Validation rules

A Validate step runs a list of rules over the data an Extract step produced and flags anything that fails. Every rule is one of two kinds, and a single Validate step can mix both.

Rule kind	How it’s checked	Best for	Cost
AI	A model reads your plain-language description and judges the data	Fuzzy / semantic conditions (“the vendor looks like a real company”, “the two names refer to the same person”)	Billed per rule
Deterministic	A structured check runs in plain code — no model	Exact, testable conditions (a number in range, `a + b = c`, a value in a set, a pattern, a required field)	Free

Reach for a deterministic rule whenever the condition is something you could check with a calculator or a lookup — it’s instant, free, and never flakes. Use an AI rule when the condition needs judgement or language understanding.

Deterministic checks

Each deterministic rule is built from one check. Fields are referenced by name (the field name from the upstream Extract step).

Check	What it asserts	Example
Number in range	A numeric field falls within bounds	`amount` between `0` and `1000000`
Date in range	A date field falls within bounds — each an ISO date or `today` (relative)	`expiry_date` on or after `today` (not expired)
Arithmetic	A sum / difference / product of fields equals another field, within a tolerance	`subtotal + tax = total` (±0.01)
Comparison	A field compares (`=`, `≠`, `>`, `≥`, `<`, `≤`) to a fixed value or another field	`end_date ≥ start_date`
One of	A field’s value is in an allowed set	`currency` is one of `EUR`, `USD`, `GBP`
Pattern	A field matches a regular expression	`iban` matches `^[A-Z]{2}\d{2}`
Required	A field is present and not empty	`vendor_name` is filled in

Each check resolves to pass, fail, or inconclusive (when the referenced field is missing or can’t be read as the expected type). Numbers are read leniently — "€1.234,56" and "1,234.56" both parse — and dates accept the common written formats.

Build a rule in Studio

Add a Validate step after the Extract step whose output you want to check.
Open the step, go to the Rules tab, and click Add rule.
Choose AI or Deterministic with the toggle.
- AI — type the rule in plain language; reference a field with the field picker.
- Deterministic — pick a check type, choose the field(s), and enter the values.
Set a severity (error or warning) and save.

Failures appear in the Validation tab of the results, next to the extracted data.

Author rules via the API

Validation rules are part of the validate node in the typed-graph create body — no separate endpoint. A deterministic rule carries a check; an AI rule carries a description. Reference fields by their name as defined on the upstream extract.

{
  "name": "Invoice with checks",
  "nodes": [
    { "id": "parse_1", "type": "parse" },
    {
      "id": "extract_1",
      "type": "extract",
      "extraction_schema": {
        "fields": [
          { "name": "invoice_date", "description": "Invoice date.", "data_type": "date" },
          { "name": "subtotal", "description": "Subtotal before tax.", "data_type": "float" },
          { "name": "tax", "description": "Tax amount.", "data_type": "float" },
          { "name": "total", "description": "Grand total.", "data_type": "float" },
          { "name": "currency", "description": "ISO currency code.", "data_type": "string" }
        ]
      }
    },
    {
      "id": "validate_1",
      "type": "validate",
      "rules": [
        {
          "id": "not-expired",
          "kind": "deterministic",
          "severity": "error",
          "check": { "type": "date", "field": "invoice_date", "earliest": "2000-01-01", "latest": "today" }
        },
        {
          "id": "totals-add-up",
          "kind": "deterministic",
          "severity": "error",
          "check": { "type": "arithmetic", "operands": ["subtotal", "tax"], "operator": "sum", "equals": "total", "tolerance": 0.01 }
        },
        {
          "id": "known-currency",
          "kind": "deterministic",
          "severity": "warning",
          "check": { "type": "one_of", "field": "currency", "allowed": ["EUR", "USD", "GBP"] }
        },
        {
          "id": "vendor-legit",
          "kind": "ai",
          "severity": "warning",
          "description": "The vendor is a real, named company."
        }
      ]
    }
  ],
  "edges": [
    { "source": "parse_1", "target": "extract_1" },
    { "source": "extract_1", "target": "validate_1" }
  ]
}

Check payloads

{ "type": "range", "field": "amount", "min": 0, "max": null }
// Date bounds: an ISO date "YYYY-MM-DD", "today" (relative), or null.
{ "type": "date", "field": "expiry_date", "earliest": "today", "latest": null }   // not expired
{ "type": "date", "field": "invoice_date", "earliest": "2024-01-01", "latest": "2024-12-31" }
{ "type": "arithmetic", "operands": ["subtotal", "tax"], "operator": "sum", "equals": "total", "tolerance": 0.01 }
{ "type": "comparison", "left": "end_date", "op": ">=", "right": { "source": "field", "field": "start_date" } }
{ "type": "comparison", "left": "year", "op": ">=", "right": { "source": "literal", "value": 2000 } }
{ "type": "one_of", "field": "currency", "allowed": ["EUR", "USD", "GBP"], "case_sensitive": false }
{ "type": "regex", "field": "iban", "pattern": "^[A-Z]{2}\\d{2}" }
{ "type": "required", "field": "vendor_name" }

operator defaults to sum; tolerance to 0; case_sensitive to false. Unset date bounds are null.

Author rules with the SDK

The check classes are exported from the workflow package; pass ValidationRules to .validate().

from anyformat.workflow import (
    Schema, ValidationRule,
    DateCheck, ArithmeticCheck, OneOfCheck,
)

wf = (
    client.workflow("Invoice with checks")
    .parse()
    .extract([
        Schema.date("invoice_date", "Invoice date."),
        Schema.float("subtotal", "Subtotal before tax."),
        Schema.float("tax", "Tax amount."),
        Schema.float("total", "Grand total."),
        Schema.string("currency", "ISO currency code."),
    ])
    .validate(
        ValidationRule(id="not-expired", kind="deterministic", severity="error",
            check=DateCheck(type="date", field="invoice_date", earliest="2000-01-01", latest="today")),
        ValidationRule(id="totals-add-up", kind="deterministic", severity="error",
            check=ArithmeticCheck(type="arithmetic", operands=["subtotal", "tax"], equals="total", tolerance=0.01)),
        ValidationRule(id="known-currency", kind="deterministic", severity="warning",
            check=OneOfCheck(type="one_of", field="currency", allowed=["EUR", "USD", "GBP"])),
        # An AI rule still works the same way:
        ValidationRule(id="vendor-legit", description="The vendor is a real, named company."),
    )
    .create()
)

const wf = await client
  .workflow("Invoice with checks")
  .parse()
  .extract([
    Schema.date("invoice_date", "Invoice date."),
    Schema.float("subtotal", "Subtotal before tax."),
    Schema.float("tax", "Tax amount."),
    Schema.float("total", "Grand total."),
    Schema.string("currency", "ISO currency code."),
  ])
  .validate([
    { id: "not-expired", kind: "deterministic", severity: "error",
      check: { type: "date", field: "invoice_date", earliest: "2000-01-01", latest: "today" } },
    { id: "totals-add-up", kind: "deterministic", severity: "error",
      check: { type: "arithmetic", operands: ["subtotal", "tax"], operator: "sum", equals: "total", tolerance: 0.01 } },
    { id: "known-currency", kind: "deterministic", severity: "warning",
      check: { type: "one_of", field: "currency", allowed: ["EUR", "USD", "GBP"] } },
    { id: "vendor-legit", kind: "ai", description: "The vendor is a real, named company." },
  ])
  .create();

Rules referencing a field by name require that field to exist on the upstream Extract step. The Studio also lets you reference fields you haven’t saved yet by their persistent id — both forms resolve at run time.

Deterministic checks

Build a rule in Studio

Author rules via the API

Check payloads

Author rules with the SDK

What’s next?

Workflow steps

How credits work

​Deterministic checks

​Build a rule in Studio

​Author rules via the API

​Check payloads

​Author rules with the SDK

​What’s next?

Workflow steps

How credits work

Deterministic checks

Build a rule in Studio

Author rules via the API

Check payloads

Author rules with the SDK

What’s next?