Memory hook: Identify the input and the required output before choosing an AI service.
Must remember
Words, voices and conversations
- Transcribe converts speech to text; Polly converts text to speech. Meeting subtitles point to Transcribe; reading a message aloud points to Polly. Translate changes the language of text, so translated subtitles can require Transcribe followed by Translate.
- Comprehend interprets text: sentiment, entities, key phrases and language insights. Comprehend Medical specializes in supported clinical entities and relationships; extracting a medication name does not make it a diagnostic system.
- Lex manages conversational intents, slots and dialogue. Connect supplies contact-center capabilities and telephony, now documented as Connect Customer. A support flow can use Connect for the call, Lex to understand the request and backend services to fulfill it. A chatbot and a complete contact center are different requirements.
- Distinguish language translation from sentiment classification. An application may need both, but one API response does not automatically supply the other. Confirm language and feature support for the particular operation rather than assuming every language works everywhere.
Images, documents and recommendations
- Rekognition analyzes images and video: visual labels, supported face analysis and other image-understanding features. Textract extracts document text and structure, including supported forms and tables. When the required result is an invoice's fields and line items, structured document extraction is the stronger clue than the generic word “image.”
- Personalize creates individualized recommendations using interaction and item information. It is not an enterprise document search engine. Kendra searches indexed enterprise content; the index and connector lifecycle add cost and administration. Both are retained from the requested curriculum even though neither is explicitly named in the current in-scope service list.
- SageMaker AI provides custom model development, training and deployment. Choose it when the workload needs a model or workflow that a suitable pretrained API does not already provide. Owning training data, evaluation and model serving adds decisions about quality, capacity and operations.
Architecture decisions around the API
- A synchronous request fits a small interactive operation; larger supported jobs may need asynchronous completion, an output store and retries. Distinguish the job's lifecycle from the data it writes. Deleting a job does not necessarily remove stored output.
- Keep application credentials in a service role. Limit actions and data access, encrypt sensitive input/output, and select a Region that meets data-handling requirements. Medical text and face data need particularly deliberate handling; use harmless sample inputs in this pack.
- Decouple bursty work with a queue and handle throttling with bounded retries. Evaluate accuracy against the actual business task; a confidence score is not a guarantee of correctness. Include a human review step when uncertain predictions cannot safely drive an automatic action.
- Pay attention to persistent capacity: an occasional API call, a running inference endpoint, a notebook and an enterprise-search index have different idle-cost behavior. None is justified merely because it is available in a console.
Choose under exam pressure
| Clue in the requirement | Choose or investigate |
|---|---|
| Audio recording needs searchable text | Transcribe |
| Written directions must be spoken | Polly |
| Reviews need sentiment scores | Comprehend |
| Invoice needs named fields and table cells | Textract |
| An image needs visual labels | Rekognition |
| Voice support needs intents plus call handling | Lex plus Connect |
| A bespoke model must be trained and hosted | SageMaker AI |
| Shopping suggestions depend on each user's history | Personalize concept |
Traps
- The service name is not enough: match supported input, output, language, latency and quality requirements.
- Reading text inside an image is not automatically equivalent to extracting document structure.
- “Managed” does not mean “no persistent resources” or “no idle charge.” Delete endpoints, jobs and outputs according to their separate lifecycles.
Active recall
1. A French meeting recording must become English subtitles. Which sequence fits, and why is Translate alone insufficient?
Use Transcribe to produce text from speech, then Translate for the language conversion, with supported languages and timestamps considered. Translate operates on text; it does not replace the audio transcription step.
2. Finance needs invoice totals and line items from scans. Why choose Textract over generic image labels?
The required output is document structure and fields. Textract addresses that extraction task; a label saying an image contains a document does not provide its line-item table.
3. A help line needs callers to state their intent and reach an agent. Is Lex the entire solution?
No. Lex supplies conversational understanding, while Connect supplies contact-center and telephony functions. Backend fulfillment and appropriate access control remain separate components.
4. A team translates ten short messages each day. Why question a continuously running custom inference endpoint?
A purpose-built translation API can already meet the task with less model-management work. Persistent inference capacity can introduce idle charges and unnecessary operational complexity.
5. Product recommendations and searches across HR policies appear in one proposal. Should they use the same service?
Not automatically. Personalized recommendations depend on user/item interactions; enterprise search depends on indexed documents and access controls. Personalize and Kendra illustrate those different course concepts.
Terraform anchor: Stable map keys make policy instances predictable, while valid JSON alone does not prove that the IAM permissions match the application.
Sources
- AWS AI and ML overview groups the purpose-built and custom-model service families.
- Textract overview explains structured document extraction.
- Connect overview distinguishes contact-center capabilities from chatbot intent handling.
- Published SAA-C03 in-scope services identifies the named ML services; the list is explicitly non-exhaustive.