Bedrock Prompt Shortening: 6 optimizations, 0 changes, a fake +45%
I tested Bedrock's shortenPrompt on my agent's real prompt across three models: it returned the original six times and reported a +45% gain with no change.
Latest articles
Every article I've published in English, newest first.
2026
Temporal Policies in AgentCore: 98 Denied Deploys and a 409 That Never Came
I tested AgentCore Temporal Policies with 5,294 calls: an agent that parallelizes loses its deploy, denials burn your limit, and the 409 never arrives.
I Took the Wheel Off My RAG: Managed KB vs. Manual Chunking
Managed Knowledge Base ties my manual chunking setup, but AgenticRetrieveStream's default planner never decomposed a single query across 80 evaluated questions.
I Let AWS Rewrite My DevOps Agent's Prompt: 142 Sessions, +6.2%, and a p-value of 0.38
AgentCore Optimization closes the observe → evaluate → improve loop. I ran the full loop on my DevOps agent: recommendation, A/B test, and the gotchas.
Lambda MicroVMs vs AgentCore Runtime: When to Use Each for Production Agents
AWS launched Lambda MicroVMs: isolated Firecracker VMs, state up to 8h. Is it the same as AgentCore Runtime? A decision guide for CTOs and cloud architects.
AgentCore Payments: When Your Agent Has Its Own Wallet
AgentCore Payments gives your agent its own wallet. I ran the x402 flow on a real AWS account: code, spend limits, and 4 gotchas before the first on-chain tx.
AWS Agent Registry: a private catalog to stop agent sprawl
Hands-on guide to AWS Agent Registry, now generally available (GA): 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.
2025
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.
2024
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.
2021
AWS S3 Presigned URLs: How to Generate and Use Signed URLs with Java (SDK v2)
Generate S3 Presigned URLs with AWS SDK Java v2 (S3Presigner): secure upload and download without exposing credentials. Duration, security, and v1 migration.