Exam Room · AI Practitioner

Cheat Sheet: AWS AI Services

· 10 min read

AI Fundamentals · part of The Exam Room

A fast pass over the managed AI services: one line each, and the pairs that look interchangeable but are not.

Services at a glance

Service What it does Reach for it when
Amazon Polly Text to speech Content needs to be spoken aloud
Amazon Transcribe Speech to text Audio needs to become a transcript
Amazon Translate Language translation Text needs to move between languages
Amazon Comprehend Text analysis: sentiment, entities, PII detection You need to understand what a body of text contains, not generate new text
Amazon Lex Conversational interfaces You are building a chatbot or voice bot with defined intents
Amazon Rekognition Image and video analysis You need to detect objects, faces, text, or moderate content in visual media
Amazon Textract Document structure extraction You need forms, tables, and key-value pairs out of a scanned or digital document
Amazon Kendra Enterprise search; maintenance mode, closed to new customers since July 2026 You need a retrieval layer over enterprise content, not a ready assistant
Amazon Personalize Recommendations You need to rank or suggest items for a user based on behaviour
Amazon Quick A managed assistant over company data You need connectors, permissions, and citations with no code written
Amazon Q Developer A coding and AWS assistant in the IDE, CLI, and console You need help writing, reviewing, or explaining code, or answering questions about your AWS account

Decision rules

  • If the job is turning text into audio, that is Polly; if it is turning audio into text, that is Transcribe. The direction of the arrow decides which one.
  • If the task is understanding existing text (sentiment, entities, PII), reach for Comprehend rather than asking a foundation model to do analysis a purpose-built service already does more cheaply.
  • If you are building a defined-intent chatbot or voice interface, use Lex; an open-ended assistant over your own documents is Amazon Quick, not a Lex bot.
  • If the input is an image or video and the question is “what is in this”, use Rekognition; if the input is a document and the question is “what is its structure”, use Textract.
  • If you need a retrieval layer with connectors and access control feeding your own application, that is Kendra (maintenance mode and closed to new customers since July 2026, so existing indexes only); if you need a ready assistant with a UI, that is Amazon Quick.
  • If the ask is “recommend items to this user”, that is Personalize, not a general-purpose model prompted with behavioural data.
  • If a request is about writing code or working with your AWS account, that is Q Developer; if it is about answering questions from company documents, that is Amazon Quick. The two get named in almost the same breath and do different jobs.
  • If a purpose-built AI service already solves the problem, prefer it over building the same capability on a foundation model; it is usually cheaper, faster, and more consistent for a narrow task.

Traps

  • Assuming Comprehend generates text. It analyses text that already exists; it does not write anything new.
  • Confusing Rekognition and Textract because both process images. Rekognition answers “what is depicted”; Textract answers “what is the structure of this document” (fields, tables, key-value pairs).
  • Treating Kendra as a chatbot. It is the retrieval layer other things are built on top of, not a conversational surface in itself.
  • Picking Kendra for a new build. It has been in maintenance mode and closed to new customers since July 2026; existing indexes keep running, but a new retrieval build goes elsewhere.
  • Swapping Amazon Quick and Q Developer in a sentence about “the AWS assistant”. One answers from company data with citations; the other sits in the IDE, CLI, and console for code and AWS work. They do not overlap.
  • Reaching for a foundation model to do sentiment analysis or entity extraction when Comprehend already does it as a managed, purpose-built call.
  • Picking Personalize for a one-off recommendation with no behavioural history to train on; it needs interaction data to be worth using over a simpler rule.
  • Forgetting that Lex handles defined intents and slots; an open-ended, document-grounded conversation is a different architecture, not a Lex bot with more intents bolted on.

Say it in one line

  1. Polly turns text into speech; Transcribe turns speech into text. Pick by which way the conversion runs.
  2. Comprehend analyses text that already exists: sentiment, entities, PII. It does not generate anything.
  3. Lex builds defined-intent chatbots and voice bots from intents and slots; an open-ended assistant is a different build.
  4. Rekognition reads images and video; Textract reads document structure, forms, and tables.
  5. Kendra is the enterprise-search retrieval layer, now maintenance-only and closed to new customers; Amazon Quick is the ready assistant with connectors, permissions, and citations.
  6. Personalize ranks and recommends from behavioural data.
  7. Amazon Quick answers questions from company data with citations and no code; Q Developer helps with code and your AWS account. Similar-sounding names, different jobs.
  8. Prefer a purpose-built AI service over a foundation model when one already exists for the task.

These posts are LLM-aided. Backbone, original writing, and structure by Craig. Research and editing by Craig + LLM. Proof-reading by Craig.