Read Breeze projects and cards for context, then file the work as an approved step.
Connect Breeze and the agent can see how work is actually tracked: active projects, the cards in each one, who is on the team, and which stage a task sits in. When something needs to be written down — a follow-up card from an incident, a new stage, a person added to a project — the agent shows the change first and waits for your approval. Authentication is by API key.
18 tools: 7 read, 11 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Breeze 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 project people, archive project, create card, create_list, 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 Breeze — 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.