Read your Bolna voice agents and call history, then place calls as approved steps
Connect Bolna and Luumen can read your voice agent configurations, phone numbers, voices, providers, knowledgebases, and past call executions with transcripts and costs. Ask what an agent is set up to do or why a call ended the way it did, and get an answer from the account itself. Changes — creating agents, uploading batches, placing outbound calls — are previewed before they run.
33 tools: 16 read, 17 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Bolna 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 provider to bolna, copy bolna agent, create bolna voice ai agent (v2), create bolna batch, and more — is shown as a plan and requires approval by default, including the 6 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 Bolna — 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.