Parallel
for LuumenAI

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.

The Parallel toolbox

32 tools: 21 read, 11 write. Reads answer instantly. Writes require approval by default. Everything is logged.

  • ReadCreate Chat CompletionsGet realtime chat completions from Parallel AI.
  • ReadExtract Content from URLsExtract relevant content from specific web URLs.
  • ReadFetch Task Group RunsRetrieve task runs from a Task Group as a resumable stream.
  • ReadGet FindAll Run ResultFetch the final (or latest available) FindAll candidates and result payload for a run.
  • ReadGet FindAll Run SchemaRetrieve the schema configuration of a FindAll run by findall_id.
  • ReadIngest FindAll RunTransform a natural language search objective into a structured FindAll specification.
  • ReadList Monitor EventsList events for a monitor from up to the last 300 event groups.
  • ReadList MonitorsList active monitors for the user.
  • ReadRetrieve Event GroupRetrieve an event group for a monitor.
  • ReadRetrieve FindAll Run StatusRetrieve status and metadata for a FindAll run by findall_id.
  • ReadRetrieve MonitorRetrieve a specific monitor by ID.
  • ReadRetrieve Task GroupRetrieve details of a specific task group.
  • ReadRetrieve Task Group RunRetrieve run status by run_id for a task group.
  • ReadRetrieve Task RunRetrieve run status by run_id.
  • ReadRetrieve Task Run InputRetrieve the input data of a specific task run by run_id.
  • ReadRetrieve Task Run ResultRetrieve the result of a task run by run_id, blocking until the run completes.
  • ReadParallel SearchPerform parallel semantic search.
  • ReadStream FindAll EventsStream events from a FindAll run.
  • ReadStream Task Group EventsStream events for a Task Group.
  • ReadStream Task Run EventsStream events for a Task Run.
  • ReadSuggest TaskSuggest tasks based on user intent.
  • WriteAdd Enrichment to FindAll RunAdd an enrichment to a FindAll run. Approval by default
  • WriteAdd Runs to Task GroupInitiate multiple task runs within a TaskGroup. Approval by default
  • WriteCancel FindAll RunCancel an active FindAll run by findall_id. Approval by default
  • WriteCreate MonitorCreate a web monitor that periodically runs the specified query. Approval by default
  • WriteCreate Task GroupCreate a new task group. Approval by default
  • WriteCreate Task RunCreate and initiate a task run. Approval by default
  • WriteDelete MonitorDelete a monitor, stopping all future executions. Approval by default
  • WriteExtend FindAll RunExtend a FindAll run by adding additional matches to the current match limit. Approval by default
  • WriteStart FindAll RunStart a FindAll run. Approval by default
  • WriteSimulate EventSimulate sending an event for a monitor. Approval by default
  • WriteUpdate MonitorUpdate a monitor's configuration. Approval by default

One prompt, start to finish

What a governed Parallel run looks like inside Luumen.

Questions

How does LuumenAI connect to Parallel?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

Can LuumenAI change things in Parallel on its own?

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.

Who gets access to the integration?

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.

Is there an audit trail?

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.

Put Parallel to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.