Classify millions of product descriptions overnight.
No per-item instant response is required, but results are needed by morning.
Choose two appropriate designs.
Use batch inference with managed input and output units, and monitor completion time, retries, cost, and quality against the deadline.
Detailed explanation
Large workloads can be grouped without a real-time connection for every item.
Large workloads can be grouped without a real-time connection for every item.
The design can be checked against the morning deadline.
The design can be checked against the morning deadline.
Rate limits, cost, and failure recovery become difficult.
Rate limits, cost, and failure recovery become difficult.
Batch output still needs quality and safety checks.
Batch output still needs quality and safety checks.
Try it yourself
An example you can run in a temporary verification environment.
Amazon Bedrock公式推論方式とAIF-C01 Domain 3.1のモデル選択を確認する。Expected result
リアルタイム性と処理量・運用費用の要件で推論方式を選べる。Key points
- Batch inference
- SLO
- Retry
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.