I built an iOS photo backup where your own AWS account is the backend: no servers, on-device semantic search, a Bedrock agent in your pocket, ~$0.35/month. The full architecture story is now published on AWS Builder Center.
AWS is deploying Cerebras CS-3 systems in its data centers, pairing Trainium for prefill with the Wafer Scale Engine 3 for decode. Why disaggregated inference is the right architecture, and what makes a 4-trillion-transistor chip the right tool for the decode problem.
Wafer-scale inference on Bedrock and open 3T-class models both landed this month. Neither will run your robot's control loop — but together they redraw the line between what a robot computes on-board and what it can safely delegate to the cloud.
The claim that you can't tag Bedrock calls is partly true and mostly misleading. Here are the four cost attribution mechanisms, when to use each, and the gateway pattern that unlocks per-user dollars in your bill.
AWS quietly shipped two open-source answers to two different agent problems. I deployed both, wired them together, then tried to break the architecture. Here is what holds, what doesn't, and the pattern for letting customers 'create agents' without losing governance.
From zero-percent RL success to reliable grasping via imitation learning — all in a physics sim on a MacBook, orchestrated by an LLM.
The layered AIOps pattern that displaces a legacy alert-correlation engine: CloudWatch and OpenTelemetry for telemetry, AWS DevOps Agent for autonomous RCA, ServiceNow as the system of record with write-back. Here's how the layers actually connect.
A grounded look at what agentic AI actually accelerates in a large VMware migration, where AWS Transform earns its keep, and where a human still owns the decision.
Every leadership team eventually asks how modern is our AWS estate? Here is how to answer it with one honest number, computed from Cost and Usage Report data, and how to avoid turning it into a vanity metric.
The week the agentic stack crystallized: AWS Summit NYC shipped production agent infrastructure, SpaceX bought Cursor for $60B, and humanoid robots hit their first real benchmarks.
Regulators and industry converge on agentic AI governance, Neura Robotics raises a record European round, AWS builds the agent runtime layer, and Claude Fable 5 sparks a trust crisis over invisible model routing.
Bedrock becomes the multi-model marketplace, coding tools enter their metered era, humanoid robots hit European factory floors, and Anthropic files for a near-trillion-dollar IPO.
Amazon built two radically different approaches to predicting the future — a proprietary supply chain optimization pipeline (SCOT) and an open-source time series foundation model (Chronos). This post compares their architectures, trade-offs, and when each philosophy applies.
AWS KMS can technically sign with asymmetric keys, but it speaks REST — not PKCS#11. For PKI workloads that need HSM-backed signing, key export, and multi-tenant isolation, CloudHSM's Crypto User model gives you partition-equivalent isolation without legacy constraints.
Amazon Leo Ultra delivers 1 Gbps via satellite with private networking to AWS. Here is what it concretely changes for enterprise connectivity, how it integrates with Cloud WAN and Direct Connect, and when it beats MPLS, SD-WAN, or Starlink.
AWS DevOps Agent is GA and included with Support plans. But it doesn't replace your custom agents -- it complements them. Here's the hybrid pattern: what to buy, what to build, and how MCP bridges the gap.
After a week with Amazon Quick -- a desktop AI work companion -- I'm convinced the developer workflow as we know it is dead. Here's what happened when I stopped switching between 15 tools and started orchestrating agents from a single chat.
AWS released the Agent Toolkit for AWS on May 6, 2026 -- a managed MCP server exposing the full AWS API surface to autonomous agents. I shipped an infrastructure agent the same week. Here's the two-phase safety pattern that lets you hand an agent the keys to your account without waking up to a $10K bill.
A decision framework for choosing between Amazon's Chronos-2 foundation model and custom XGBoost many-models pipelines for demand forecasting. Based on real patterns from SKU-level supply chain work.
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's restricted network. Here is what actually works in production.
Your board asks 'is our data safe in the cloud?' 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.
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.
Boulder is a meta-orchestrator that spawns AI workers on ECS Fargate to autonomously write, deploy and self-heal full-stack apps on Amplify Gen 2. Here is the architecture, the decisions, and why every serious AI agent system eventually converges on SQS + Bedrock + IAM.
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.
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.
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.
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's why this changes everything.
Weekly roundup of AWS announcements: AI Scholars program, Agent Plugin for serverless, Aurora Express setup, Lambda upgrades, Polly streaming, and more.
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%.
How to identify, clean, and monitor the hidden storage consumers that come with AI-assisted development tools like Claude Code and Kiro
AWS Verified Access is a strong ZTNA solution for internal users, but it breaks down for external contractors and partners on unmanaged devices. Here's a hybrid architecture that closes the gap with AppStream 2.0.
How Amazon Connect's native AI stack replaces fragmented CCaaS platforms with a unified, pay-per-use contact center backbone for global enterprises.
Enterprise teams invest in best-of-breed CSPM tools and still face critical IAM incidents. The gap isn't tooling — it's security governance. Here's how native AWS services fill it.
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.
Most RAG tutorials stop at 'put vectors in a database.' 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.
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.
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's Encrypt and Certbot.
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.
AWS KMS doesn't allow key material export by design. When an external PKI partner generates keys but doesn't retain them, you'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.
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.
A deep dive into the multi-agent architecture behind AWS Security Agent's automated penetration testing — from specialized agent swarms to assertion-based validation.
When your security team says 'make it private', they usually mean 'make it secure.' 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.
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.
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.
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.
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's personality.
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.
How to architect a secure, multi-tenant SFTP service across AWS accounts using Transfer Family, NLB, Transit Gateway, and per-partner S3 isolation.
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.
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.
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).
How we combined a Reachy humanoid robot with Amazon Bedrock Nova Sonic to create an AI-powered Solutions Architect for AWS Summits
EBS snapshot costs were growing month-over-month with no clear explanation or optimization strategy.
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.
A practical guide to building generative AI applications with Amazon Bedrock
Enterprise workflows often require interacting with web applications that lack APIs. Traditional automation scripts are brittle and break when UIs change.
Building a production forecasting application without the complexity of traditional ML model training and feature engineering.