Tisane API is a natural language processing tool that detects problematic content, extracts topics, and performs aspect-based sentiment analysis across 27 languages.
Tisane API is a natural language processing tool that detects problematic content, extracts topics, and performs aspect-based sentiment analysis across 27 languages. On Nagent, Tisane is exposed as a fully-configurable artificial intelligence integration that any agent can call — 13 actions, and API key authentication. No code is required to wire Tisane into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Tisane to automate the kinds of tasks artificial intelligence teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Tisane into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Tisane, with input parameters and output schema. Drop these into any step of an agent built in Helix.
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
No publicly available marketplace agent is found using this tool yet. There are 92 agents privately built on Nagent that already use Tisane.
Build on Nagent
Connect Tisane to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Tisane, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Tisane is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Tisane is connected, you configure its 13 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Tisane steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Tisane event fires, the agent kicks off automatically.
Every Tisane action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Tisane ships with 13 pre-built artificial intelligence actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Tisane together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Tisane-based workflows tailored to your business.