Send approval requests to a named group of humans, and read back their answers
HITL.sh holds a decision open until a person answers it. Connect it and Luumen can see your approval loops, check who is actually active in each one, and broadcast a request to them. The response comes back as structured data, so a runbook can wait on a named human instead of a guess. Connected with an API key.
10 tools: 5 read, 5 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Human Approval - HITL Platform 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 — cancel approval request, create approval request, create loop, delete loop, and more — is shown as a plan and requires approval by default, including the 2 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 Human Approval - HITL Platform — 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.