Query your knowledge graphs, then index new runbooks with approval
Connect Writer and Luumen can read your knowledge graphs, files, and available models from the terminal. Ask a graph a question about a runbook, parse an uploaded PDF, or check which models are on hand. When you want to index a new document or create a graph, Luumen shows the change first and asks before it writes. Authentication is by API key.
23 tools: 16 read, 7 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Writer 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 file to knowledge graph, create knowledge graph, delete file, delete graph, and more — is shown as a plan and requires approval by default, including the 3 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 Writer — 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.