Developing Generative Artificial Intelligence Solutions
AWS Skill Builder
Last updated March 6, 2026
Developing Generative Artificial Intelligence Solutions is a free, one-hour course that traces the generative AI application lifecycle: defining a business use case, choosing a foundation model, improving and evaluating that model's performance, and deploying it with an eye on the business goal it was meant to serve. It introduces the selection criteria for picking a pre-trained model, explains retrieval-augmented generation (RAG) and what it is good for, weighs the cost trade-offs of the different ways to customize a foundation model, and gives a first look at the role of agents in handling multi-step tasks. It is positioned as a primer — a deliberately high-level pass that sets up the deeper courses on prompt engineering, RAG, and fine-tuning rather than going deep itself. Delivered through interactive elements, videos, text, and graphics.
What you'll learn
- The GenAI application lifecycle (use case → deployment)
- Criteria for selecting a pre-trained foundation model
- What RAG is and where it applies in business
- Cost trade-offs across model-customization approaches
- The role of agents in multi-step tasks
- Evaluating FM performance and the metrics that matter
Frequently asked questions about Developing Generative Artificial Intelligence Solutions
Who is Developing Generative Artificial Intelligence Solutions for?
Anyone interested in machine learning and AI, independent of job role, who wants a high-level map of how generative AI applications are planned, built, and evaluated before going deeper.
Is Developing Generative Artificial Intelligence Solutions free?
Yes — Developing Generative Artificial Intelligence Solutions is completely free to take.
What are the prerequisites for Developing Generative Artificial Intelligence Solutions?
Recommends completing a foundational ML and AI course and an AI use-cases course first.
Why we suggest this course
A useful overview of how a generative AI project actually comes together — from picking a foundation model to evaluating and deploying it — with plain introductions to RAG, customization cost trade-offs, and agents. Two things worth knowing: it is a primer by design, so it sets up the harder concepts rather than teaching them in depth; and it is built by AWS, with its examples framed around Amazon Bedrock, though the lifecycle thinking transfers to other tools.