AIF-C01 - Applications of foundation models (28% of the exam) - Section 3.1
Describe design considerations for applications that use foundation models.
Consider model selection, context windows, cost, latency, and guardrails when designing an application on a foundation model. Understand where to add retrieval, caching, or human review.
Model selectionContext windowGuardrails
Practice question for this objective
lock_openFree sampleApplications of foundation modelsmedium
An organisation is selecting a foundation model for a document summarisation service. The documents are technical engineering reports averaging 15,000 tokens each. The team has shortlisted two models: Model X supports a 4,096-token context window and Model Y supports a 32,000-token context window. Both models have comparable quality benchmarks. Which selection criterion most directly favours Model Y for this use case?
AModel Y's larger context window allows full-document summarisation without chunking, reducing implementation complexity and potential coherence loss.check_circle Correct
BModel Y's larger context window means it was trained on more data, so its factual knowledge is more comprehensive for engineering topics.
CModel Y's larger context window lowers per-token inference cost because fewer API calls are needed when processing large batches of documents.
DModel Y's larger context window enables the model to generate longer summaries, meeting any output length requirements imposed by the engineering team.
Identify context window size as the decisive model selection criterion when source documents exceed one model's input limit. Context window is the total token budget for a single inference call (input plus output). When documents average 15,000 tokens and one candidate model caps at 4,096 tokens, that model cannot process a full document in one call. Model Y's 32,000-token window accommodates the full document, eliminating chunking complexity and preserving cross-section coherence. Model selection must therefore account for context window relative to expected input length.
Why A is correct: Because the average document (15,000 tokens) exceeds Model X's 4,096-token window, Model X would require chunking and then re-stitching summaries, introducing complexity and risk of losing cross-section context. Model Y can ingest the full document in a single call.
Why B is wrong: Context window size is an architectural inference-time property and is not correlated with training dataset size or domain coverage. Conflating these is a common misunderstanding. The selection advantage here is purely about input capacity at inference time.
Why C is wrong: Larger context windows typically carry higher per-token costs, not lower ones, because they require more memory and compute. Fewer API calls may reduce overhead but per-token pricing generally increases with window size. Cost is not the selection advantage cited in the question.
Why D is wrong: Context window size controls input capacity, not output length directly. Output length is governed by max output token settings. The relevant advantage here is the ability to ingest 15,000-token documents as input, not to produce longer outputs.
Answers that look right on this material and are not. Each one is a distractor from a different question in the AIF-C01 bank for this domain.
The model's training data cutoff date, because any catalogue content newer than the cutoff will be ignored by the model during inference.
errorWhy it is wrong: Training cutoff affects factual knowledge baked into weights, not the ability to process input tokens supplied at inference time. Providing the catalogue as context bypasses the cutoff problem entirely, so this is not the limiting factor here.
Self-hosted models can be fine-tuned on internal data more easily than API-based models, which is required for domain-specific performance.
errorWhy it is wrong: Many API-based foundation model providers also offer fine-tuning services. Fine-tuning capability alone does not require self-hosting, and it is not the strongest consideration given the explicit network-boundary constraint stated in the question.
A model with a large context window, because multilingual inputs tend to be longer when translated compared to English-only inputs.
errorWhy it is wrong: While multilingual tokenisation can produce more tokens than English for the same semantic content, context window size is not the primary criterion for multilingual capability. A large context window does not confer language coverage; it only affects input length capacity.