☁️ Welcome to YZ's Blog

🤖 Optimizing enterprise AI assistants: How Crypto.com uses LLM reasoning and feedback for enhanced efficiency

☁️ Build modern serverless solutions following best practices using Amazon Q Developer CLI and MCP

🤖 Build an intelligent eDiscovery solution using Amazon Bedrock Agents

🤖 How PerformLine uses prompt engineering on Amazon Bedrock to detect compliance violations

☁️ Boost cold-start recommendations with vLLM on AWS Trainium

🤖 Benchmarking Amazon Nova: A comprehensive analysis through MT-Bench and Arena-Hard-Auto

🤖 Customize Amazon Nova in Amazon SageMaker AI using Direct Preference Optimization

🤖 Multi-tenant RAG implementation with Amazon Bedrock and Amazon OpenSearch Service for SaaS using JWT

☁️ Enhance generative AI solutions using Amazon Q index with Model Context Protocol – Part 1

🤖 Beyond accelerators: Lessons from building foundation models on AWS with Japan’s GENIAC program