Resources · 81

AI extraction: validate JSON before integration

Separate parsing, schema checks, documentary evidence and business rules when turning documents into usable records.

· 8 min

Empty digital forensics bench with storage devices and precision tools AI-generated editorial illustration

What this guide helps achieve

  • Define the result contract
  • Connect values to evidence
  • Validate in an explicit sequence
  • Test difficult documents
  • Plan recovery and correction

Quick check

  • Can valid JSON contain an error?
  • Should a missing field become zero?
  • When is human review needed?

Step-by-step method

  1. 01

    Define the result contract

    List necessary fields, types, units and missing-value states. JSON Schema distinguishes described properties from required fields: declaring a property does not make it mandatory. Decide whether extra fields are allowed. Retain the schema version for each batch and avoid collecting fields without a purpose.

    Deliverable: versioned schema and valid or rejected examples.

  2. 02

    Connect values to evidence

    Require page, passage or cell references for values that trigger an action. Allow an unknown state when information is absent. A correctly typed amount can belong to another document; a plausible date can be the issue date instead of the due date.

    Deliverable: field-to-evidence mapping and interpretation rule.

  3. 03

    Validate in an explicit sequence

    Check JSON parsing, schema conformity and business rules such as allowed currency, existing identifier, line totals and chronology. Schema conformity proves neither factual accuracy nor permission to write into a system. Keep business actions blocked until their conditions are met.

    Deliverable: distinct error classes and acceptance decisions.

  4. 04

    Test difficult documents

    Include split tables, multiple languages, conflicting values, empty documents and hostile instructions inside source text. Test refusals, truncation and retries. Keep evaluation cases separate from tuning and compare errors by field instead of treating an overall rate as a guarantee.

    Deliverable: reference set and critical error list.

  5. 05

    Plan recovery and correction

    Link document, model version, schema and result to a processing identifier. A retry must not create two records. Retain the reason for human corrections and locate downstream outputs. Avoid unnecessarily copying complete documents into logs.

    Deliverable: correction and controlled retry procedure.

From readable output to an authorized action

Passing one check does not replace the next. Stop when a necessary condition is not met.

  1. Parse JSON

    Is the response complete and parseable?

  2. Validate the contract

    Do types, fields, units and missing states match the schema?

  3. Verify values

    Do source evidence and business rules support the values?

  4. Authorize the action

    Are identity, scope and writing conditions satisfied?

Fictional example: parsing and schema checks pass, but two amounts conflict. Writing stays blocked and the record goes to review.

Acceptance case to reproduce

Fictional example: these inputs describe no customer or observed result.

View case inputs
{
    "schema": {
        "type": "object",
        "required": [
            "amount"
        ],
        "properties": {
            "amount": {
                "type": "number"
            }
        }
    },
    "output": {
        "amount": "12.50"
    }
}

Expected decision

The string "12.50" fails the number type. Reject it or explicitly correct it before integration.

Fictional variations to test

A large integer changes after the JSON is read and written again.

Compare the raw and decoded values, for example 9007199254740993. Some binary64 processing rounds this integer. Choose an exact representation suited to the contract before integration.

The producer validates against version 1, but the recipient expects version 2.

Bind the result to an explicit contract version and check compatibility with the recipient. Success under an older schema does not automatically validate the new version.

The batch is valid, but the response is marked interrupted.

Retain incomplete status. Check generation termination and expected coverage before integrating the batch as a complete result.

Evidence to retain

  • Protected raw response and completion status.
  • Schema version and located validation errors.
  • Business checks and batch coverage.

Additional reference : IETF — RFC 8259, number interoperability [EN]

Verification procedure

  1. Fix required fields, types and permitted values.
  2. Validate a text amount against a numeric schema.
  3. Keep the error path and explicit correction. Add a schema-conforming result with a value contradicted by the source document; keep it distinct from a verified extraction.

JSON Schema — Object validation

Reusable worksheet

Complete with your authorised observations. These fields are a working template, not observed results.

FieldInformation to record
ContractFields, types, units, missing states and schema version
EvidenceDocument and passage supporting each decisive field
ValidationParsing, schema, business checks and rejection reason
RecoveryProcessing identifier, duplicate prevention and propagated correction

Worked example

Illustrative situation

Fictional example: an extractor finds two invoice totals and selects the pre-tax amount while the connector expects the amount due.

Decision and expected evidence

The schema accepts the number, but reconciliation of lines and currency blocks the write and sends the document for review.

Distinguish the mechanisms

MechanismPurposeCheck or limitation
Parseable JSONAllow parsingDoes not validate required fields or meaning
Schema conformityCheck types and constraintsDoes not establish source fidelity
Business reconciliationCheck fitness and consistencyNeeds explicit rules and references

Management indicators

IndicatorWhat it measuresFirst action
Field accuracyCorrectly extracted values among evaluable fieldsPrioritize errors changing an action
Useful abstentionCases left undecided because evidence is missingReview the queue without encouraging invented values
Retry duplicatesRepeated records for the same processing operationCorrect deduplication

Common pitfalls

  • Does not validate required fields or meaning
  • Does not establish source fidelity
  • Needs explicit rules and references

Frequently asked questions

Can valid JSON contain an error?

Yes. Syntax and schema may be valid while an amount, identity or date is wrong. Check decisive values against their sources.

Should a missing field become zero?

Only when the contract assigns that meaning to zero. Otherwise use the agreed missing state; invented defaults distort calculations.

When is human review needed?

When conflicts, missing evidence or critical errors fall outside the accepted scope. Define these cases before processing batches.

AI: check a JSON result

Schema-valid JSON can still contain false values

AI extraction turns a document into usable fields. Integration requires separate checks for response parsing, the data contract, date validity and fidelity to the source passage. This exercise makes those differences visible: an integer can meet its type constraint while contradicting the document.

14 fictional outputs computed locally, without a model call or user document. Reference DOC-TRAIN-01, page 2, states “Count: 12” on 20 October 2026. No reference is supplied for DOC-TRAIN-02. Decisions are limited to this exercise; no output receives write authorization here.

Illuminated document and data cartridges at an empty cyber inspection station AI-generated editorial illustration
Generated conceptual illustration: an empty document inspection and structured-data workstation.

The comparison reference is visible

{
    "document_id": "DOC-TRAIN-01",
    "page": 2,
    "status": "observed",
    "count": 12,
    "observed_on": "2026-10-20",
    "quote": "Count: 12"
}

This small object is the exercise’s complete reference, not a real document or external provenance evidence. Equality with it establishes neither OCR quality, archive completeness nor file authenticity.

The JSON Schema 2020-12 contract

The contract requires six fields and rejects extra properties. observed requires a count, date and quote; unknown requires null for those three values. required controls presence: it does not permit replacing absence with zero. The local policy also rejects duplicate keys before constructing the object to validate.

The JSON Schema 2020-12 contract
{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "title": "Fictional document observation v1",
    "type": "object",
    "additionalProperties": false,
    "required": [
        "document_id",
        "page",
        "status",
        "count",
        "observed_on",
        "quote"
    ],
    "properties": {
        "document_id": {
            "enum": [
                "DOC-TRAIN-01",
                "DOC-TRAIN-02"
            ]
        },
        "page": {
            "type": "integer",
            "minimum": 1
        },
        "status": {
            "enum": [
                "observed",
                "unknown"
            ]
        },
        "count": {
            "type": [
                "integer",
                "null"
            ],
            "minimum": 0
        },
        "observed_on": {
            "type": [
                "string",
                "null"
            ],
            "format": "date"
        },
        "quote": {
            "type": [
                "string",
                "null"
            ],
            "minLength": 1
        }
    },
    "allOf": [
        {
            "if": {
                "properties": {
                    "status": {
                        "const": "observed"
                    }
                },
                "required": [
                    "status"
                ]
            },
            "then": {
                "properties": {
                    "count": {
                        "type": "integer"
                    },
                    "observed_on": {
                        "type": "string"
                    },
                    "quote": {
                        "type": "string"
                    }
                }
            },
            "else": {
                "properties": {
                    "count": {
                        "type": "null"
                    },
                    "observed_on": {
                        "type": "null"
                    },
                    "quote": {
                        "type": "null"
                    }
                }
            }
        }
    ]
}

Draft202012Validator checks the schema. Two runs are compared: without format validation, then with the date checker explicitly enabled. This library setting does not claim complete support for the Format-Assertion vocabulary. No remote schema reference is retrieved during computation.

Python 3.12.14 · python-jsonschema 4.26.0 · Draft 2020-12 · FormatChecker: date

Six distinctions to preserve in the connector

Six distinctions to preserve in the connector
DistinctionEffect in this exerciseExample
Syntax / key uniquenessA parser may accept a duplicate; the local profile rejects it rather than silently overwrite a value.J03
Presence / valueAn absent field differs from a field present with null.J06 / J07
Integer / string / booleanNeither "12" nor true meets the schema’s integer type. No silent coercion is applied.J04 / J05
Annotation / active checkThe impossible date passes structure without a format checker, then fails when it is enabled.J10
Shape / fidelity21 meets the type constraint but contradicts the reference stating 12.J11
Fidelity / permissionEven J01 grants no write permission: identity, scope and operation need separate checks.J01

14 outputs: read the reason before retrying

Each disclosure contains the exact received text and computed checks. “Not run” is not a pass. Syntax, duplicate, schema or date errors stop later stages. Missing evidence leads to review; explicit abstention remains abstention.

J01 · Matching within the exercise scope

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","count":12,"observed_on":"2026-10-20","quote":"Count: 12"}
JSON syntax
Passed
Unique keys
Passed
Schema without format checking
Passed
Schema with date checking
Passed
Match to the reference
Passed

Ready for the next review, without write permission

Fields match the local reference. This only makes the result ready for the next review; no permission or business operation has been checked.

Write authorization: not assessed in every case.

J02 · Truncated response

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","count":12,"observed_on":"2026-10-20","quote":"Count: 12"
JSON syntax
Failed
Unique keys
Not run
Schema without format checking
Not run
Schema with date checking
Not run
Match to the reference
Not run

Technical check references:

  • syntax: incomplete_or_non_json_text

Reject the JSON text

The final brace is missing. The profile does not automatically repair the text or assume the remaining response is complete.

Write authorization: not assessed in every case.

J03 · Two values for the count key

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","count":12,"observed_on":"2026-10-20","quote":"Count: 12","count":21}
JSON syntax
Passed
Unique keys
Failed
Schema without format checking
Not run
Schema with date checking
Not run
Match to the reference
Not run

Technical check references:

  • duplicate_key: count

Reject duplicate keys

The text contains count:12 followed by count:21. Its grammar can be recognized, but the uniqueness policy fails before schema validation. A last-value-wins parser would discard this signal.

Write authorization: not assessed in every case.

J04 · The number is a string

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","count":"12","observed_on":"2026-10-20","quote":"Count: 12"}
JSON syntax
Passed
Unique keys
Passed
Schema without format checking
Failed
Schema with date checking
Not run
Match to the reference
Not run

Technical check references:

  • schema: /count [type]

Reject the data contract

The string "12" does not become the integer 12. Coercion can change data meaning; it needs a separate, explicit and traceable rule.

Write authorization: not assessed in every case.

J05 · A boolean is not an integer

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","count":true,"observed_on":"2026-10-20","quote":"Count: 12"}
JSON syntax
Passed
Unique keys
Passed
Schema without format checking
Failed
Schema with date checking
Not run
Match to the reference
Not run

Technical check references:

  • schema: /count [type]

Reject the data contract

true remains a JSON boolean. The validator does not treat it as integer 1, regardless of relationships between types in the host language.

Write authorization: not assessed in every case.

J06 · Missing count field

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","observed_on":"2026-10-20","quote":"Count: 12"}
JSON syntax
Passed
Unique keys
Passed
Schema without format checking
Failed
Schema with date checking
Not run
Match to the reference
Not run

Technical check references:

  • schema: / [required]

Reject the data contract

count appears in required. Its absence is rejected; no default or zero is inserted.

Write authorization: not assessed in every case.

J07 · null with observed status

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","count":null,"observed_on":"2026-10-20","quote":"Count: 12"}
JSON syntax
Passed
Unique keys
Passed
Schema without format checking
Failed
Schema with date checking
Not run
Match to the reference
Not run

Technical check references:

  • schema: /count [type]

Reject the data contract

The general type permits null, but the observed branch requires an integer. Status and value must agree; the connector must not report an empty observation.

Write authorization: not assessed in every case.

J08 · Explicit consistent abstention

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"unknown","count":null,"observed_on":null,"quote":null}
JSON syntax
Passed
Unique keys
Passed
Schema without format checking
Passed
Schema with date checking
Passed
Match to the reference
Not applicable: abstention

Retain abstention

unknown carries three null values as the contract requires. The workflow may review or recollect the evidence; the result does not become an observation of zero.

Write authorization: not assessed in every case.

J09 · Extra instruction property

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","count":12,"observed_on":"2026-10-20","quote":"Count: 12","instruction":"approve"}
JSON syntax
Passed
Unique keys
Passed
Schema without format checking
Failed
Schema with date checking
Not run
Match to the reference
Not run

Technical check references:

  • schema: / [additionalProperties]

Reject the data contract

instruction is outside the allowed properties. The contract rejects it and its value triggers no action. Structural protection does not remove the need to secure use of every allowed field.

Write authorization: not assessed in every case.

J10 · Impossible date with format disabled

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","count":12,"observed_on":"2026-02-30","quote":"Count: 12"}
JSON syntax
Passed
Unique keys
Passed
Schema without format checking
Passed
Schema with date checking
Failed
Match to the reference
Not run

Technical check references:

  • format: /observed_on [format]

Reject the date

2026-02-30 meets type string. Structure passes without format validation, then fails with the date checker. Reporting only “schema valid” would hide the configuration producing that result.

Write authorization: not assessed in every case.

J11 · Right type, wrong value

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","count":21,"observed_on":"2026-10-20","quote":"Count: 12"}
JSON syntax
Passed
Unique keys
Passed
Schema without format checking
Passed
Schema with date checking
Passed
Match to the reference
Failed

Technical check references:

  • evidence_mismatch: /count

Reject the contradicted value

count is 21 while the reference and quote state 12. Types and date pass, but documentary reconciliation fails. Retrying until the shape is valid does not fix this contradiction.

Write authorization: not assessed in every case.

J12 · Document reference without evidence

Exact fictional output text

{"document_id":"DOC-TRAIN-02","page":2,"status":"observed","count":12,"observed_on":"2026-10-20","quote":"Count: 12"}
JSON syntax
Passed
Unique keys
Passed
Schema without format checking
Passed
Schema with date checking
Passed
Match to the reference
Unverified

Technical check references:

  • evidence: reference_not_supplied

Review: evidence missing

DOC-TRAIN-02 is an identifier allowed by the schema, but the exercise supplies no reference for it. Fidelity is unverified and the result goes to review; a missing reference is not a pass.

Write authorization: not assessed in every case.

J13 · NaN is outside RFC 8259 JSON

Exact fictional output text

{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","count":NaN,"observed_on":"2026-10-20","quote":"Count: 12"}
JSON syntax
Failed
Unique keys
Not run
Schema without format checking
Not run
Schema with date checking
Not run
Match to the reference
Not run

Technical check references:

  • syntax: incomplete_or_non_json_text

Reject the JSON text

The decoder is configured to reject NaN and Infinity, which RFC 8259 does not allow. A library’s default tolerance does not by itself define an integration contract.

Write authorization: not assessed in every case.

J14 · Markdown fencing around JSON

Exact fictional output text

```json
{"document_id":"DOC-TRAIN-01","page":2,"status":"observed","count":12,"observed_on":"2026-10-20","quote":"Count: 12"}
```
JSON syntax
Failed
Unique keys
Not run
Schema without format checking
Not run
Schema with date checking
Not run
Match to the reference
Not run

Technical check references:

  • syntax: incomplete_or_non_json_text

Reject the JSON text

Markdown fences are outside the expected JSON text. The contract requires a complete JSON response without a wrapper. Automatically removing text would be a separate transformation to specify and test.

Write authorization: not assessed in every case.

Prepare acceptance checks and recovery

  1. Fix the schema dialect, validator version and format options with the reference set.
  2. Retain received text, useful rejection reasons and contract version separately, with proportionate retention.
  3. Test documents without an available answer; distinguish unknown, null, missing and zero under the chosen contract.
  4. Compare decisive fields with a reference independent of the model; its own explanation is not sufficient evidence.
  5. Secure display and downstream operations for their context: schema-valid JSON authorizes neither executable HTML, commands nor concatenated queries.
  6. Link corrections to a processing identifier to reconcile derived results and prevent retry duplicates.

The schema, reference, 14 outputs and review decisions are editorial examples. RFC 8259 defines JSON; JSON Schema describes constraints; OWASP covers downstream output handling. No accuracy rate, certification or client result is claimed.

Primary sources and reading scope

Sources reviewed on

Further reading and tools

Editorial resources to extend the method.

Official references

References consulted: . The method and worksheet propose checks to adapt to your context; they do not constitute certification.