Markup AI
for LuumenAI
Check drafts against your brand voice, terminology, and style targets
Connect Markup AI and Luumen can see the content agents your organization has published, along with the personas, brand voice profiles, style guides, and terminology sets behind them. Ask what a profile actually enforces, or which terms apply to a draft. When you want a document evaluated, Luumen runs the agent you picked and brings back the result.
The Markup AI toolbox
10 tools: 9 read, 1 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet AgentGet one agent's metadata and complete runtime input and output JSON Schemas before executing it.
- ReadGet Analysis ProfileGet one persona, brand voice profile, style target, or style guide by ID, including detailed configuration needed to understand its effect on analysis.
- ReadGet WorkflowGet the current status and result of an asynchronous agent workflow by ID.
- ReadList Agent CategoriesReturn all agent categories available to the connected organization for discovery and agent-list filtering.
- ReadList AgentsDiscover Markup AI agents available to the connected organization, optionally filtered by category.
- ReadList Analysis ProfilesList selectable persona, brand voice, style guide, style target, or content profile resources used to configure agent runs.
- ReadList Terminology ResourcesList terminology term sets or domains with filters and cursor-controlled pagination.
- ReadList WorkflowsList one cursor-controlled page of agent execution workflows, optionally filtering that page by status, stable agent name, or creation time.
- ReadSearch TerminologyFind organization terminology rules relevant to supplied text, optionally limited to selected domains.
- WriteRun AgentRun one selected Markup AI agent against document text, synchronously or asynchronously. Approval by default
One prompt, start to finish
What a governed Markup AI 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 — run agent — is shown as a plan and requires approval by default. 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 Markup AI — 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 Markup AI to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.