An insurer receives claim forms as scanned PDFs. It needs the printed values out of the form's fields — policy number, date, amount — as structured text it can put into a database. The team has no machine learning expertise and does not want to train anything. Which service should it start with?

AWS Certified Cloud Practitioner (CLF-C02), objective 3. Cloud technology and services medium

Machine-checked — no person has signed for it. This question was read against the source cited below by an automated pass, which found no contradiction. That is a weaker claim than it sounds: the same kind of process wrote the question, so it can confirm its own mistake.

Treat it as a good draft rather than as settled fact, and read the source below before you rely on it. It is not used in mock exams here — only questions a person has signed for are.

The options

Correct Amazon Textract

Correct. Textract is the pre-trained service for documents specifically: it extracts text, and it understands the structure of forms and tables, which is what turns a scan into key-value pairs rather than a wall of words.

Not correct Amazon Rekognition

Wrong service for documents. Rekognition analyses images and video — objects, scenes, faces, moderation. It can detect text in an image, but recovering a form's field structure is what Textract is built for.

Not correct Amazon Comprehend

Wrong at this stage, and it is the natural next step rather than the first one. Comprehend does natural language processing — entities, key phrases, sentiment, language — on text you already have. Something must produce the text first.

Not correct Amazon SageMaker

Wrong for a team with no machine learning staff. SageMaker is the platform for building, training and deploying your own models. It is the right answer when nothing pre-trained fits, which is not the case for reading a form.

Why

Sort the pre-trained artificial intelligence services by what goes in. Images and video: Rekognition. Documents and scans: Textract. Text: Comprehend for analysis, Translate for languages. Speech: Transcribe turns speech into text, Polly turns text into speech. Conversations: Lex. Enterprise search: Kendra. SageMaker sits underneath all of them as the build-your-own option. The habit worth forming is to reach for a pre-trained service first and only build a model when the catalogue has no answer.

Where this comes from

Cited
AWS exam guide task statement 3.7

Practise this

Reading one question is not practice. The trainer will draw a set from objective 3 and space the ones you get wrong.

Practise AWS Certified Cloud Practitioner (CLF-C02)

More questions on this objective

All questions on Cloud technology and services