Read call transcripts and agent config, then change voice agents with approval
Connect Synthflow AI and your voice agents stop being a separate console. Pull transcripts, assistant settings, knowledge bases, phone numbers, and simulation results into the terminal while you work. When something needs to change — a new action, an updated knowledge base, a contact attached to a memory store — Luumen shows the call first and waits for your approval.
79 tools: 32 read, 47 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Synthflow 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 document to knowledge base source, attach actions to agent, attach contact to memory store, attach knowledge base to agent, and more — is shown as a plan and requires approval by default, including the 14 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 Synthflow 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.