Nanonets
for LuumenAI
Check document models and extraction results, then update them with approval
Nanonets turns invoices, forms, and scanned paperwork into structured fields. Luumen reads your models, their configured details, workflow runs, and the documents already processed, so you can see where extraction is drifting. Changes — new models, guideline updates, training uploads — are previewed and approved before they run. Luumen connects with an API key.
The Nanonets toolbox
11 tools: 6 read, 5 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet All ModelsRetrieves all models (OCR and Image Classification) in the user's NanoNets account.
- ReadGet All Prediction FilesRetrieve all prediction files (OCR results) for a NanoNets model.
- ReadGet OCR Model DetailsRetrieve details of an OCR model.
- ReadGet OCR Training ImagesRetrieve training images for an OCR model.
- ReadGet WorkflowsRetrieve a list of all workflows in your Nanonets account.
- ReadList Workflow DocumentsRetrieve a paginated list of documents processed by a NanoNets workflow.
- WriteCreate ModelCreate a new image classification or OCR model. Approval by default
- WriteDelete OCR ModelPermanently deletes an OCR model from Nanonets. Approval by default
- WriteUpdate Model AI GuidelinesUpdate AI Agent guidelines for an OCR model. Approval by default
- WriteUpload Training Images by FileUpload a training image file to a specified OCR model. Approval by default
- WriteUpload Training Images by URLUpload training images by URL to a specified OCR model. Approval by default
One prompt, start to finish
What a governed Nanonets 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 model, delete ocr model, update model ai guidelines, upload training images by file, and more — 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 Nanonets — 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 Nanonets to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.