LLMWhisperer
for LuumenAI

Turn scanned PDFs into text an LLM can actually read

LLMWhisperer converts PDFs and scanned documents into text laid out so a language model can follow it. Connect it with an API key and Luumen can check extraction status, pull job details and highlight metadata, and read your account usage. Conversions and webhook changes run as previewed, approved steps.

Book a DemoDownload Luumen

The LLMWhisperer toolbox

11 tools: 6 read, 5 write. Reads answer instantly. Writes require approval by default. Everything is logged.

  • ReadGet Highlights MetadataGet line metadata for highlighting extracted text in the original document.
  • ReadGet Usage InformationCheck usage metrics of your LLMWhisperer account.
  • ReadGet Usage StatisticsRetrieve usage statistics for your LLMWhisperer account based on a specific tag.
  • ReadGet Webhook DetailsRetrieve registered webhook details for LLMWhisperer.
  • ReadCheck Whisper StatusCheck the status of a text extraction process in LLMWhisperer.
  • ReadGet Whisper DetailRetrieve comprehensive details about ongoing or completed text extraction process.
  • WriteConvert Document to Text (v2)Convert PDF/scanned documents to text format for LLM consumption. Approval by default
  • WriteRegister WebhookRegister a new webhook endpoint for LLMWhisperer async notifications. Approval by default
  • WriteDelete WebhookDelete a registered webhook from LLMWhisperer system. Approval by default
  • WriteUpdate Webhook ConfigurationUpdate an existing webhook configuration for document conversion callbacks. Approval by default
  • WriteRetrieve Whisper TextRetrieve extracted text from asynchronous whisper processing. Approval by default

One prompt, start to finish

What a governed LLMWhisperer run looks like inside Luumen.

Questions

How does LuumenAI connect to LLMWhisperer?

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 LLMWhisperer on its own?

Read actions answer immediately. Anything that writes — convert document to text (v2), register webhook, delete webhook, update webhook configuration, 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 LLMWhisperer — 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 LLMWhisperer to work with Luumen

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

Book a DemoDownload Luumen