Extract hedging and certainty cues (may, probably, clearly, approximately) from text with offsets

$0.005 USDC per call · Agent infrastructure · POST /api/v1/hedge-extract · Id hedge-extract

Finds hedge and booster cues in an agent's or source's text using a fixed English lexicon (modals, epistemic verbs, adverbs and adjectives, approximators, shield phrases, certainty boosters) plus caller-supplied phrases, and returns each cue with its category, the sentence it sits in, and offsets in UTF-16, code points, UTF-8 bytes and graphemes. Rule-based and English only: a cue is a word match, not a reading of meaning ('may' can be permission); ambiguous cues carry a note. No cue found returns unknown, which is not evidence of certainty. Does not rewrite or score confidence.

What you get

Lets an agent notice that a source said 'may' before reporting 'does'. 100,000 characters per $0.005 call.

Call it

Send the JSON body below to https://agents.writerslogic.com/api/v1/hedge-extract. 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/hedge-extract \
  -H 'content-type: application/json' \
  -d '{"text":"The patch may reduce latency by roughly 20%. It clearly fixes the crash."}'

Input

Field	Type	Required	Description
`text`	string; length 1..100000	yes	Text to scan.
`extraCues`	array<object>; max 50 items	no	Caller cues added to the lexicon.

Example request body

{
  "text": "The patch may reduce latency by roughly 20%. It clearly fixes the crash."
}

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.
`cues`	array<object>; max 500 items	no
`sentences`	array<object>; max 500 items	no	Only sentences that contain a cue.
`truncated`	boolean	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