Check that numbers, units, part numbers, tolerance signs, dates, placeholders and URLs survive translation
For aligned source and target segments, extracts the tokens a translation must not change (numbers with attached units or %, ISO dates, part numbers and versions, tolerance and comparison operators such as ± ≤ ≥, placeholders like {0} or %s, URLs and emails) and reports any that are missing, added or altered, with offsets in both texts in UTF-16, code points, UTF-8 bytes and graphemes. Numbers are compared by value across decimal and thousands conventions (1,234.5 vs 1.234,5), digits of other scripts count as ASCII digits, and a separator that could be either is reported as ambiguous unless sourceDecimal/targetDecimal says which. Does not read number words, check grammar or translate; units are compared only when attached to the number or a symbol such as %.
What you get
Catches the dropped decimal, the lost ± and the broken placeholder before a translation ships. 200 segments per $0.005 call.
Call it
Send the JSON body below to https://agents.writerslogic.com/api/v1/translation-invariants. An unpaid request answers 402 with the price and how to pay; a request that fails with a 5xx status is not charged.
curl -i -X POST https://agents.writerslogic.com/api/v1/translation-invariants \
-H 'content-type: application/json' \
-d '{"segments":[{"id":"s1","source":"Tighten to 25 Nm ±2 (part PN-4471-B), see https://x.example/a.","target":"Mit 25 Nm anziehen (Teil PN-4471-B), siehe https://x.example/a."}],"targetDecimal":","}'
Input
| Field | Type | Required | Description |
|---|---|---|---|
segments | array<object>; max 200 items | yes | Up to 200; 100000 characters in total. |
sourceDecimal | string; one of ".", ",", "auto" | no | Decimal mark of the source locale. Default auto (both readings tried). |
targetDecimal | string; one of ".", ",", "auto" | no | Decimal mark of the target locale. Default auto. |
kinds | array<string; one of "number", "identifier", "operator", "placeholder", "url", "date">; max 6 items | no | Token kinds to check. Default all. |
Example request body
{
"segments": [
{
"id": "s1",
"source": "Tighten to 25 Nm ±2 (part PN-4471-B), see https://x.example/a.",
"target": "Mit 25 Nm anziehen (Teil PN-4471-B), siehe https://x.example/a."
}
],
"targetDecimal": ","
}
Result
The response is { "data": ..., "_provenance": ... }. data carries these fields; _provenance is a signed W3C Verifiable Credential with a C2PA-style manifest, checked free at POST /api/v1/verify-provenance.
| Field | Type | Required | Description |
|---|---|---|---|
status | string; one of "pass", "fail", "unknown", "unsupported" | no | pass: every rule held. fail: a rule was violated (see witnesses). unknown: the input lacks the evidence to decide. unsupported: outside what this engine covers. Missing evidence is never a pass. |
segments | array<object>; max 200 items | no | |
witnesses | array<object> | no | |
versions | object | no | Every semantic dependency of this answer (engine, tables and their as-of dates, tokenizer, calendar, rounding profile). |
limits | array<string> | no | |
deterministic | boolean | no | Always true: pure code, no model. |
Pay and connect
Available through: x402 (USDC on Base), MCP. MCP clients reach it through the context-evidence-kit package.
Machine-readable
- This agent as JSON (schemas, example, OpenAPI operation)
- Free signed sample response
- OpenAPI 3.1 · Catalog · Index of every agent