AWS Agent Registry: a private catalog to stop agent sprawl
Hands-on guide to AWS Agent Registry in preview: 4 IAM personas, 8 real records, 12 gotchas, and a Claude Code demo consuming the catalog over MCP.
Sharing real-world experiences with AWS and GenAI
A space where I share learnings, challenges, and technical solutions around AWS and Generative AI. From cloud architectures to practical AI implementations, here you will find detailed technical content born from real-world experience. Let us learn and grow together as a community.
Search the blog
Featured
Real Benchmark: 5 Chunking Strategies in Amazon Bedrock Knowledge Bases
A reproducible benchmark with 25 questions, Sonnet 4.6 as generator and Nova Pro as cross-family judge. Plus the 7 problems I hit deploying this with Terraform. April 2026.
Your Coding Agent Will Never Start From Scratch Again: Session Storage in AgentCore Runtime
Every time you restart a coding agent, it loses everything: installed dependencies, generated files, project state. AgentCore Runtime Session Storage solves this with an AWS-managed persistent filesystem. Full implementation with Strands Agents and real, tested code.
Bedrock Structured Outputs: From Begging to Contract
How I migrated my AWS news agent from defensive parsing to Bedrock Structured Outputs, eliminated 130 lines of code, and cut API calls in half. The difference between asking the model to be consistent and guaranteeing it.
AgentCore Episodic Memory: When Your Agent Learns from Experience
Stop bloating your system prompt with edge cases. Discover how AgentCore Episodic Memory transforms your agent's past interactions into structured episodes and reflections that improve its performance over time. Complete implementation with boto3 and a real DevOps use case.
AgentCore Policy: Stop Your DevOps Agent from Deleting Production
Technical analysis of AgentCore Policy announced at AWS re:Invent 2025. Real implementation of deterministic control for AI agents with working code and traces.
Amazon Bedrock AgentCore Evaluations: LLM-as-a-Judge in Production
Amazon Bedrock AgentCore Evaluations: LLM-as-a-Judge with 13 built-in evaluators, continuous online monitoring, and custom evaluators. Practical guide with code.
Amazon Bedrock Automated Reasoning: Eliminate AI Hallucinations
Eliminate AI hallucinations with Bedrock Automated Reasoning Checks: formal mathematical verification for LLMs. Step-by-step tutorial with real example and precision metrics.
Amazon Bedrock + MCP: Building a Digital Forensics Assistant
Build a digital forensics AI assistant with MCP + Amazon Bedrock: auto-discovery of specialized tools, FastMCP server, and intelligent Bedrock client. Production code included.
Amazon Bedrock Session Management: AI Context Persistence
Implement conversation persistence with Amazon Bedrock Session Management APIs: maintain context across sessions with LangGraph and proven design patterns.
Automating Product Reviews with Amazon Bedrock Flows and Claude 3.5
Learn to automate product review generation using Amazon Bedrock Flows and Claude 3.5 Sonnet. Step-by-step practical guide with real examples.
Amazon Bedrock Intelligent Prompt Routing: Cut AI Costs by 94%
Bedrock Prompt Routing automatically selects the optimal model and reduces AI costs up to 94%. Step-by-step tutorial with cost analysis from the AWS console.
Amazon Bedrock Guardrails: Content Filters, PII, and Streaming
Implement Amazon Bedrock Guardrails: modular content filters, PII detection and redaction, real-time streaming, and DRAFT-to-production versioning. With code.
Amazon Bedrock Multi-Agent: AI Agent Orchestration in Production
Orchestrate specialized AI agents with Amazon Bedrock Multi-Agent: a virtual marketing team for social media content. With code and real examples.
Amazon Bedrock Agents: Building an Industrial AI Assistant
Build an industrial AI assistant with Amazon Bedrock Agents: AI-optimized APIs, technical knowledge base, and IoT integration. Real code included.
LLM + SQL: Deterministic Answers with Amazon Bedrock and Athena
Combine Amazon Bedrock with SQL in Athena for precise deterministic answers. A hybrid architecture that overcomes LLM limitations in enterprise data analysis.
Amazon Bedrock + RDS Aurora: Generative AI Inside Your MySQL Database
Integrate Amazon Bedrock with Aurora MySQL for intelligent SQL queries: a generative AI assistant inside your database. Step-by-step guide with code.
AWS Agent Registry: a private catalog to stop agent sprawl
Hands-on guide to AWS Agent Registry in preview: 4 IAM personas, 8 real records, 12 gotchas, and a Claude Code demo consuming the catalog over MCP.
Real Benchmark: 5 Chunking Strategies in Amazon Bedrock Knowledge Bases
A reproducible benchmark with 25 questions, Sonnet 4.6 as generator and Nova Pro as cross-family judge. Plus the 7 problems I hit deploying this with Terraform. April 2026.
Your Coding Agent Will Never Start From Scratch Again: Session Storage in AgentCore Runtime
Every time you restart a coding agent, it loses everything: installed dependencies, generated files, project state. AgentCore Runtime Session Storage solves this with an AWS-managed persistent filesystem. Full implementation with Strands Agents and real, tested code.
Bedrock Structured Outputs: From Begging to Contract
How I migrated my AWS news agent from defensive parsing to Bedrock Structured Outputs, eliminated 130 lines of code, and cut API calls in half. The difference between asking the model to be consistent and guaranteeing it.
AgentCore Episodic Memory: When Your Agent Learns from Experience
Stop bloating your system prompt with edge cases. Discover how AgentCore Episodic Memory transforms your agent's past interactions into structured episodes and reflections that improve its performance over time. Complete implementation with boto3 and a real DevOps use case.
AgentCore Policy: Stop Your DevOps Agent from Deleting Production
Technical analysis of AgentCore Policy announced at AWS re:Invent 2025. Real implementation of deterministic control for AI agents with working code and traces.
Hi, I'm Gerardo
Knowledge has to be improved, challenged, and constantly increased, or it vanishes -Peter Drucker
Solutions Architect, AWS Golden Jacket, with a passion for sharing knowledge. As an active AWS Community Builders member, former AWS Ambassador, and AWS User Group Leader, I dedicate myself to building bridges between technology and people. A Java developer at heart and independent consultant, I take cloud architecture beyond theory through international conferences and real-world solutions. My insatiable curiosity for learning and sharing keeps me in constant evolution alongside the tech community.