Extracta.ai
for LuumenAI
Read extraction jobs and results, then change the schema as an approved step
Extracta.ai pulls structured fields out of PDFs, images, and text files. Connect it and Luumen can read your extraction and classification configs, check batch results, and watch the credit balance without leaving the terminal. Changes to a schema or classification are previewed first and go through approval by default. Luumen authenticates with an API key.
The Extracta.ai toolbox
10 tools: 4 read, 6 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet Batch ResultsRetrieves extraction results for a specific batch of documents.
- ReadGet CreditsRetrieves the current credit balance available on the account.
- ReadView ClassificationRetrieves details of an existing classification configuration including name, description, document types, associated keywords, and linked extraction templates.
- ReadView ExtractionRetrieves detailed configuration and status information for an existing extraction job.
- WriteCreate ClassificationCreates a new document classification configuration. Approval by default
- WriteCreate ExtractionCreates a new extraction configuration for processing documents. Approval by default
- WriteDelete ClassificationPermanently deletes an entire document classification process including all associated batches, results, and uploaded files. Approval by default
- WriteDelete ExtractionPermanently deletes an extraction job and its configuration from the system. Approval by default
- WriteUpdate ClassificationUpdates an existing document classification by modifying its parameters. Approval by default
- WriteUpdate ExtractionUpdates an existing document extraction process by modifying specified parameters. Approval by default
One prompt, start to finish
What a governed Extracta.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 — create classification, create extraction, delete classification, delete extraction, 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.
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 Extracta.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 Extracta.ai to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.