AIGP - Understanding how to govern AI deployment and use - Section 4.3

Understand the differences in AI deployment options including cloud, on-premise and edge, and techniques to improve fit such as fine-tuning, retrieval augmented generation and agentic architectures.

Compare cloud, on-premise, and edge AI deployment options and their governance implications. Distinguish between fine-tuning, retrieval augmented generation, and agentic architectures as techniques to improve model fit, and identify when each approach is appropriate.

retrieval augmented generationfine-tuningagentic architecturesAI deployment options

Practice question for this objective

Free sampleUnderstanding how to govern AI deployment and usemedium

An AI literacy session contrasts retrieval augmented generation with fine-tuning as techniques to improve how well an AI system fits a specialised task. Which statement correctly describes what retrieval augmented generation does that fine-tuning does not?

  • AIt permanently rewrites the model's internal weights so the specialised knowledge is encoded directly in the AI system and survives without any external store.
  • BIt enlarges the model's parameter count during deployment so the AI system can store more domain facts than the base model held at release.
  • CIt removes the need for any prompt by letting the model query a database on its own and decide unaided which records to act on and modify for every incoming request.
  • DIt fetches relevant passages from an external knowledge source at query time and supplies them to the model as context, so answers can be grounded in current source content without retraining. Correct
Distinguish retrieval augmented generation, which grounds answers in external content at query time, from fine-tuning, which alters the model's weights. Retrieval augmented generation works by querying an external knowledge source for relevant material at inference time and inserting that material into the model's context window, so the AI system can produce grounded, current answers while the base model stays unchanged. Fine-tuning instead updates the model's parameters from a curated dataset, which is why the two techniques have different update cadences, cost profiles and traceability characteristics.

Why A is wrong: Tempting because adapting an AI system to a domain sounds like changing the model itself, but rewriting internal weights from a labelled dataset describes fine-tuning, not retrieval augmented generation, which leaves the base model unchanged.

Why B is wrong: Tempting because more capacity feels like the route to more knowledge, but retrieval augmented generation does not change parameter count; it supplies external context to a fixed model rather than growing the model itself.

Why C is wrong: Tempting because retrieval involves a data store, but retrieval augmented generation still operates on a user prompt; autonomous, unaided action on records describes an agentic pattern, not retrieval that merely supplies context.

Why D is correct: Retrieval augmented generation retrieves matching documents from an external store at inference time and passes them to the model as additional context, which grounds responses in up-to-date source material and avoids the need to retrain the underlying AI system.

See more AIGP practice questions, answers explained.

More in this domain

Back to all Understanding how to govern AI deployment and use objectives, or the AIGP cert hub.

Examworthy is not affiliated with or endorsed by IAPP. Original, blueprint-aligned practice material only.