Denkwerk
instruction compliance
Implements the 25 verifiable instruction types of IFEval (Zhou et al. 2023, "Instruction-Following Evaluation for Large Language Models", reference code google-research/instruction_following_eval, Apache-2.0) with the same type ids, argument names and checks (regexes for bullets, highlights, sections, paragraphs, placeholders, postscripts; \w+ word count; JSON with code fences stripped), plus extensions x:json_schema (Ajv, draft 2020-12), x:number_characters, x:markdown_headings,.
POST https://denk.halowerk.com/v1/instruction-complianceInputs
| Field | Type | Required | Description |
|---|---|---|---|
| response | string | Yes | The model response to check. |
| instructions | array | Yes |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"required": [
"response",
"instructions"
],
"properties": {
"response": {
"type": "string",
"maxLength": 200000,
"description": "The model response to check."
},
"instructions": {
"type": "array",
"minItems": 1,
"maxItems": 50,
"items": {
"type": "object",
"additionalProperties": false,
"required": [
"type"
],
"properties": {
"type": {
"type": "string",
"enum": [
"keywords:existence",
"keywords:frequency",
"keywords:forbidden_words",
"keywords:letter_frequency",
"language:response_language",
"length_constraints:number_sentences",
"length_constraints:number_paragraphs",
"length_constraints:number_words",
"length_constraints:nth_paragraph_first_word",
"detectable_content:number_placeholders",
"detectable_content:postscript",
"detectable_format:number_bullet_lists",
"detectable_format:constrained_response",
"detectable_format:number_highlighted_sections",
"detectable_format:multiple_sections",
"detectable_format:json_format",
"detectable_format:title",
"combination:two_responses",
"combination:repeat_prompt",
"startend:end_checker",
"startend:quotation",
"change_case:capital_word_frequency",
"change_case:english_capital",
"change_case:english_lowercase",
"punctuation:no_comma",
"x:json_schema",
"x:number_characters",
"x:markdown_headings",
"x:numbered_list_items",
"x:starts_with",
"x:regex",
"x:max_sentence_words",
"x:sections_present"
],
"description": "IFEval instruction id or x: extension."
},
"keywords": {
"type": "array",
"minItems": 1,
"maxItems": 50,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 200
}
},
"keyword": {
"type": "string",
"minLength": 1,
"maxLength": 200
},
"frequency": {
"type": "integer",
"minimum": 0,
"maximum": 1000000
},
"relation": {
"type": "string",
"enum": [
"less than",
"at least",
"at most",
"exactly"
],
"description": "IFEval types accept \"less than\" and \"at least\"."
},
"forbidden_words": {
"type": "array",
"minItems": 1,
"maxItems": 100,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 100
}
},
"letter": {
"type": "string",
"minLength": 1,
"maxLength": 1
},
"let_frequency": {
"type": "integer",
"minimum": 0,
"maximum": 1000000
},
"let_relation": {
"type": "string",
"enum": [
"less than",
"at least"
]
},
"language": {
"type": "string",
"pattern": "^[a-z]{2,3}$",
"description": "ISO 639-1 or 639-3 code."
},
"num_sentences": {
"type": "integer",
"minimum": 0,
"maximum": 100000
},
"num_paragraphs": {
"type": "integer",
"minimum": 0,
"maximum": 100000
},
"num_words": {
"type": "integer",
"minimum": 0,
"maximum": 1000000
},
"nth_paragraph": {
"type": "integer",
"minimum": 1,
"maximum": 10000
},
"first_word": {
"type": "string",
"minLength": 1,
"maxLength": 100
},
"num_placeholders": {
"type": "integer",
"minimum": 0,
"maximum": 10000
},
"postscript_marker": {
"type": "string",
"minLength": 1,
"maxLength": 20
},
"num_bullets": {
"type": "integer",
"minimum": 0,
"maximum": 10000
},
"options": {
"type": "array",
"minItems": 1,
"maxItems": 20,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 200
}
},
"num_highlights": {
"type": "integer",
"minimum": 0,
"maximum": 10000
},
"section_spliter": {
"type": "string",
"minLength": 1,
"maxLength": 40
},
"num_sections": {
"type": "integer",
"minimum": 0,
"maximum": 10000
},
"prompt_to_repeat": {
"type": "string",
"minLength": 1,
"maxLength": 20000
},
"end_phrase": {
"type": "string",
"minLength": 1,
"maxLength": 500
},
"capital_frequency": {
"type": "integer",
"minimum": 0,
"maximum": 1000000
},
"capital_relation": {
"type": "string",
"enum": [
"less than",
"at least"
]
},
"schema": {
"type": "object",
"description": "x:json_schema: JSON Schema (draft 2020-12 compatible)."
},
"num_characters": {
"type": "integer",
"minimum": 0,
"maximum": 10000000
},
"num_headings": {
"type": "integer",
"minimum": 0,
"maximum": 10000
},
"num_items": {
"type": "integer",
"minimum": 0,
"maximum": 10000
},
"start_phrase": {
"type": "string",
"minLength": 1,
"maxLength": 500
},
"pattern": {
"type": "string",
"minLength": 1,
"maxLength": 500,
"description": "x:regex: RE2 pattern."
},
"must_match": {
"type": "boolean",
"default": true
},
"max_words": {
"type": "integer",
"minimum": 1,
"maximum": 10000
},
"sections": {
"type": "array",
"minItems": 1,
"maxItems": 50,
"items": {
"type": "string",
"minLength": 1,
"maxLength": 200
}
}
}
}
}
}
}Published input example
{
"response": "* apples\n* pears\n* plums",
"instructions": [
{
"type": "detectable_format:number_bullet_lists",
"num_bullets": 3
},
{
"type": "punctuation:no_comma"
}
]
}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