Rosette Text Analytics
for LuumenAI

Match names and addresses, and identify text language, from the terminal

Ask Rosette Text Analytics about the text in front of you. ROSETTE_TEXT_ANALYTICS_NAME_SIMILARITY and ROSETTE_TEXT_ANALYTICS_ADDRESS_SIMILARITY score whether two records point at the same person, place, or organization. ROSETTE_TEXT_ANALYTICS_LANGUAGE_IDENTIFICATION tells you what language a ticket or log message is in. All three are read-only and answer immediately. Luumen connects with an API key.

The Rosette Text Analytics toolbox

3 tools, all read-only. They answer instantly, and every call is logged.

  • ReadAddress SimilarityCompares two addresses and returns a similarity score.
  • ReadIdentify LanguageThis tool identifies the natural language of a given text.
  • ReadCompare Name SimilarityThe 'Name Similarity' tool compares two entity names (Person, Location, or Organization) and returns a similarity score between 0 and 1 to indicate if the names are similar.

Questions

How does LuumenAI connect to Rosette Text Analytics?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

Can LuumenAI change things in Rosette Text Analytics on its own?

No. Every one of the 3 tools LuumenAI has for Rosette Text Analytics is read-only, so it can answer questions from Rosette Text Analytics but cannot change anything in it. Reads are not gated — they answer immediately, and each one is recorded on the audit trail with the actor and the result.

Who gets access to the integration?

You decide. Access is granted per agent, skill, and team, and per environment — production is not staging.

Is there an audit trail?

Every call to Rosette Text Analytics is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.

Put Rosette Text Analytics to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.