule or bound that cannot run (its path is missing, a value is not comparable, a value has nothing to be compared against): it fails rather than passing silently, so omitting a field, in the whole path or in any array element the rule applies to, cannot skip a binding rule. A rule or bound with if_present: true is skipped where its field is absent instead. When false (default) nothing changes: violations and unrunnable rules stay informational flags. Echoed back in the signed response.",
      "title": "Enforce Rules",
      "type": "boolean"
    },
    "detail": {
      "default": "full",
      "description": "'full' (default) returns everything; 'compact' returns only the summary, next actions, receipt and signature. Use compact inside verify-repair loops to save tokens. 'compact' fields: summary, next_actions, result, the receipt fields (verification_id, task_id, agent_id, output_hash, schema_hash, rules_hash, verified_at, verifier_version, enforce_rules, strict_content_check), verify and attestation - errors, errors_detail, flags, hints and the scores are left out entirely, not just emptied. Both shapes are fully signed.",
      "enum": [
        "full",
        "compact"
      ],
      "title": "Detail",
      "type": "string"
    }
  },
  "required": [
    "task_id",
    "expected_schema",
    "submitted_output"
  ],
  "$defs": {
    "Bound": {
      "description": "Optional inclusive min/max for one field. Numbers, or ISO-8601 date /\ndatetime strings (compared as datetimes; naive values are treated as UTC).",
      "properties": {
        "min": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "number"
            },
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Min"
        },
        "max": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "number"
            },
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Max"
        },
        "if_present": {
          "default": false,
          "description": "Optional. When true, the check is skipped where this field is absent (the whole path, or an element of an array it applies to) instead of being reported as unable to run: no flag, and enforce_rules does not fail on it. When false (default) an absent field is a flag, and a failure under enforce_rules.",
          "title": "If Present",
          "type": "boolean"
        }
      },
      "title": "Bound",
      "type": "object"
    },
    "ConsistencyRule": {
      "description": "One caller-supplied cross-field rule. Paths use dotted keys with '[]'\nas an array wildcard, e.g. 'items[].price' or 'order.total'.\n\n  sum_equals: sum of `field` values == `equals_field` value (or `equals`)\n  gte / lte:  `field` >= / <= `other_field` value (or `value`)\n  exists_in:  every `field` value is among `in_field` values (or `values`)\n  unique:     no duplicates among `field` values; if `field` names an\n              array itself, no duplicate elements in it",
      "properties": {
        "type": {
          "enum": [
            "sum_equals",
            "gte",
            "lte",
            "exists_in",
            "unique"
          ],
          "title": "Type",
          "type": "string"
        },
        "field": {
          "title": "Field",
          "type": "string"
        },
        "equals_field": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Equals Field"
        },
        "equals": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "number"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Equals"
        },
        "other_field": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Other Field"
        },
        "value": {
          "anyOf": [
            {
              "type": "integer"
            },
            {
              "type": "number"
            },
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Value"
        },
        "in_field": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "In Field"
        },
        "values": {
          "anyOf": [
            {
              "items": {},
              "type": "array"
            },
            {
              "type": "null"
            }
          ],
          "default": null,
          "title": "Values"
        },
        "tolerance": {
          "default": 1e-9,
          "description": "Absolute tolerance for sum_equals and the near-match check gte/lte use. The default (1e-9) suits exact arithmetic but is usually too tight for money that passed through any floating-point math (e.g. percentage discounts, tax, unit-price * quantity): 0.1 + 0.2 != 0.3 in IEEE-754 floats by about 5.5e-17, and real pricing data regularly carries larger rounding drift than that. For a field in major currency units (dollars, euros), 0.01 (one cent) is a reasonable tolerance; for minor units (cents) already stored as integers, the default is fine. Too loose a tolerance can mask a genuine mismatch, so prefer the smallest value that tolerates your data's own rounding, not a large one 'to be safe.'",
          "minimum": 0,
          "title": "Tolerance",
          "type": "number"
        },
        "if_present": {
          "default": false,
          "description": "Optional. When true, the check is skipped where this field is absent (the whole path, or an element of an array it applies to) instead of being reported as unable to run: no flag, and enforce_rules does not fail on it. When false (default) an absent field is a flag, and a failure under enforce_rules. Applies to this rule's own `field`; fields it refers to (equals_field, other_field, in_field) must still exist.",
          "title": "If Present",
          "type": "boolean"
        }
      },
      "required": [
        "type",
        "field"
      ],
      "title": "ConsistencyRule",
      "type": "object"
    }
  },
  "title": "verify_schemaArguments"
}

Use before relying on another agent. Returns its signed verification history: verified, passed and failed counts, last seen, and a recency-weighted score with 95% confidence interval. Check a counterparty before you pay, or see the record buyers will see. Agent Scores are paid only: $0.01 per lookup.

{
  "type": "object",
  "properties": {
    "agent_id": {
      "description": "The agent_id whose verification history to score (as passed to /verify/schema): the agent that produced the output checked by those calls (for example, the seller). agent_ids starting with 'test-' are reserved for testing and never have a history.",
      "maxLength": 200,
      "minLength": 1,
      "pattern": "^[^\\x00-\\x1f\\x7f]+$",
      "title": "Agent Id",
      "type": "string"
    }
  },
  "required": [
    "agent_id"
  ],
  "title": "get_verification_recordArguments"
}