Document & Image Intelligence

Reading the text in uploaded and scanned documents, AI models reading stored documents and images, and what the platform does not analyse.

Document and Image Intelligence

Document and image intelligence is the platform reading content it cannot otherwise interpret: the words inside uploaded documents, the text in a scanned page, and, through the AI gateway, a model reading a stored document or a picture. This page sets out what exists today, what each part does, and what is not available, so you can plan around the real capabilities.

Where to find it

Architect Panel → Automation:

Tasks — Document Text Extraction, which reads documents in the background every 15 minutes

Architect Panel → Configuration:

AI Settings — the ocr role, when scans are read by an AI model

Architect Panel → Activity:

AI Usage — the cost of each scan read by AI, under the feature ocr

Architect Panel → Security:

Classification Levels — Allow Export, which decides whether a document may be read off-site

What exists

Text extraction for search. PDFs, Word and OpenDocument files, spreadsheets, presentations, and plain text, HTML and e-mail are read into the document index so their contents can be searched.
Reading scans (OCR). A scanned image, or a PDF that is only a picture of text, needs optical character recognition. Your hosting administrator chooses the reader in the server's configuration: Tesseract on your own server, AWS Textract, or an AI model through the gateway. It is off until chosen.
AI reading of scans. With the AI reader, each scan is sent to the model on the ocr role and asked for a transcription and nothing else. See the next article.
Stored documents as AI input. A custom feature or an MCP client can give a model a stored document, under the export rules. See AI Gateway.

What is not available

Language detection and image labelling have no screen, setting or automatic use on the platform. They exist only as building blocks a developer can use in custom code.
Pulling fields out of an arbitrary document, such as the total on any invoice, is not a configurable feature. One installation-specific extractor reads supplier bills arriving from Xero, and it is not configured from any panel screen.

Not the same as Data Extraction

Data Extraction ingests structured files such as CSV, JSON and XML, where a value sits at a known place. Everything on this page reads unstructured content, where nothing is at a known position and the result is a best reading. If your source is a spreadsheet export, use Data Extraction.

Extraction runs in the background

Reading a document can take seconds to tens of seconds, so uploads are queued and the Document Text Extraction task works through the queue every 15 minutes. It ships disabled: until it is switched on, nothing queued is ever read, nothing new is searchable, and only Claude can be sent a stored PDF.

In Tasks, switch on Document Text Extraction.
Ask your hosting administrator which OCR reader, if any, is configured, and whether it reads files on your server or elsewhere.
Upload one document of each type you expect, including a scan, and search for a phrase from each after the next run.

Results are readings, not facts

Text from a clean, machine-made PDF is exact. Text read from a scan or photograph is approximately right: good enough to find a document, not good enough to rely on for a figure or a reference number without someone checking it against the original. Quality in is quality out: a straight, well-lit scan reads far better than a photograph taken at an angle.

What goes wrong, and how to tell

Nothing new is searchable: the extraction task is off.
Scans never become searchable: no OCR reader is configured, or the reader is off-site and the document's classification forbids export. The latter is recorded as a failure naming the reason.
A scan is "Not read yet" with a sentence about AI credit: the AI reader was refused because the tenant's AI credit is used up. It is not re-read automatically after a top-up.

Worked example

An organisation with a library of scanned correspondence switches on Document Text Extraction and asks its hosting administrator to configure Tesseract, because some of the archive is classified and must not leave. Typed PDFs become searchable within the hour; scans follow as the queue is worked through. Nobody expects the platform to detect the language of letters, because the team checked this page first.

Recommendations

Switch on the extraction task, or nothing is ever read.
Choose the OCR reader with your classification in mind: only a local reader can read everything.
Check a sample of each document type after the first run.
Treat text from scans as a strong suggestion, checked against the original where it matters.

Reading Scanned Documents

A scanned page is a picture of text: until something reads it, it is stored and served but can never be found by search. The platform can read scans with one of three readers, and one of them is an AI model on the gateway's ocr role. This article covers choosing a reader, setting up the AI one, and what to expect from each.

Where to find it

Architect Panel → Automation:

Tasks — Document Text Extraction, which sends each queued scan to the reader

Architect Panel → Configuration:

AI Settings — the ocr row in Which provider each AI feature uses

Architect Panel → Activity:

AI Usage — one run per scan read by AI, with its cost

Architect Panel → Security:

Classification Levels — Allow Export, which off-site readers must respect

The three readers

Tesseract, a program on your own server. Nothing leaves. Scanned PDFs can be read too if a second program that renders PDF pages is installed.
AWS Textract. The file leaves the system. It reads images and PDFs, but only the first page of a multi-page PDF; the rest is recorded as unread rather than claimed as indexed.
An AI model, through the gateway's ocr role. The file leaves the system. Of the image types the document index sends for OCR, it reads JPG and PNG up to 5 MB, but not TIFF, and it is never sent a PDF.

The reader is chosen by your hosting administrator in the server's configuration, not on a screen, and it ships switched off. A document whose classification does not allow export is never given to Textract or the AI reader; it is recorded as a failure naming the reason, and a local reader would read it.

Setting up the AI reader

Ask your hosting administrator to set the installation's OCR reader to the AI gateway.
On AI Settings, decide the ocr role's provider and model. Left on Inherit it uses the builder model; choose a model that reads images, and consider a cheaper one than builder, since transcription is a simple task.
Save, and press Test beside ocr on AI Usage.
In Tasks, make sure Document Text Extraction is switched on.
Upload a scanned image as a document, wait for the next run, and search for a phrase from it.
On AI Usage, filter Recent AI calls by the feature ocr and open the run: it shows the cost and the document version it read, but no text.

What the AI reader does

It asks for a transcription and nothing else: the words exactly as they appear, in reading order, with [?] for an illegible word. A description of the document would be searched as if it were the document's own words.
It keeps the cost, never the text, in the run log. The transcription already lives with the document, under its access rules, classification and redactions.
It is charged to the document's tenant where AI billing is on. When the tenant's credit is used up, the scan is recorded as "Not read yet" with the credit sentence, and is not re-read automatically after a top-up.
A very dense page may be cut short. The part that was read is kept, and the shortfall is noted in the error log.

Scanned PDFs

A PDF goes to the ordinary PDF reader first. When that finds no words at all, it is tried again through OCR, but only where the reader can take a PDF: Textract, or Tesseract with the page renderer. The AI reader is sent images only, so with it a scanned PDF stays unread.

Supplier invoices from Xero

Separately, one installation-specific extractor reads supplier bills that arrive from Xero with an attachment, using AWS Textract's expense analysis and label rules held in that app's own tables. It normalises UK and European number formats and, where a line's total agrees with its quantity times its price, prefers that total. It has no panel screen and is not part of a standard installation.

What goes wrong, and how to tell

Scans are never read: no reader is configured, or the extraction task is off.
TIFF scans are never read with the AI reader: the AI reader does not take TIFF. Scan to PDF or JPG, or use Tesseract.
A classified scan fails with a reason about leaving the system: that is the export rule working.
AI Usage shows ocr runs failing with not_configured: the ocr role's provider has no key.

Worked example

A team receives photographed delivery notes as JPGs. The hosting administrator sets the reader to the AI gateway, and the architect points the ocr role at a smaller model that reads images, tests it, and confirms the extraction task is on. Next morning the notes are searchable by consignment number, and AI Usage grouped by feature shows what reading them cost.

Recommendations

Use Tesseract if anything you hold forbids export; it is the only reader that can read everything.
Give the ocr role its own, cheaper model rather than inheriting builder.
Prefer JPG or PNG scans if you use the AI reader.
Check AI Usage after a bulk upload: every scan is a paid call.

Language and Image Analysis

People often expect a business platform to detect what language a message is in, or label what a photograph shows. On ActiveManage neither is a feature you can switch on today: there is no screen, setting, workflow step or automatic use for them. This page says plainly what is and is not available, and which features cover the nearby needs.

Where to find it

Architect Panel → Configuration:

AI Settings — the ocr role, for reading text in images, and the image and video generation settings

Architect Panel → Automation:

Tasks — Document Text Extraction, which reads text in scanned images

Architect Panel → Activity:

AI Usage — the cost of anything read by an AI model

What is not available

Language detection: there is no setting that records or acts on the language of a message or record.
Image labelling or screening: nothing tags photographs with what they contain, or checks uploaded images before they are published.
Sentiment and entity detection: not available as features either.

The platform does include building blocks for these, based on AWS language and image services and using the installation's AWS credentials, but nothing in the platform calls them. Using them means custom development, and the cost lands on your AWS account.

What covers the nearby needs

Text in an image. A sign, a serial plate or a scanned letter is read into the document index by the configured OCR reader, so it becomes searchable. See Document & Image Intelligence.
What a message is about. Inbound messaging rules can match on what a message is about using TypeSafe Jev; see Is About (AI) Message Rules.
A model looking at a picture. The AI gateway accepts images as input, so a custom feature can ask a model a question about a photograph, logged and charged like any other AI call.
Making images. Generating pictures and video is a separate feature; see AI Images & Video.

If you need one of the missing capabilities

Write down the decision it would drive: route a message, tag a record, hold an image for review.
Check whether one of the features above already answers it, for example matching on what a message is about instead of its language.
If not, raise it as custom development, and settle where the data will be processed and what it costs before work starts.
Keep any automated result as a suggestion a person confirms, and store its confidence alongside it, so a threshold can be tuned later from real data.

Using results from a model

Whatever reads text or images produces a likelihood, not a fact. Short text is genuinely ambiguous, and photographs taken at an angle or in poor light read badly. Use results to pre-fill, prioritise or suggest, with a person deciding, and never to publish or refuse something unattended. Where automated analysis affects how someone is treated, say so in your privacy information.

What goes wrong, and how to tell

A process assumes language is recorded: it is not. Check with your developer what the custom code actually stores.
Text inside photographs is not searchable: no OCR reader is configured, or the extraction task is off.
Unexpected AWS charges after custom work: the AWS building blocks bill your AWS account directly and do not appear on AI Usage.

Worked example

A service wants replies sent in the language a customer wrote in. Reading this page, the team finds there is no language detection to switch on. They instead add a preferred-language field to the contact record, filled in at first contact, and route on that. It is simpler, never guesses wrong on a three-word message, and needed no custom development.

Recommendations

Do not plan around language detection or image labelling as if they were features.
Prefer a field a person fills in where the answer drives how someone is treated.
Use OCR for text in images, and the gateway for custom questions about pictures.
Settle cost and data location first if you commission custom analysis.