Read your Wit.ai intents, entities, and traits, then change them with approval
Connect Wit.ai and Luumen can read your apps, intents, entities, traits, and training data whenever you ask. Check what an intent already covers, see which keywords sit under an entity, or run a message through the model to see how it parses. Changes — new intents, keywords, synonyms, training utterances — are previewed and held for your approval before they land.
31 tools: 15 read, 16 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Wit.ai 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 — add entity keyword, add keyword synonym, add value to trait, create wit.ai app, and more — is shown as a plan and requires approval by default, including the 7 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 Wit.ai — 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.