Structured web research and standing monitors, run from the terminal
Parallel turns a plain-language research question into schema-compliant output. Connect it and Luumen can read existing monitors, task groups, and FindAll results for context, then start new runs or set up a monitor when you ask. Useful for vendor checks, incident background, and tracking pages that matter to your change calendar. Authentication is by API key.
32 tools: 21 read, 11 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Parallel 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 enrichment to findall run, add runs to task group, cancel findall run, create monitor, 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 Parallel — 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.