courseraАнализ данных

Gen AI Dev- Safe User Interactions with Gen AI Applications

Курс от Amazon Web Services

Продвинутый≈ 1.8 чАнглийский

О курсе

Welcome to the third part of this learning plan centered around the role and responsibilities of a generative AI professional developer.In part two, you learned how to implement Agentic AI solutions and tools. You also learned about AI agents, how they work, make decisions, and take actions.In this part, you'll learn about security, governance, and compliance when working with your AI applications, and work with AI-assisted development tools.

Навыки, которые вы освоите

Artificial Intelligence and Machine Learning (AI/ML)Generative AI IT Security Architecture Retrieval-Augmented Generation Machine Learning Prompt Engineering Amazon Web Services Natural Language Processing Generative AI Agents Security Controls Data Validation Artificial Intelligence Data Governance Model Evaluation Cloud Computing Verification And Validation Agentic systems Cybersecurity Software Development

Программа курса

6 модулей · 61 учебных материалов

01Introduction5 материалов

Part 3 Introduction

WelcomeЧтение

Course Introduction

OverviewЧтение Purpose of Content Input FilteringЧтение First line of defenseЧтение

Учитесь у экспертов

AWS Instructor

Преподаватель курса

Gen AI Dev- Safe User Interactions with Gen AI Applications

О курсе

Навыки, которые вы освоите

Программа курса

Part 3 Introduction

Course Introduction

Учитесь у экспертов

AWS Instructor

Amazon Bedrock Guardrails

AWS Step Functions and Lambda for Custom Moderation Workflows

Prompt Injections and Real-Time Validation Mechanisms

Model Response Filtering Purpose and Techniques

Output Response filtering with Amazon Bedrock Guardrails

Content Moderation and Toxicity Detection

Text-to-SQL Transformations to Prevent Harmful Outputs

Grounding and Fact-Checking Responses with Amazon BedRock KB

Semantic Similarity Searches for Verification

Enforce Structured Outputs with JSON Schema

Benefits of Multilayer Content Safety Architectures

Summary

We want to hear from you