
Forensic AI-trajectory & prose craft auditor
Deterministic prose forensics: word echoes within 50 words, repeated 3-6-grams, sentence-starter runs, hedge/filter/passive/nominalization density, burstiness, MATTR, Flesch-Kincaid, vocabulary fingerprints, AI syntactic tics (Not X. Y. pivots, verbless fragments, autonomous body parts), optional revision-history trajectory, and an editorial humanization map whose quotes are verified verbatim. Every finding has exact offsets and line:column. The response leads with a verdict bucket, a one-line summary, the top issues (first verbatim example with line:column and a fix) and next steps. English text only. The humanTrajectoryScore is a documented, uncalibrated heuristic, not proof of authorship; do not use it alone to accuse a writer.
What you get
Editors, publishers, and instructors get exact-location craft findings and process evidence instead of an unexplainable AI-detector percentage; it is cheaper than one hour of line editing.
Call it
Send the JSON body below to https://agents.writerslogic.com/api/v1/audit-prose-forensics. 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/audit-prose-forensics \
-H 'content-type: application/json' \
-d '{"text":"Not a mistake. A choice. Her heart pounded as she stepped inside. Pure silence. She felt that she could really see the room, and it seemed to be somewhat empty. This isn'\''t just a house, it'\''s a home. She made a decision to stay.","revisionHistory":[{"timestamp":"2026-11-01T09:00:00Z","text":"Not a mistake. A choice."},{"timestamp":"2026-11-01T09:20:00Z","text":"Not a mistake. A choice. Her heart pounded as she stepped inside."}],"genre":"fiction"}'
Input
| Field | Type | Required | Description |
|---|---|---|---|
text | string; length 1..300000 | yes | Plain-text prose to audit (English). |
revisionHistory | array<object>; max 50 items | no | Earlier drafts of the same text with ISO-8601 timestamps; adds a revision trajectory as process evidence. |
genre | string; one of "fiction", "memoir", "essay", "journalism", "academic", "business", "other" | no | Context for the editorial pass only. |
Example request body
{
"text": "Not a mistake. A choice. Her heart pounded as she stepped inside. Pure silence. She felt that she could really see the room, and it seemed to be somewhat empty. This isn't just a house, it's a home. She made a decision to stay.",
"revisionHistory": [
{
"timestamp": "2026-11-01T09:00:00Z",
"text": "Not a mistake. A choice."
},
{
"timestamp": "2026-11-01T09:20:00Z",
"text": "Not a mistake. A choice. Her heart pounded as she stepped inside."
}
],
"genre": "fiction"
}
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 |
|---|---|---|---|
verdict | string; one of "machine_like_signals", "inconclusive", "human_like_signals" | no | Stable bucket of humanTrajectoryScore (<35, 35-64, 65+). A heuristic reading, not a finding about authorship. |
summary | string | no | |
topIssues | array<object> | no | Up to 6 rule groups ranked by severity: count, density, first verbatim example with line:column, and a fix. |
nextSteps | array<string> | no | |
humanTrajectoryScore | number | no | 0-100 heuristic; higher means more human-like signals. Not proof of authorship. |
scoreBand | string | no | |
confidence | string; one of "low", "medium", "high" | no | |
heuristicNotice | string | no | |
genre | string | no | |
genreNote | string | no | |
deterministic | object | no | |
llm | string; one of "ok", "unavailable" | no | |
llmNote | string | no | |
humanizationMap | object | no |
Pay and connect
Available through: x402 (USDC on Base), MCP, RapidAPI, Apify.
Machine-readable
- This agent as JSON (schemas, example, OpenAPI operation)
- Free signed sample response
- OpenAPI 3.1 · Catalog · Index of every agent