<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Alexandre Agius Blog</title><description>AWS Solutions Architect passionate about AI &amp; Security</description><link>https://www.agiusalexandre.com/</link><item><title>AWS Weekly Roundup — February 2026: AgentCore, Bedrock, EC2 and More</title><link>https://www.agiusalexandre.com/blog/2026-02-22-aws-news-weekly-roundup-february-2026/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-22-aws-news-weekly-roundup-february-2026/</guid><description>A curated summary of the most important AWS announcements from February 2026 — from Bedrock AgentCore deep dives to new EC2 instances and the European Sovereign Cloud.</description><pubDate>Sun, 22 Feb 2026 00:00:00 GMT</pubDate></item><item><title>TFLOPS: The GPU Metric Every AI Engineer Should Understand</title><link>https://www.agiusalexandre.com/blog/2026-02-24-tflops-gpu-metric-ai-engineers/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-24-tflops-gpu-metric-ai-engineers/</guid><description>What TFLOPS actually measures, why FP16 matters for LLMs, and why the most important GPU bottleneck for inference isn&apos;t compute at all.</description><pubDate>Tue, 24 Feb 2026 00:00:00 GMT</pubDate></item><item><title>A $13.5K Open-Source Humanoid Robot: Inside Unitree G1&apos;s AI Stack</title><link>https://www.agiusalexandre.com/blog/2026-02-14-unitree-g1-open-source-humanoid-robot/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-14-unitree-g1-open-source-humanoid-robot/</guid><description>Unitree ships a humanoid robot with 43 degrees of freedom, a full AI training pipeline on GitHub, and Apple Vision Pro teleoperation — for $13.5K. Here&apos;s what the developer ecosystem looks like.</description><pubDate>Sat, 14 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Getting Hands-On with Mistral AI: From API to Self-Hosted in One Afternoon</title><link>https://www.agiusalexandre.com/blog/2026-02-24-getting-hands-on-with-mistral-ai/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-24-getting-hands-on-with-mistral-ai/</guid><description>A practical walkthrough of two paths to working with Mistral — the managed API for fast prototyping and self-hosted deployment for full control — with real code covering prompting, model selection, function calling, RAG, and INT8 quantization.</description><pubDate>Tue, 24 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Transformer Anatomy: Attention + FFN Demystified</title><link>https://www.agiusalexandre.com/blog/2026-02-23-transformer-anatomy-attention-ffn-demystified/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-23-transformer-anatomy-attention-ffn-demystified/</guid><description>A deep dive into the Transformer architecture — how attention connects tokens and why the Feed-Forward Network is the real brain of the model. Plus the key to understanding Mixture of Experts (MoE).</description><pubDate>Mon, 23 Feb 2026 00:00:00 GMT</pubDate></item><item><title>OpenClaw vs NanoBot vs PicoClaw vs TinyClaw: Four Approaches to Self-Hosted AI Assistants</title><link>https://www.agiusalexandre.com/blog/2026-02-15-openclaw-nanobot-picoclaw-tinyclaw-self-hosted-ai-assistants/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-15-openclaw-nanobot-picoclaw-tinyclaw-self-hosted-ai-assistants/</guid><description>A deep architectural comparison of four open-source frameworks that turn messaging apps into AI assistant interfaces — from a 349-file TypeScript monolith to a 10MB Go binary that runs on a $10 board.</description><pubDate>Wed, 04 Mar 2026 00:00:00 GMT</pubDate></item><item><title>LLM Distillation vs Quantization: Making Models Smaller, Smarter, Cheaper</title><link>https://www.agiusalexandre.com/blog/2026-02-25-llm-distillation-vs-quantization-practical-guide/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-25-llm-distillation-vs-quantization-practical-guide/</guid><description>Two strategies to shrink LLMs — one compresses weights, the other transfers knowledge. A practical guide to distillation and quantization: when to use each, how to implement them with Hugging Face, and why the real answer is both.</description><pubDate>Wed, 25 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Python, Transformers, and SageMaker: A Practical Guide for Cloud Engineers</title><link>https://www.agiusalexandre.com/blog/2026-02-24-python-transformers-sagemaker-practical-guide/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-24-python-transformers-sagemaker-practical-guide/</guid><description>Everything a cloud/AWS engineer needs to know about Python, the Hugging Face Transformers framework, SageMaker integration, quantization, CUDA, and AWS Inferentia — without being a data scientist.</description><pubDate>Tue, 24 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Fine-Tuning Mistral with Transformers and Serving with vLLM on AWS</title><link>https://www.agiusalexandre.com/blog/2026-02-22-fine-tuning-mistral-vllm-aws/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-22-fine-tuning-mistral-vllm-aws/</guid><description>End-to-end guide: fine-tune Mistral models with LoRA using Hugging Face Transformers, then deploy at scale with vLLM on AWS — from training to production serving on SageMaker, ECS, or Bedrock.</description><pubDate>Sun, 22 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Deploying a Personal AI Assistant on AWS with Bedrock AgentCore Runtime</title><link>https://www.agiusalexandre.com/blog/2026-02-22-deploying-personal-ai-assistant-aws-bedrock-agentcore/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-22-deploying-personal-ai-assistant-aws-bedrock-agentcore/</guid><description>A hands-on walkthrough of deploying OpenClaw on AWS using AgentCore Runtime for serverless agent execution, Graviton ARM instances, and multi-model Bedrock access — from CloudFormation template to customizing the agent&apos;s personality.</description><pubDate>Sun, 22 Feb 2026 00:00:00 GMT</pubDate></item><item><title>LLM Architecture Explained Simply: 10 Questions From Prompt to Token</title><link>https://www.agiusalexandre.com/blog/2026-02-26-llm-architecture-explained-simply-from-prompt-to-token/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-26-llm-architecture-explained-simply-from-prompt-to-token/</guid><description>A beginner-friendly walkthrough of how an LLM actually works end-to-end: from typing a prompt to receiving a response — covering tokenization, embeddings, Transformer layers, KV cache, the training loop, embeddings for search, and why decoder-only models won.</description><pubDate>Thu, 26 Feb 2026 00:00:00 GMT</pubDate></item><item><title>LLM Inference Demystified: PagedAttention, KV Cache, MoE &amp; Continuous Batching</title><link>https://www.agiusalexandre.com/blog/2026-02-26-llm-inference-demystified-pagedattention-kv-cache-moe-continuous-batching/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-26-llm-inference-demystified-pagedattention-kv-cache-moe-continuous-batching/</guid><description>The 5 key concepts every cloud architect should know about LLM serving: PagedAttention, KV cache mechanics, continuous batching, MoE trade-offs, and real production numbers.</description><pubDate>Thu, 26 Feb 2026 00:00:00 GMT</pubDate></item><item><title>MPLS vs SD-WAN vs CloudWAN: Enterprise Networking Explained Simply</title><link>https://www.agiusalexandre.com/blog/2026-02-26-mpls-vs-sd-wan-vs-cloudwan-explained-simply/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-26-mpls-vs-sd-wan-vs-cloudwan-explained-simply/</guid><description>A visual, jargon-free guide comparing MPLS, SD-WAN, and AWS CloudWAN for enterprise networking — with analogies, comparison tables, and an architecture diagram showing how the three layers connect.</description><pubDate>Thu, 26 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Your Security Team Wants to Privatize Your App — Here&apos;s What They Actually Need</title><link>https://www.agiusalexandre.com/blog/2026-02-27-zero-trust-vs-network-privatization-aws/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-02-27-zero-trust-vs-network-privatization-aws/</guid><description>When your security team says &apos;make it private&apos;, they usually mean &apos;make it secure.&apos; This post compares four approaches — VPC privatization, WAF IP allowlisting, CloudFront + auth hardening, and AWS Verified Access — and explains why Zero Trust beats network perimeters for internal applications.</description><pubDate>Fri, 27 Feb 2026 00:00:00 GMT</pubDate></item><item><title>World Monitor: How Open-Source OSINT Is Democratizing Global Intelligence</title><link>https://www.agiusalexandre.com/blog/2026-03-01-worldmonitor-open-source-osint-dashboard/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-01-worldmonitor-open-source-osint-dashboard/</guid><description>A deep dive into World Monitor — an open-source intelligence dashboard that aggregates 150+ feeds, 40+ geospatial layers, and AI-powered analysis into a real-time situational awareness platform. What OSINT is, how these platforms work under the hood, and why it matters now more than ever.</description><pubDate>Sun, 01 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Inside AWS Security Agent: How Multi-Agent Systems Automate Penetration Testing</title><link>https://www.agiusalexandre.com/blog/2026-03-02-aws-security-agent-multi-agent-penetration-testing/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-02-aws-security-agent-multi-agent-penetration-testing/</guid><description>A deep dive into the multi-agent architecture behind AWS Security Agent&apos;s automated penetration testing — from specialized agent swarms to assertion-based validation.</description><pubDate>Mon, 02 Mar 2026 00:00:00 GMT</pubDate></item><item><title>The RISEN Framework: Writing System Prompts That Actually Work for AI Agents</title><link>https://www.agiusalexandre.com/blog/2026-03-02-risen-framework-claude-code-system-prompts/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-02-risen-framework-claude-code-system-prompts/</guid><description>A 5-component framework for writing effective system prompts for any AI agent — Bedrock Agents, Claude Code, LangChain, Strands, or custom builds. With a practical Claude Code implementation.</description><pubDate>Mon, 02 Mar 2026 00:00:00 GMT</pubDate></item><item><title>When Your Keys Get Locked In: Navigating AWS KMS Import Limitations</title><link>https://www.agiusalexandre.com/blog/2026-03-05-aws-kms-key-locked-in-cloudhsm-xks-private-ca/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-05-aws-kms-key-locked-in-cloudhsm-xks-private-ca/</guid><description>AWS KMS doesn&apos;t allow key material export by design. When an external PKI partner generates keys but doesn&apos;t retain them, you&apos;re stuck. Here are the four AWS alternatives — CloudHSM, XKS, Private CA, and fixing the process — with a decision framework to pick the right one.</description><pubDate>Thu, 05 Mar 2026 00:00:00 GMT</pubDate></item><item><title>HTTPS on AWS Lightsail: Setting Up Let&apos;s Encrypt with Apache and Route 53</title><link>https://www.agiusalexandre.com/blog/2026-03-07-https-lightsail-letsencrypt-apache-route53/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-07-https-lightsail-letsencrypt-apache-route53/</guid><description>Step-by-step guide to configuring a custom subdomain with Route 53 and securing an AWS Lightsail instance with a free TLS certificate using Let&apos;s Encrypt and Certbot.</description><pubDate>Sat, 07 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Migrating 180+ Public Certificates to AWS ACM Exportable Certificates</title><link>https://www.agiusalexandre.com/blog/2026-03-07-migrating-public-certificates-aws-acm-exportable/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-07-migrating-public-certificates-aws-acm-exportable/</guid><description>A practical guide to replacing a third-party CA with ACM exportable public certificates — covering pricing, automation patterns, industry validity changes, and the gotchas nobody mentions.</description><pubDate>Sat, 07 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Building a RAG System That Actually Works: Chunking, Vector Engines, and Testing</title><link>https://www.agiusalexandre.com/blog/2026-03-10-rag-chunking-testing-vector-engines/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-10-rag-chunking-testing-vector-engines/</guid><description>Most RAG tutorials stop at &apos;put vectors in a database.&apos; This post covers what actually determines quality: how you chunk documents, which vector search engine to pick, and how to measure and iterate on retrieval performance using Bedrock Knowledge Bases and LLM-as-judge evaluation.</description><pubDate>Tue, 10 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Vector Search vs Semantic Search: They&apos;re Not the Same Thing</title><link>https://www.agiusalexandre.com/blog/2026-03-10-vector-search-vs-semantic-search/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-10-vector-search-vs-semantic-search/</guid><description>Vector search, semantic search, keyword search, hybrid search — these terms get used interchangeably but they mean different things. This post breaks down what each actually does, when each matters, and why hybrid search wins for RAG.</description><pubDate>Tue, 10 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Securing Active Directory on AWS: A Practical Guide to AD Tiering with ANSSI and AWS SRA Alignment</title><link>https://www.agiusalexandre.com/blog/2026-03-12-securing-active-directory-on-aws-tiering-anssi-sra/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-12-securing-active-directory-on-aws-tiering-anssi-sra/</guid><description>How to map the ANSSI AD tiering model onto AWS, why Managed AD may not be enough for Tier 0, and which AWS security services close the compliance gaps.</description><pubDate>Thu, 12 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Why Amazon Connect Is an AI Platform That Happens to Handle Phone Calls</title><link>https://www.agiusalexandre.com/blog/2026-03-16-amazon-connect-ai-platform-contact-center/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-16-amazon-connect-ai-platform-contact-center/</guid><description>How Amazon Connect&apos;s native AI stack replaces fragmented CCaaS platforms with a unified, pay-per-use contact center backbone for global enterprises.</description><pubDate>Mon, 16 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Your CSPM Won&apos;t Save You — Why Cloud Security Is a Governance Problem</title><link>https://www.agiusalexandre.com/blog/2026-03-16-your-cspm-wont-save-you-cloud-security-governance/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-16-your-cspm-wont-save-you-cloud-security-governance/</guid><description>Enterprise teams invest in best-of-breed CSPM tools and still face critical IAM incidents. The gap isn&apos;t tooling — it&apos;s security governance. Here&apos;s how native AWS services fill it.</description><pubDate>Mon, 16 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Your ZTNA Strategy Has a Blind Spot — External Users Need a Different Approach</title><link>https://www.agiusalexandre.com/blog/2026-03-17-ztna-blind-spot-external-users-need-different-approach/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-17-ztna-blind-spot-external-users-need-different-approach/</guid><description>AWS Verified Access is a strong ZTNA solution for internal users, but it breaks down for external contractors and partners on unmanaged devices. Here&apos;s a hybrid architecture that closes the gap with AppStream 2.0.</description><pubDate>Tue, 17 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Strands Agents Steering Plugins — How Just-in-Time Guidance Beats Prompts and Workflows</title><link>https://www.agiusalexandre.com/blog/2026-03-20-strands-steering-plugins-accuracy-beats-prompts/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-20-strands-steering-plugins-accuracy-beats-prompts/</guid><description>Strands Agents plugins let you intercept every decision in the agentic loop. Steering hooks achieved 100% accuracy across 600 evaluation runs — where prompt engineering scored 82.5% and graph workflows 80.8%.</description><pubDate>Fri, 20 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Chemistry LLMs in the Real World: What a Discovery Call Taught Me About AI in Chemical R&amp;D</title><link>https://www.agiusalexandre.com/blog/2026-03-24-chemistry-llms-real-world-ai-chemical-rd/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-03-24-chemistry-llms-real-world-ai-chemical-rd/</guid><description>A discovery call with a global specialty chemicals company revealed that the real AI bottleneck isn&apos;t models — it&apos;s data. Here&apos;s what enterprise chemistry teams actually need versus what the hype promises.</description><pubDate>Tue, 24 Mar 2026 00:00:00 GMT</pubDate></item><item><title>How the Orchestrator Works — The AI Agent That Never Works Alone</title><link>https://www.agiusalexandre.com/blog/2026-04-03-how-sisyphus-works-ai-orchestrator/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-03-how-sisyphus-works-ai-orchestrator/</guid><description>The Orchestrator is an AI agent that delegates ALL work to specialized subagents. Here&apos;s the architectural philosophy behind why specialization beats generalization in AI agent systems.</description><pubDate>Fri, 03 Apr 2026 00:00:00 GMT</pubDate></item><item><title>AWS Weekly Digest — Week 14, 2026: AI Scholars, Agent Plugin for Serverless, Aurora Express, and Lambda Upgrades</title><link>https://www.agiusalexandre.com/blog/2026-04-05-aws-weekly-digest-w14-2026/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-05-aws-weekly-digest-w14-2026/</guid><description>Weekly roundup of AWS announcements: AI Scholars program, Agent Plugin for serverless, Aurora Express setup, Lambda upgrades, Polly streaming, and more.</description><pubDate>Sun, 05 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Claude Mythos &amp; Project Glasswing — When AI Finds Zero-Days in Everything</title><link>https://www.agiusalexandre.com/blog/2026-04-08-anthropic-mythos-glasswing-cybersecurity-ai/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-08-anthropic-mythos-glasswing-cybersecurity-ai/</guid><description>Anthropic just dropped a model that autonomously finds and exploits zero-days in every major OS and browser. Then they built an industry coalition to use it defensively. Here&apos;s why this changes everything.</description><pubDate>Wed, 08 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Boulder — An AI Build Factory on AWS That Generates, Deploys, and Maintains Apps on Its Own</title><link>https://www.agiusalexandre.com/blog/2026-04-20-boulder-ai-build-factory-aws/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-20-boulder-ai-build-factory-aws/</guid><description>Boulder uses 9 Strands agents on Bedrock AgentCore to generate, deploy, and maintain full-stack apps on AWS Amplify — with self-healing builds and self-improving prompts.</description><pubDate>Mon, 20 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Browser Automation Agents - Amazon Bedrock AgentCore</title><link>https://www.agiusalexandre.com/blog/agentcore-browser-automation/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/agentcore-browser-automation/</guid><description>Enterprise workflows often require interacting with web applications that lack APIs. Traditional automation scripts are brittle and break when UIs change.</description><pubDate>Wed, 14 Jan 2026 00:00:00 GMT</pubDate></item><item><title>How to Build an AI Executive Assistant That Never Forgets with Claude Code</title><link>https://www.agiusalexandre.com/blog/ai-executive-assistant-claude-code/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/ai-executive-assistant-claude-code/</guid><description>Turn Claude Code into a persistent executive assistant with morning briefings, auto-logging, context-aware reminders, complex skills, and a memory that compounds over time — using only markdown files.</description><pubDate>Thu, 26 Feb 2026 00:00:00 GMT</pubDate></item><item><title>AWS Backup Cost Analysis</title><link>https://www.agiusalexandre.com/blog/aws-backup-cost-analysis/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/aws-backup-cost-analysis/</guid><description>EBS snapshot costs were growing month-over-month with no clear explanation or optimization strategy.</description><pubDate>Mon, 26 Jan 2026 00:00:00 GMT</pubDate></item><item><title>How to Track and Cap AI Spending per Team with Amazon Bedrock</title><link>https://www.agiusalexandre.com/blog/bedrock-cost-control-inference-profiles/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/bedrock-cost-control-inference-profiles/</guid><description>AI platform teams need governance before scaling. Learn how to use Amazon Bedrock inference profiles, AWS Budgets, and a proactive cost control pattern to track, allocate, and cap AI spending per team.</description><pubDate>Fri, 06 Feb 2026 00:00:00 GMT</pubDate></item><item><title>How I Built This Blog with AI-DLC: A New Way to Develop Software with AI</title><link>https://www.agiusalexandre.com/blog/building-with-ai-dlc/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/building-with-ai-dlc/</guid><description>Discover AI-DLC (AI Development Lifecycle), a structured framework for AI-assisted software development. Learn how I used it to build this blog from scratch and how it enables continuous iteration.</description><pubDate>Mon, 26 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Time Series Forecasting App - Amazon Chronos-2</title><link>https://www.agiusalexandre.com/blog/chronos-time-series-forecasting/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/chronos-time-series-forecasting/</guid><description>Building a production forecasting application without the complexity of traditional ML model training and feature engineering.</description><pubDate>Wed, 14 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Cloud Sovereignty Deep Dive - AWS KMS Control Plane Analysis</title><link>https://www.agiusalexandre.com/blog/cloud-sovereignty-kms/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/cloud-sovereignty-kms/</guid><description>XKS protects key material from extraction, but does it protect against legal compulsion to use those keys? Updated with AWS European Sovereign Cloud (GA January 2026).</description><pubDate>Wed, 04 Feb 2026 00:00:00 GMT</pubDate></item><item><title>From Seed Round to Stock Exchange — Understanding IPOs When You&apos;re Not a Finance Person</title><link>https://www.agiusalexandre.com/blog/from-seed-round-to-stock-exchange-understanding-ipos/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/from-seed-round-to-stock-exchange-understanding-ipos/</guid><description>A tech worker&apos;s guide to IPOs, startup valuations, equity compensation, and what it actually means when you join a pre-IPO company.</description><pubDate>Sun, 01 Mar 2026 00:00:00 GMT</pubDate></item><item><title>Getting Started with Amazon Bedrock</title><link>https://www.agiusalexandre.com/blog/getting-started-with-bedrock/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/getting-started-with-bedrock/</guid><description>A practical guide to building generative AI applications with Amazon Bedrock</description><pubDate>Sun, 25 Jan 2026 00:00:00 GMT</pubDate></item><item><title>A Practical Guide to Fine-Tuning LLMs: From Full Training to LoRA</title><link>https://www.agiusalexandre.com/blog/fine-tuning-llms-practical-guide/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/fine-tuning-llms-practical-guide/</guid><description>Understand how LLM fine-tuning works, when to use it, and how to choose between full fine-tuning, LoRA, soft prompts, and other PEFT methods.</description><pubDate>Sat, 07 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Managing Local Storage in the AI Development Era</title><link>https://www.agiusalexandre.com/blog/managing-local-storage-ai-development-era/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/managing-local-storage-ai-development-era/</guid><description>How to identify, clean, and monitor the hidden storage consumers that come with AI-assisted development tools like Claude Code and Kiro</description><pubDate>Fri, 20 Mar 2026 00:00:00 GMT</pubDate></item><item><title>RAG on AWS: Which Vector Store Is Right for You?</title><link>https://www.agiusalexandre.com/blog/rag-aws-vector-store-guide/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/rag-aws-vector-store-guide/</guid><description>AWS now offers 9 different ways to store and search vectors for RAG workloads. This guide compares every option through the Well-Architected Framework to help you pick the right one.</description><pubDate>Mon, 09 Feb 2026 00:00:00 GMT</pubDate></item><item><title>Building ReachyArchi: A Voice-Driven Robotic AWS Solutions Architect</title><link>https://www.agiusalexandre.com/blog/reachyarchi-voice-robot-architect/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/reachyarchi-voice-robot-architect/</guid><description>How we combined a Reachy humanoid robot with Amazon Bedrock Nova Sonic to create an AI-powered Solutions Architect for AWS Summits</description><pubDate>Thu, 29 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Replacing Legacy SFTP with AWS Transfer Family in a Multi-Account Landing Zone</title><link>https://www.agiusalexandre.com/blog/replacing-legacy-sftp-transfer-family-multi-account/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/replacing-legacy-sftp-transfer-family-multi-account/</guid><description>How to architect a secure, multi-tenant SFTP service across AWS accounts using Transfer Family, NLB, Transit Gateway, and per-partner S3 isolation.</description><pubDate>Fri, 13 Feb 2026 00:00:00 GMT</pubDate></item><item><title>How LLMs Learn to Behave: RLHF, Reward Models, and the Alignment Problem</title><link>https://www.agiusalexandre.com/blog/rlhf-reward-models-alignment/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/rlhf-reward-models-alignment/</guid><description>A practical walkthrough of how large language models are aligned with human values — from collecting feedback to PPO optimization and the reward hacking pitfalls.</description><pubDate>Mon, 09 Feb 2026 00:00:00 GMT</pubDate></item><item><title>SEO Enhancement - agiusalexandre.com</title><link>https://www.agiusalexandre.com/blog/seo-enhancement/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/seo-enhancement/</guid><description>Blog posts weren&apos;t appearing correctly in search results or showing rich previews when shared on social media.</description><pubDate>Mon, 26 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Tag Filtering - agiusalexandre.com</title><link>https://www.agiusalexandre.com/blog/tag-filtering/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/tag-filtering/</guid><description>Blog readers needed a way to browse content by topic instead of scrolling through all posts.</description><pubDate>Mon, 26 Jan 2026 00:00:00 GMT</pubDate></item><item><title>Cloud WAN vs Transit Gateway — 3 Things It Actually Adds, 5 Things It Does Not</title><link>https://www.agiusalexandre.com/blog/2026-04-09-cloud-wan-vs-transit-gateway-honest-assessment/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-09-cloud-wan-vs-transit-gateway-honest-assessment/</guid><description>Cloud WAN promises centralized global networking. At a 30 percent premium over Transit Gateway, what do you actually get, and what are the common misconceptions? Here is the honest technical and financial analysis.</description><pubDate>Thu, 09 Apr 2026 00:00:00 GMT</pubDate></item><item><title>From RPA Bots to AI Agents — A 5-Criterion Scoring Framework for Enterprise Migration</title><link>https://www.agiusalexandre.com/blog/2026-04-21-rpa-to-agentic-ai-scoring-framework/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-21-rpa-to-agentic-ai-scoring-framework/</guid><description>Your RPA estate has 50 bots. Some should become AI agents, some should stay as bots, some need a hybrid pattern. Here is a repeatable, weighted scoring rubric — and the 5 migration patterns it maps to.</description><pubDate>Tue, 21 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Cloud Sovereignty for the Board — A 3-Tier Architecture That Maps Data Sensitivity to Control Level</title><link>https://www.agiusalexandre.com/blog/2026-04-23-cloud-sovereignty-3-tier-architecture/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-23-cloud-sovereignty-3-tier-architecture/</guid><description>Your board asks &apos;is our data safe in the cloud?&apos; The answer is not yes or no — it is a classification decision that maps each workload to the right control tier. Here is the framework, with the metadata exposure gap most teams miss.</description><pubDate>Thu, 23 Apr 2026 00:00:00 GMT</pubDate></item><item><title>The Cloud Trust Scorecard — 8 KPIs to Bridge the CIO-CFO Gap on Cloud Value</title><link>https://www.agiusalexandre.com/blog/2026-04-23-cloud-trust-scorecard-cio-cfo-kpis/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-23-cloud-trust-scorecard-cio-cfo-kpis/</guid><description>Your CFO asks &apos;is our cloud well-run?&apos; You need one dashboard, eight numbers, and zero jargon. Here is the framework: 4 money KPIs + 4 risk KPIs = Trust. With specific formulas, targets, and what to explicitly exclude.</description><pubDate>Thu, 23 Apr 2026 00:00:00 GMT</pubDate></item><item><title>SageMaker Unified Studio — The DataZone Migration Decision Framework for Data Engineers</title><link>https://www.agiusalexandre.com/blog/2026-04-20-sagemaker-unified-studio-datazone-migration-decision/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-20-sagemaker-unified-studio-datazone-migration-decision/</guid><description>Your DataZone environment works. AWS says SMUS is the future. Do you upgrade, go greenfield, or wait? Here is the coverage matrix, the 70–85 percent pipeline replacement reality, and the multi-account mesh architecture you actually need.</description><pubDate>Mon, 20 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Agentic Data Governance — Building a Multi-Platform Access Broker with Bedrock Agents</title><link>https://www.agiusalexandre.com/blog/2026-04-22-agentic-data-governance-architecture-aws/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-22-agentic-data-governance-architecture-aws/</guid><description>Your data lives in AWS, Databricks, and Microsoft Fabric. Your business glossary is in Collibra. Users just want to find data and get access. Here is an agentic architecture that makes governance the default instead of the blocker.</description><pubDate>Wed, 22 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Overlapping CIDRs in Cross-Account Kubernetes Migrations — Why PrivateLink Resource Endpoints Change Everything</title><link>https://www.agiusalexandre.com/blog/2026-04-10-privatelink-resource-endpoints-overlapping-cidrs/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-10-privatelink-resource-endpoints-overlapping-cidrs/</guid><description>You are migrating microservices between Kubernetes clusters across AWS accounts, but the source uses /16 CIDRs that collide with corporate. The 2022 playbook (Private NAT Gateway + NLB per service) is obsolete. Here is what re:Invent 2024 gave us.</description><pubDate>Fri, 10 Apr 2026 00:00:00 GMT</pubDate></item><item><title>Linux Package Management in AWS China Regions — RHUI, Squid Proxies, and What EPEL Cannot Do</title><link>https://www.agiusalexandre.com/blog/2026-04-24-linux-repos-aws-china-rhel-rhui-proxy/</link><guid isPermaLink="true">https://www.agiusalexandre.com/blog/2026-04-24-linux-repos-aws-china-rhel-rhui-proxy/</guid><description>You have RHEL 9 instances in AWS China regions managed via SSM. Installing PostgreSQL 17 or EPEL packages means opening dozens of dynamic URLs through China&apos;s restricted network. Here is what actually works in production.</description><pubDate>Fri, 24 Apr 2026 00:00:00 GMT</pubDate></item></channel></rss>