OpenUI Cloud
for LuumenAI
Read OpenUI conversations and artifacts, then generate new interfaces on approval
Connect OpenUI Cloud and Luumen can read the conversations and artifacts your team already has in Thesys. List conversations, page through their items, and pull the full renderable content of any artifact. When you need something new, Luumen generates the UI response or opens a conversation as a previewed step you approve first. Auth is an API key.
The OpenUI Cloud toolbox
8 tools: 4 read, 4 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet ArtifactRetrieve one persisted OpenUI artifact, including its complete renderable content.
- ReadList ArtifactsList persisted OpenUI artifacts, optionally filtering by name or artifact kinds, one cursor-controlled page at a time.
- ReadList Conversation ItemsRead one cursor-controlled page of persisted messages and function-call items from a managed OpenUI conversation.
- ReadList ConversationsList managed OpenUI conversations visible to the connected organization, one cursor-controlled page at a time.
- WriteCreate ConversationCreate a managed OpenUI conversation that can receive persisted turns from Generate UI. Approval by default
- WriteDelete ConversationPermanently delete one managed OpenUI conversation by ID. Approval by default
- WriteGenerate UIGenerate an OpenUI response from text or structured Responses API input. Approval by default
- WriteRename ConversationChange the title of an existing managed OpenUI conversation. Approval by default
One prompt, start to finish
What a governed OpenUI Cloud run looks like inside Luumen.
Questions
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 conversation, delete conversation, generate ui, rename conversation — 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.
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 OpenUI Cloud — 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.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut OpenUI Cloud to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.