Read meaning out of incident text, and manage the dictionaries behind it
TextRazor turns free text into structured signal. Point Luumen at a stream of tickets, postmortems, or alert descriptions and it extracts entities, classifies topics, and runs a full analysis pass in one step. When the extraction misses your internal service names, Luumen can update the custom dictionaries and classifiers behind it as an approved change.
6 tools: 4 read, 2 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed TextRazor run looks like inside Luumen.
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — manage custom classifiers, dictionary manager — is shown as a plan and requires approval by default, including the 2 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to TextRazor — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Connect in minutes. Every action scoped, approved, and audited from day one.