Pipeless Recommendations
for LuumenAI

Read activity feeds and recommendations, then record events as approved steps

Pipeless turns your application event data into activity feeds and personalized recommendations. Connect it and Luumen can read recent events, walk an object's incoming and outgoing activity, and pull the recommendations or follow suggestions a given object would see. When a backfill or correction is needed, Luumen records the events for you as a previewed step.

Book a DemoDownload Luumen

The Pipeless Recommendations toolbox

10 tools: 7 read, 3 write. Reads answer instantly. Writes require approval by default. Everything is logged.

  • ReadList Activity FeedReturn one cursor-controlled chronological page of actions by objects followed by a specified object.
  • ReadList Object ActivityReturn one cursor-controlled page of incoming or outgoing relationship activity involving a specific object.
  • ReadList Recent EventsReturn the most recent events sent to the app, up to the requested limit; Pipeless provides no continuation cursor for this read.
  • ReadList Recommended ContentReturn a bounded personalized list of content recommendations for an object using configurable positive, negative, tag, author, follow, and dismissal signals.
  • ReadList Related ContentReturn content objects related to a target content object using optional tag and collaborative-interaction signals.
  • ReadList Users To FollowReturn a bounded personalized list of user or account objects that the specified object may want to follow.
  • ReadRank ContentRank a supplied set of content IDs for an object and report which IDs Pipeless could rank.
  • WriteCreate EventRecord one typed relationship event for Pipeless activity and recommendation algorithms. Approval by default
  • WriteCreate Events BatchRecord 1 to 10 relationship events in one Pipeless request. Approval by default
  • WriteDelete EventDelete event records matching an exact start object, relationship type and timestamp, and end object. Approval by default

One prompt, start to finish

What a governed Pipeless Recommendations run looks like inside Luumen.

Questions

How does LuumenAI connect to Pipeless Recommendations?

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 Pipeless Recommendations on its own?

Read actions answer immediately. Anything that writes — create event, create events batch, delete event — is shown as a plan and requires approval by default, including the 1 action 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 Pipeless Recommendations — 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.

All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task statusAffindaRead parsed documents, collections, and annotations — change them with approvalAgent MailGive the agent its own mailbox for reading threads and sending updatesAI/ML APIInspect assistants, threads, and runs — and change them as approved steps

Put Pipeless Recommendations to work with Luumen

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

Book a DemoDownload Luumen