Read Humanloop experiments and sessions, then create projects as approved steps
Connect Humanloop with an API key and Luumen can read your prompt experiments and session history whenever you ask. Check which experiments are running on a project, page through recent sessions, and set up a new project when the work needs its own home. Project creation and deletion are previewed and held for your approval by default.
4 tools: 2 read, 2 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Humanloop 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 — create project, delete project — is shown as a plan and requires approval by default, including the 1 action 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 Humanloop — 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.