Detects the language of a message, flags abuse types and sentiment, scores text similarity, and paraphrases or translates a passage.
13actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro performs deep linguistic analysis to extract meaning, entities, and sentiment from customer messages. Your team understands not just what customers say, but what they actually need.
Ayro finds how closely related two messages are, even if worded completely differently. Your team matches similar customer issues to existing solutions instantly.
Ayro automatically identifies the language of incoming customer messages. Your team routes multilingual conversations to the right agent without guessing or asking.
Each card is one request a support team gets, and the Tisane actions Ayro runs to close it.
Ayro strips any markup out of the incoming text, identifies its language code, and confirms that language is on Tisane's supported list, so an analysis is not run against something the API cannot read.
Analyze Text returns the abuse types, entities, topics, and aspect-based sentiment it finds, and Ayro can enumerate the valid abuse types and tags first, so a flag arrives with a category rather than a bare score.
Ayro scores the semantic similarity of two fragments from 0 to 1 and compares two person names to decide whether they refer to the same individual, so a duplicate is identified rather than assumed.
Ayro walks up from a concept to its broader parent or down to the narrower ones and lists a lexeme's inflected forms, so a term is matched by meaning rather than by exact spelling.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Tisane actions it has and picks the ones a request needs.
Authorize the Tisane account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Tisane actions that close it and chains as many as the request needs.
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started freeTisane · Ayro
What can you do in Tisane without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Tisane.
Tisane covers 27 languages for detection, sentiment, and abuse analysis, and Get Supported Languages returns the current list with the code for each. Ayro calls it before submitting text, so an unsupported language is caught up front instead of coming back as an empty result.
All 13 actions your agent can call on Tisane, straight from the live MCP connection.
Analyze input text for detailed NLU insights.
Calculate semantic similarity between two text fragments.
Compare two compound named entities and identify differences.
Detect the language of the provided text.
Extract raw text from markup content.
Fetch metadata for a family from Tisane language models, including definition, description, hypernyms, and external references (Wikidata, WordNet).
List all languages supported by the API.
List feature values for a particular category such as entity types, subtypes, abuse types, and tags.
List all hypernyms related to a family.
List all hyponyms related to a family.
Retrieve inflected forms of a specified lexeme within a given language family.
Fetch all senses (meanings) related to a word.
Translate or paraphrase text.
Same connection, same setup. Pick the next one your team already uses.
Reports credit balance and key validity, lists automated and downloaded image batches, prunes old generations, and wires up print event webhooks.
Searches the toolkit catalogue for the right action, walks users through authorising accounts, executes tools singly or in batches, and enables triggers.
Generates text, speech, images, and Veo video from a prompt, embeds text for semantic search, and counts tokens before a call is made.
Submits documents for conversion, tracks the job by its whisper hash, retrieves the extracted text, and manages the callback webhooks.
Retrieves the passages that answer a query, ingests documents from files, URLs or raw text, and keeps the indexed material current.
Drafts product titles, social posts, emails, and video descriptions, then summarizes or translates them across 72+ languages.

Authorize the account and your agent has all 13 actions from the first conversation.
