Inspect CustomGPT agents, check their knowledge base, and reindex stale pages
Connect CustomGPT.ai and Luumen can read your agents the way you would: project settings, plugin configuration, page metadata, conversation and traffic analytics. When a document in the knowledge base has gone stale, Luumen shows you the page it found and the change it wants to make, then waits for your approval before reindexing.
40 tools: 22 read, 18 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Customgpt 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 — activate persona version, add source to project, clone customgpt project, create conversation, and more — is shown as a plan and requires approval by default, including the 4 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 Customgpt — 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.