mediumMultiple Choice
AIF-C01 Practice Question: A financial services firm wants to deploy a…
A financial services firm wants to deploy a generative AI application that answers customer questions about account balances and recent transactions. The firm has strict latency requirements (responses under 2 seconds) and wants to minimize costs. Which strategy for model selection and deployment is MOST appropriate?
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Select a smaller, faster foundation model (e.g., Amazon Titan Text Lite) and use on-demand inference
For latency-sensitive and cost-conscious applications, selecting a smaller, faster model is preferable over a large model or custom deployment. Provisioned Throughput for dedicated capacity would increase cost and may not be needed if the base model performs adequately.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Select a smaller, faster foundation model (e.g., Amazon Titan Text Lite) and use on-demand inference
Why this is correct
A smaller foundation model such as Amazon Titan Text Lite generates tokens faster, directly satisfying the sub-two-second latency constraint. On-demand inference avoids provisioning charges, minimising cost for variable customer traffic. Larger models would add latency and expense without improving simple balance and transaction lookups.
- ✗
Use the largest available foundation model via on-demand inference for highest accuracy
Why it's wrong here
The largest foundation model on on-demand inference adds per-token cost and inference latency, risking the two-second budget while inflating spend. It is tempting because on-demand suits variable, low-volume workloads where maximum accuracy matters and no latency or cost ceiling applies.
- ✗
Fine-tune a large model specifically on account data and deploy on a dedicated endpoint
Why it's wrong here
Fine-tuning a large model and hosting it on a dedicated endpoint incurs substantial training and continuous inference infrastructure costs, conflicting with the minimise-cost requirement. Fine-tuning suits specialised domain adaptation where prompt engineering and retrieval prove insufficient. Retrieval-augmented generation over a smaller model meets the latency and cost constraints here.
- ✗
Deploy a large model using Provisioned Throughput to guarantee low latency
Why it's wrong here
Provisioned Throughput reserves dedicated model units, billed hourly whether or not requests arrive, so idle capacity inflates spend against the cost-minimisation requirement. It is tempting because it guarantees consistent latency for sustained, high-volume, predictable traffic where throughput reservation genuinely pays off.
Go deeper
Related to this question
About these practice questions
One of 862 original AIF-C01 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AIF-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AIF-C01 exam.