This≠That™ Meaning Comparision API

:: This≠That™ Meaning Comparision API — Documentation

: Overview

This≠That™ is a semantic intent evaluation API designed to determine whether two artefacts are meaningfully equivalent or materially different. It evaluates intent stability, not surface similarity .

This≠That is suited for workflows where subtle wording or structural shifts may alter obligation, scope, safety posture, or authority.

It does not generate content. It evaluates semantic continuity under comparison. The API is deterministic within bounded inputs.

: Typical Use Cases

This≠That provides semantic compare under constraint. It answers questions such as:

Policy and contract revision review.
Code permission boundary changes.
AI-generated output verification.
Safety constraint comparison.
Spec or product requirement validation.
Agent instruction stability checks.
"Is this intent substitution acceptable / allowed under defined rules?"

: Getting Started

Review the request / response schema
Provide two artefacts for comparison
Inspect the evaluation result and receipt

: Basic Usage

➤ This≠That API is accessed via a single POST endpoint. It accepts two artefacts and returns a semantic evaluation result with receipt metadata.

Endpoint

POST https://api.maenen.ai/v1/maenen/this-vs-that

Request Headers

Header	Description
`Authorization`	`API key using Bearer format`
`Accept`	`application/json`
`Content-Type`	`application/json`

Request Body (basic)


{

 "this": "Original artefact text or structured content",

 "that": "Modified or alternative artefact",

 "options": {

  "mode": "default"

 }

}

➤ this — May be text, structured policy, code, or specification.

➤ that — The comparison artefact. Must correspond in scope to the original input.

➤ options — Optional configuration object. Defaults are bounded and deterministic.

: Response (success)

➤ A successful response returns a structured semantic evaluation and receipt.

Endpoint

{

 "evaluation": {

  "equivalence": "materially_different",

  "confidence": "bounded",

  "summary": "Obligation weakened from mandatory to optional"

 },

 "receipt": {

  "status": "verified",

  "determinism": "stable",

  "scope": "bounded",

  "receipt_id": "tnt_..."

 }

}

Evaluation Fields

Field	Description
`equivalence`	`equivalent` -or- `materially_different`
`confidence`	Bounded evaluation indicator
`summary`	High-level explanation of detected shift

— The summary output offered provides interpretive guidance. It does not rewrite or alter the inputs.

: The Receipt

This≠That returns a receipt documenting the evaluation boundary and determinism.

Receipt Fields (High-Level)

Field	Description
`status`	Verification result
`determinism`	Deterministic outcome indicator
`scope`	Evaluation boundary classification
`warnings`	Optional non-fatal notices
`receipt_id`	Unique identifier

Example (redacted)


{
 "receipt": {

  "status": "verified",

  "determinism": "stable",

  "scope": "bounded",

  "warnings": [],

  "receipt_id": "tnt_…"

 }

}

Receipts are suitable for:

Audit & compliance review
Pipeline debugging
Agent chain validation
Governance workflows

: Failure Response Examples

This≠That uses explicit, bounded error responses. Failures do not return partial evaluation results.

❌ Invalid Request


{
 "error": {

  "code": "invalid_request",

  "message": "Malformed comparison payload""

 }

}

❌ Scope Mismatch


{
 "error": {

  "code": "scope_mismatch",

  "message": "Inputs are not comparable within bounded evaluation scope"

 }

}

❌ Input Exceeds Limits


{
 "error": {

  "code": "input_limit_exceeded",

  "message": "Input size exceeds allowed limits

 }

}

❌ Authentication Error


{
 "error": {

  "code": "unauthorized",

  "message": "Invalid or missing API key"

 }

}

: Limits & Guardrails

This≠That enforces strict evaluation boundaries.

Input Limits

Maximum input size enforced
Structured validation prior to processing
Rejection of malformed payloads

Processing Guardrails

Bounded semantic scope
Deterministic evaluation
No generation or rewriting
No external data access

Output Characteristics

Stable structure
No hidden fields
No silent mutation
No adaptive variation across identical inputs

: Privacy & Data Handling

This≠That is designed with minimal data exposure.

Inputs are processed ephemerally
No training on customer data
No secondary use of payloads
No cross-request retention

Receipts may be stored by clients for audit or compliance purposes. For full details, see the Maenen privacy policy.

: Capability Scoping

Some API capabilities are gated by key scope. Keys without the requisite scope will receive:

403 capability_not_permitted

: Edge Rate Enforcement

Rate limits are applied at the network edge (via NGINX). Excess traffic will receive:

429 Too Many Requests

These limits are distinct from usage ceilings and do not imply SLA guarantees.

: Support

For technical issues or questions, contact support via the site. Note that during beta trial, full support and any SLA is not offered, though your query or comment will be carefully considered. Please include:

A short description of the issue
Example payloads (if possible)
The receipt from the relevant request

- Receipts significantly reduce back-and-forth and speed up diagnosis.

: Beta Notes

This API is currently in limited beta.

Supported modes and limits may evolve.
No uptime or performance guarantees are implied.
Breaking changes will be communicated ahead of time where possible.

: Versioning

This documentation applies to:

API version: v0.1 (beta)

FOR-THE-DREAM-IS-WITH-INTEGRITY-FOR-THE-FREEDOM-OF-INTELLIGENCE