NagentArtefacts
Dev & Technology
Enterprise and White Glove
Company
Tisane connects to a Nagent workspace with an API key. Once it is connected, agents can call 13 Tisane actions, such as "Get Family Details", "Get Supported Languages" and "List Feature Values". Nothing is enabled on connect: each action is allowed one at a time, and an action with side effects runs or waits for a person according to the agent's level.
Every operation an agent can call against Tisane, with input parameters and output schema.
TISANE_ANALYZE_TEXTTool to analyze input text for detailed NLU insights. Use after preparing text when you need to detect sentiment, entities, topics, and other linguistic features.
Input parameters
Text content to be analyzed
IETF BCP-47 language tag for the input text
Optional analysis settings. Empty dict for defaults (see Tisane API Configuration Guide).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_CALCULATE_SIMILARITYTool to calculate semantic similarity between two text fragments. Use when you need a numeric similarity score (0-1) for two texts.
Input parameters
First text fragment to compare.
Second text fragment to compare.
Additional settings for similarity calculation, leave empty for defaults.
IETF language code for content1 (e.g., 'en').
IETF language code for content2 (e.g., 'en').
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_COMPARE_ENTITIESTool to compare two compound named entities and identify differences. Currently only supports person entity type. Use when you need to determine if two person names refer to the same individual or identify specific differences.
Input parameters
The entity type to compare. Currently only 'person' is supported.
The first entity to compare.
The second entity to compare.
IETF language tag for the first entity (e.g., 'en', 'fr').
IETF language tag for the second entity (e.g., 'en', 'fr').
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_DETECT_LANGUAGETool to detect the language of the provided text. Use when you need to identify the language code.
Input parameters
The text whose language needs to be detected.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_EXTRACT_TEXTTool to extract raw text from markup content. Use when cleaning HTML, CSS, JS, or JSON to get pure decoded text. Use after confirming the input is UTF-8 text; this does not process binary content.
Input parameters
The markup (HTML, CSS, JS, JSON) to strip and decode into plain text. Must be UTF-8 text; binary content is not supported.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_GET_FAMILY_DETAILSTool to fetch metadata for a family from Tisane language models, including definition, description, hypernyms, and external references (Wikidata, WordNet). Use when you need detailed information about a specific family concept by its numeric identifier.
Input parameters
Numeric identifier of the family to retrieve details for
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_GET_SUPPORTED_LANGUAGESTool to list all languages supported by the API. Use when needing to discover available languages for text analysis or processing. Call before submitting text to ensure support.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_LIST_FEATURE_VALUESTool to list feature values for a particular category such as entity types, subtypes, abuse types, and tags. Use when you need to discover valid values for a specific feature category before analysis or filtering.
Input parameters
Feature type category to query. Must be one of: Grammar, Style, or Semantics
IETF language code for which to retrieve feature values (e.g., 'en', 'fr', 'es')
Feature list name (localized) to retrieve values for. Examples: 'tense', 'mood', 'entity_type', 'abuse_type'
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_LIST_HYPERNYMSTool to list all hypernyms related to a family. A hypernym is a parent concept (e.g., vehicle is a hypernym of truck). Use when you need to understand the conceptual hierarchy or broader categories for a given family ID.
Input parameters
Numeric identifier of the family to retrieve hypernyms for
Maximum distance from the family. Determines how many levels of hypernyms to retrieve
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_LIST_HYPONYMSTool to list all hyponyms related to a family. A hyponym is a child concept (e.g., 'truck' is a hyponym of 'vehicle'). Use when you need to discover more specific concepts within a semantic family.
Input parameters
Numeric identifier of the family to retrieve hyponyms for
Maximum distance (depth level) from the family to retrieve hyponyms
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_LIST_INFLECTIONSTool to retrieve inflected forms of a specified lexeme within a given language family. Use when you need to get all grammatical variants of a word.
Input parameters
The family identifier to inspect (numeric ID as string)
The lexeme identifier to inspect (numeric ID as string)
The language code (IETF BCP-47 format, e.g., 'en', 'ru')
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_LIST_WORD_SENSESTool to fetch all senses (meanings) related to a word. Use when you need to explore word definitions, families, features, and lemma information for linguistic analysis.
Input parameters
The word to inspect and retrieve senses for
Standard culture code (ISO-639 language code with optional country extension, e.g., 'en', 'fr', 'es')
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TISANE_TRANSFORM_TEXTTool to translate or paraphrase text. Use when you need to convert content between languages or paraphrase within the same language.
Input parameters
Target language IETF tag. If same as source, text will be paraphrased.
Source language IETF tag. Use '*' or 'lang1\\ | lang2' to auto-detect.
Text content to transform (UTF-8).
Optional translation settings (see Tisane API Configuration).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
Agents can call 13 Tisane actions on Nagent, including "Get Family Details", "Get Supported Languages" and "List Feature Values". Get Family Details: Fetch metadata for a family from Tisane language models, including definition, description, hypernyms, and external references (Wikidata, WordNet). Each action is listed on this page with its input parameters and its output.
Tisane connects with an API key, under your workspace's own connection. Nothing is enabled on connect: each action is allowed one at a time and can be scoped to the agents that need it.
Get Family Details takes 1 required input: id. It returns data, error and successful.