Read research projects, notes, and insights, then write findings back with approval
Connect Dovetail and Luumen can read your research workspace directly in the terminal — projects, notes, docs, data items, and published insights. Ask what a round of interviews said about onboarding, or pull a doc as Markdown for a postmortem. When something needs writing back, like a new insight or a project for the next study, Luumen shows the change first and asks before it runs. Authentication is by API key.
51 tools: 25 read, 26 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Dovetail 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 channel, create contact, create data, create data point, and more — is shown as a plan and requires approval by default, including the 6 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 Dovetail — 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.