Marcin Świderski
Developing Generative AI Applications on AWS
This course is designed to introduce generative AI to software developers interested in leveraging large language models without fine-tuning. The course provides an overview of generative AI, planning a generative AI project, getting started with Amazon Bedrock, the foundations of prompt engineering, and the architecture patterns to build generative AI applications using Amazon Bedrock and LangChain.
Digital Credential Validity
Verified
Issued:
5/28/2026 5:03 PM
Valid from:
5/28/2026 5:03 PM
Validity:
Does not expire
These dates show the digital credential's own validity. The electronic seal that secures the PDF has separate, technical certificate dates that do not limit the digital credential.
Digital Credential URI
urn:uuid:cf69a979-5f54-506a-b097-baf3dbcedfd3
Claims
This credential confirms participation in the two-day course “Developing Generative AI Applications on AWS.” The person who received the credential completed a structured learning activity focused on designing and building generative AI applications using AWS services, with particular emphasis on Amazon Bedrock, foundation models, prompt engineering, LangChain, retrieval-augmented generation, generative AI application components, security, governance, monitoring, and architecture patterns.
The course provided practical knowledge on planning generative AI projects, identifying business value in generative AI use cases, using Amazon Bedrock and foundation models, applying prompt engineering techniques, integrating LangChain, and understanding common implementation patterns for generative AI applications on AWS.
Learning outcome summaryAfter completing the course, the learner is able to describe core generative AI concepts, identify business value in generative AI use cases, plan a generative AI project, explain how Amazon Bedrock works, apply prompt engineering practices, recognize the main components of generative AI applications, and discuss the use of LangChain and architecture patterns when building generative AI applications on AWS.
Learning outcomes
- Knowledge Describe the foundations of generative AI Explains core concepts of generative AI, foundation models, large language models, and their relationship to the broader field of machine learning.
- Identify business value in generative AI use cases Recognizes use cases where generative AI may create business value and explains the potential benefits, limitations, and risks of such solutions.
- Plan a generative AI project Describes the key steps involved in planning a generative AI project, including business context, technical requirements, risks, and mitigation strategies.
- Explain how Amazon Bedrock works Describes the basic concepts, benefits, typical use cases, cost structure, and reference architecture associated with Amazon Bedrock-based solutions.
- Apply prompt engineering practices Uses general prompt engineering practices and recognizes basic and advanced prompt techniques, including zero-shot and few-shot approaches.
- Select prompt techniques for specific use cases and models Identifies which prompt techniques are appropriate for selected use cases and model types.
- Recognize and mitigate risks related to prompts and model responses Identifies potential prompt misuse, analyzes possible bias in foundation model responses, and designs prompts that help reduce such risks.
- Identify components of generative AI applications Recognizes key components of generative AI applications, including foundation models, inference parameters, APIs, datasets, embeddings, RAG, retrievers, memory, chains, and agents.
- Describe Amazon Bedrock foundation models and APIs Explains Amazon Bedrock foundation models, inference parameters, key APIs, and methods used to interact with Amazon Bedrock.
- Explains Amazon Bedrock foundation models, inference parameters, key APIs, and methods used to interact with Amazon Bedrock. Identifies AWS offerings and practices that support monitoring, securing, governing, and auditing applications built with Amazon Bedrock.
- Explain LangChain integration with Amazon Bedrock Describes how LangChain can be integrated with large language models, prompt templates, chains, chat models, embedding models, document loaders, retrievers, memory, and agents for Amazon Bedrock.
- Recognize architecture patterns for generative AI applications Describes architecture patterns for text summarization, question answering, chatbot interfaces, code generation, and LangChain agent-based applications using Amazon Bedrock.
Learning modeNon-formal education
Mode of studyOnline
TypeCourse
Language of instructionPolish
The person participating in the course completed the two-day training “Developing Generative AI Applications on AWS”, focused on designing and building generative AI applications using AWS services. The course introduced the foundations of generative AI, project planning for generative AI solutions, Amazon Bedrock, foundation models, prompt engineering, generative AI application components, LangChain integration, and architecture patterns for building generative AI applications on AWS.
The learning activity covered practical approaches to using large language models without fine-tuning, including business value identification, risk and mitigation considerations, prompt engineering techniques, Amazon Bedrock use cases and architecture, inference parameters, embeddings, retrieval-augmented generation, application security, data protection, auditability, monitoring, governance, and selected implementation patterns such as text summarization, question answering, chatbots, code generation, and LangChain agent-based applications.
Contributes to achievementCompletion of the course “Developing Generative AI Applications on AWS”
Start date2026-05-27
End date2026-05-28
Learning methodOnline
Type of educational activityOnline courses
LanguagePolish
Contact hours16 hours
Organizers
Partners: 1
-
i.
CloudTeam
Want to issue digital credentials like these?
See how at credentium.com →
