Apply generative AI concepts and techniques
Unlock the complete study guide.
Bundled into the existing AWS Certified AI Business Strategist premium course — no separate purchase.
14-day refund guarantee on one-time purchases and your first subscription charge.
Included in this chapter:
- Three layers that shape a generative AI response
- Writing prompts that state task, evidence, and format
- Examples, templates, and iterative prompt refinement
- Tokens, context windows, and generation limits
- RAG: supplying evidence at response time
- Fine-tuning and other ways to customize a model
- Choosing and evaluating an adaptation
- Applying GenAI techniques to business gaps
Prompt engineering vs RAG vs fine-tuning: which layer each changes
| Decision factor | Prompt engineering | RAG | Fine-tuning |
|---|---|---|---|
| Layer it changes | The request (written instructions, evidence, examples) | The request (evidence retrieved automatically) | The trained parameters |
| Gap it closes | Wrong task, format, audience, or style | Missing private or frequently changing knowledge | Persistent behavior or style that prompts did not fix |
| What you must supply | Clear instructions, relevant evidence, examples | Authoritative, current, permission-controlled sources | Reliable examples (or quality feedback) of the desired output |
| When facts change | Edit the evidence in the prompt | Refresh the sources and their index; updates can be available in minutes | Retrain, which can take hours to days |
| Source citations | Can cite supplied sources when prompted | Can return references to the retrieved sources | No built-in reference to sources |
| Effort and skills | Lowest; no training | Managed options such as Amazon Bedrock Knowledge Bases | Training and evaluation work, often a data scientist |
Decision tree
Cheat sheet
Unlock with Premium — includes all practice exams and the complete study guide.
Also tested in
- MLA-C02 AWS Certified Machine Learning Engineer - Associate Choose ML and AI modeling approaches
- MLA-C02 AWS Certified Machine Learning Engineer - Associate Train and customize ML and AI models
- AI-103 AI-103 Optimize and Operationalize Generative AI Systems
- GAIL Generative AI Leader Overcoming Model Limitations
- GAIL Generative AI Leader Prompt Engineering
- GH-300 GitHub Copilot Craft Effective Prompts
References
- https://aws.amazon.com/what-is/retrieval-augmented-generation/
- https://docs.aws.amazon.com/bedrock/latest/userguide/design-a-prompt.html
- https://docs.aws.amazon.com/aws-certification/latest/ai-business-strategist-01/ai-business-strategist-01-domain1.html
- https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-engineering-guidelines.html
- https://docs.aws.amazon.com/bedrock/latest/userguide/inference-parameters.html
- https://docs.aws.amazon.com/bedrock/latest/userguide/custom-models.html
- https://aws.amazon.com/what-is/prompt-engineering/
- https://docs.aws.amazon.com/nova/latest/userguide/prompting.html
- https://docs.aws.amazon.com/nova/latest/userguide/prompting-tools-rag.html
- https://docs.aws.amazon.com/nova/latest/userguide/prompting-focus.html
- https://docs.aws.amazon.com/connect/latest/adminguide/upgrade-models-ai-prompts-agents.html
- https://docs.aws.amazon.com/wellarchitected/latest/generative-ai-lens/genperf01-bp01.html
- https://aws.amazon.com/blogs/security/context-window-overflow-breaking-the-barrier/
- https://aws.amazon.com/blogs/machine-learning/break-the-context-window-barrier-with-amazon-bedrock-agentcore/
- https://docs.aws.amazon.com/wellarchitected/latest/generative-ai-lens/gencost01-bp01.html
- https://aws.amazon.com/blogs/machine-learning/amazon-bedrock-agentcore-memory-building-context-aware-agents/
- https://docs.aws.amazon.com/prescriptive-guidance/latest/retrieval-augmented-generation-options/rag-vs-fine-tuning.html
- https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html
- https://docs.aws.amazon.com/prescriptive-guidance/latest/retrieval-augmented-generation-options/what-is-rag.html
- https://aws.amazon.com/bedrock/evaluations/
- https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base.html
- https://aws.amazon.com/blogs/security/authorizing-access-to-data-with-rag-implementations/
- https://docs.aws.amazon.com/bedrock/latest/userguide/guardrails-contextual-grounding-check.html
- https://docs.aws.amazon.com/aws-certification/latest/ai-business-strategist-01/ai-business-strategist-01-domain3.html
- https://docs.aws.amazon.com/nova/latest/nova2-userguide/nova-cpt.html
- https://docs.aws.amazon.com/nova/latest/userguide/nova-forge-sft.html
- https://docs.aws.amazon.com/bedrock/latest/userguide/reinforcement-fine-tuning.html
- https://docs.aws.amazon.com/bedrock/latest/userguide/model-distillation.html