Denkwerk
answer completeness
For each required point the answer is searched sentence by sentence (and in windows of two adjacent sentences). keywords: every keyword group must occur (any alternative of a group, case-insensitive, whole words). lexical (default): share of the point's content terms found in the best window (Unicode word segmentation (ICU), NFKC, Snowball stop words removed (de/en), German CISTEM stemmer (Weißweiler & Fraser 2017) or English S-stemmer (Harman 1991); numbers kept as terms with decimal comma.
POST https://denk.halowerk.com/v1/answer-completenessInputs
| Field | Type | Required | Description |
|---|---|---|---|
| answer | string | Yes | The answer to check. |
| required_points | array | Yes | Points the answer must cover. |
| method | string | No | |
| language | string | No | Language for stop words and stemming (lexical method). |
| lexical_threshold | number | No | |
| semantic_threshold | number | No | Cosine threshold for intfloat/multilingual-e5-small (heuristic; related pairs typically score 0.80-0.90, unrelated 0.65-0.75). |
| require_numbers | boolean | No | Lexical method: numbers in a point must occur in the evidence window. |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"required": [
"answer",
"required_points"
],
"properties": {
"answer": {
"type": "string",
"minLength": 1,
"maxLength": 100000,
"description": "The answer to check."
},
"required_points": {
"type": "array",
"minItems": 1,
"maxItems": 50,
"description": "Points the answer must cover.",
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"point"
],
"properties": {
"id": {
"type": "string",
"maxLength": 64
},
"point": {
"type": "string",
"minLength": 1,
"maxLength": 1000,
"description": "The point in a few words or one sentence."
},
"keywords": {
"type": "array",
"minItems": 1,
"maxItems": 20,
"description": "Optional keyword groups; a group is a string or an array of alternatives. If given, all groups must occur.",
"items": {
"anyOf": [
{
"type": "string",
"minLength": 1,
"maxLength": 100
},
{
"type": "array",
"minItems": 1,
"maxItems": 20,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 100
}
}
]
}
},
"weight": {
"type": "number",
"exclusiveMinimum": 0,
"maximum": 100,
"default": 1
}
}
}
},
"method": {
"type": "string",
"enum": [
"lexical",
"embedding",
"both"
],
"default": "lexical"
},
"language": {
"type": "string",
"enum": [
"auto",
"de",
"en"
],
"default": "auto",
"description": "Language for stop words and stemming (lexical method)."
},
"lexical_threshold": {
"type": "number",
"minimum": 0.1,
"maximum": 1,
"default": 0.6
},
"semantic_threshold": {
"type": "number",
"minimum": 0.5,
"maximum": 1,
"default": 0.8,
"description": "Cosine threshold for intfloat/multilingual-e5-small (heuristic; related pairs typically score 0.80-0.90, unrelated 0.65-0.75)."
},
"require_numbers": {
"type": "boolean",
"default": true,
"description": "Lexical method: numbers in a point must occur in the evidence window."
}
}
}Published input example
{
"answer": "The standard VAT rate in Germany is 19 percent. Food is taxed at 7 percent.",
"required_points": [
{
"id": "standard",
"point": "standard rate 19 percent"
},
{
"id": "reduced",
"point": "reduced rate 7 percent"
},
{
"id": "books",
"point": "books are taxed at 7 percent"
}
]
}Result & documentation
Machine-readable documentation of this hub
Source of this page: the published HALOWERK catalog. Updated: 2026-11-17 UTC.
More endpoints in this hub
- Denkwerk0.003 USDC
agent card generate
POSThttps://denk.halowerk.com/v1/agent-card-generateBuilds an Agent2Agent protocol Agent Card with protocolVersion, name, description, url, version, capabilities, default input/output modes and skills. Skills come from the supplied list or are derived from OpenAPI operations (operationId, su
- Denkwerk0.003 USDC
agent permission diff
POSThttps://denk.halowerk.com/v1/agent-permission-diffTakes the tool names (with optional descriptions) and permission scopes of an agent before and after a change and reports added and removed tools and scopes, classifies new capabilities by risk (payments, sending messages, deleting or writi
- Denkwerk0.003 USDC
annotation guide draft
POSThttps://denk.halowerk.com/v1/annotation-guide-draftTakes example texts per label and derives, without a language model, the most distinguishing terms per label (TF-IDF contrast against the other labels), representative examples, cross-label example pairs with high similarity that need a wri