Read agent, call, and chat config in Retell AI, then change it with approval
Connect Retell AI and your team can ask about voice agents, chat agents, conversation flows, and knowledge bases without opening the dashboard. Look up an agent's current version, check concurrency against your limits, then make the change — add a knowledge base source, run a batch test, start an outbound call — as a previewed step you approve first. Luumen connects with an API key.
67 tools: 28 read, 39 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Retell 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 community voice, add sources to knowledge base, buy a new phone number bind agents, create voice ai agent, and more — is shown as a plan and requires approval by default, including the 10 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 Retell 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.