标签：#AWS

devtools #infrastructureascode #cdk #aws Index TL;DR Major Features Bedrock AgentCore — From Alpha to Stable Fn::GetStackOutput & Weak Cross-Stack References Validations Framework Performance Improvements CloudWatch PromQL Alarms CLI Improvements New L2 Constructs Service Enhancements Community Highlights Community Content & Resources How Can You Be Involved Hey CDK community! Here's an update covering everything that shipped in April and May 2026. TL;DR Bedrock AgentCore graduated to stable — production-ready AI agent infrastructure with semver guarantees. Cross-region references got a major upgrade with native Fn::GetStackOutput support and weak cross-stack references. The new Validations framework replaces policyValidationBeta1 with a richer plugin system. And file fingerprinting is ~33% faster with persistent asset caching. These features are available in aws-cdk-lib v2.247.0 through v2.257.0 and aws-cdk CLI v2.1116.0 through v2.1125.0. Full changelogs on GitHub Releases ( Library | CLI ). Major Features Bedrock AgentCore — From Alpha to Stable The @aws-cdk/aws-bedrock-agentcore-alpha module has graduated to aws-cdk-lib/aws-bedrockagentcore — stable APIs, semver guarantees, production-ready. If you've been building AI agents with Bedrock but held off on CDK because of the alpha label, it's time to upgrade. ( #37876 ) AgentCore provides the core infrastructure for building AI agents: runtimes, gateways, identity management, observability, and online evaluation. The Policy submodule remains in alpha as it continues to evolve rapidly. ┌─────────────────────────────────────────────────────┐ │ Bedrock AgentCore (Stable) │ ├─────────────────────────────────────────────────────┤ │ │ │ ┌──────────┐ ┌──────────┐ ┌──────────────────┐ │ │ │ Runtime │ │ Gateway │ │ Identity │ │ │ │ (L2) │ │ (L2) │ │ (L2) │ │ │ └────┬─────┘ └────┬─────┘ └────────┬─────────┘ │ │ │ │ │ │ │ ▼ ▼ ▼ │ │ ┌──────────┐ ┌──────────┐ ┌──────────────────┐ │ │ │Observa- │ │Online │ │ Policy Engine │ │ │

Jump Tables, TLV Footers, and the Real Cost of Reading What You Don't Need You're paying for bytes you never read. A data engineer on a busy pipeline touches dozens of Parquet files a day: schema discovery, predicate pushdown, column pruning, metadata scrapes for a data catalog sync. In each case, the application needs maybe 200 KB of context from a file that is 4 GB on disk. Without a seekable archive format and a jump table to find the right frame, your HTTP client fetches the whole thing, and your cloud egress invoice reflects every unnecessary gigabyte. This post quantifies the problem, then walks through how HuskHoard uses seekable Zstd frames, a per-volume jump table, and TLV-encoded footer metadata to make partial egress a first-class citizen across multi-volume archives — disk, cloud, and LTO tape alike. The Problem, In Dollars S3 standard egress runs $0.09/GB. GCS is $0.08/GB. Even Cloudflare R2, which is free for egress from R2 to the internet , still costs you in latency and API call count when you cannot bound the range of bytes you need. Here is a representative read pattern for a cold analytics archive: Operation Bytes Needed Bytes Fetched (naïve) Ratio Schema discovery ~50 KB (Parquet footer) 1–8 GB (full file) ~1:16,000 Single column scan ~200 MB (one column chunk) 4 GB (full row group) 1:20 Data catalog sync (1M files) ~50 GB (footers only) ~4 PB (full files) 1:80,000 Selective restore (1 row group) ~128 MB 4 GB 1:32 On 100 TB of cold Parquet data with $0.09/GB egress: Full read for schema sync : 100 TB × $0.09 = $9,216 Partial read (footers only, avg 100 KB/file, 1M files) : ~100 GB × $0.09 = $9.00 Savings per catalog sync: $9,207 — 99.9% reduction Even a conservative column-scan scenario (pulling 15% of each file's bytes) cuts a $9,216 monthly read bill to $1,382 . The ceiling on savings is determined entirely by how precisely you can address the bytes you actually need. That precision is what frames and jump tables buy you. Zstd Frames: What They

Last year I was asked to investigate a startup's AWS bill. It had jumped from roughly $200/month to over $3,000 in a few weeks. Nobody knew why. After digging through logs, metrics, and database traffic, I found the culprit: a polling loop with no backoff strategy. The code looked harmless: async function processQueue () { const jobs = await getJobs () for ( const job of jobs ) { await processFile ( job ) } processQueue () } processQueue () At first glance, this seems reasonable. Process all available jobs, then check again. The problem appears when the queue is empty. When getJobs() returned no work, the loop immediately queried the database again. And again. And again. There was no delay, no backoff, and no event-driven trigger. As a result, the service continuously hammered the database looking for work that didn't exist. Each iteration generated: A database query Network traffic CPU usage Logging overhead Additional infrastructure load Individually, each operation was cheap. Executed hundreds of thousands of times per day, they became expensive. The fix was simple: async function processQueue () { while ( true ) { const jobs = await getJobs () for ( const job of jobs ) { await processFile ( job ) } await new Promise ( resolve => setTimeout ( resolve , 5000 )) } } Even better would have been replacing polling entirely with an event-driven design using a message queue. What this incident taught me: 1. Empty queues are production workloads. Many engineers optimize for peak traffic and forget about idle traffic. Systems often spend more time idle than busy. 2. Polling needs backoff. If you're polling, always define what happens when no work is found. 3. Cost bugs rarely look like bugs. Nothing crashed. No exceptions were thrown. The system was technically working exactly as written. It was just doing useless work 24/7. 4. Always monitor cost alongside performance. CPU, latency, and error rates looked normal. The AWS bill was the first real alert. One question I ask

AWS released Blocks in public preview, an open-source TypeScript framework where each Block bundles application code, local mocks, and AWS infrastructure. Designed for AI agents to write correct backends from the start, it runs locally without an AWS account and deploys the same code to Lambda, DynamoDB, Aurora, and Bedrock with zero changes. By Steef-Jan Wiggers

Building a Spring Boot application is only half the journey. At some point, every backend project reaches the next question: Where should this application actually run? If you are deploying on AWS, two common options are: Amazon EC2 Amazon ECS Both can run the same Dockerized Spring Boot application. But they are not the same kind of deployment model. EC2 gives you a server. ECS gives you container orchestration. Choosing between them is less about which one is “better” and more about which one fits the stage of your application. Starting with EC2 EC2 is the most direct way to run a Spring Boot application on AWS. You create a virtual machine, install what you need, and run your application. For a Dockerized Spring Boot app, the flow often looks like this: GitHub Actions ↓ SSH into EC2 ↓ Pull latest code or image ↓ Build / run Docker container ↓ Spring Boot app runs on EC2 The mental model is simple: One server One Docker container One Spring Boot application That simplicity is useful. Especially when you are launching an MVP, a freelancer project, an internal tool, or your first production version. Why EC2 Works Well for Many Spring Boot Apps EC2 is not outdated just because newer deployment platforms exist. For many applications, EC2 is enough. It works well when: traffic is predictable the application is small or medium-sized you want full control over the server you want simple debugging through SSH you do not need multiple replicas yet you want to keep infrastructure easy to understand A common setup might be: Spring Boot Dockerfile Docker Compose GitHub Actions EC2 That setup can be production-ready for many early-stage apps. It gives you: a real deployment target repeatable Docker builds automated deployment through GitHub Actions simple logs direct server access For a solo developer or small team, that matters. You can understand the entire deployment flow without needing a full container orchestration platform. The Tradeoff With EC2 The tradeoff is that you

AWS made Graviton5-powered EC2 M9g and M9gd instances generally available with 192 ARM cores, formally verified VM isolation via the Nitro Isolation Engine, and DDR5-8800 memory. ClickHouse reported 36% better performance with zero code changes. Meta committed tens of millions of cores. On-demand pricing is 9% above Graviton4, translating to roughly 15% better price-performance. By Steef-Jan Wiggers

Doing the work and being able to explain the work are two different skills. I've had the first one for 8 years. I'm building the second one now. I'm a Cloud Platform Engineer. AWS, Kubernetes, Terraform, Linux. Regulated environments, healthcare, production systems. Real experience. Almost zero public documentation of it. That's the gap I'm closing, starting from Day 1. The platform is KodeKloud. Each session gives you tasks across multiple tools. I'm posting the Linux and AWS tasks here. Here's what I built and what actually matters about each one. Task 1 (Linux): Create a User with a Non-Interactive Shell The task was to create a system user that can own processes but cannot log in interactively. This is what you do for service accounts. bash ssh user@hostname sudo su - useradd username -s /sbin/nologin cat /etc/passwd | grep username The /sbin/nologin shell is the important part. The user exists in the system, can own files and run processes, but cannot open a shell session. You verify by checking /etc/passwd because the last field in each line is the assigned shell. I've been doing this in production environments for years. I still verify every time. Not because I'm unsure. Because in a regulated environment, you don't assume, you confirm. Task 2 (AWS): Create an EC2 Key Pair via CLI aws ec2 create-key-pair \ --key-name my-key-pair \ --key-type rsa \ --key-format pem \ --query "KeyMaterial" \ --output text > my-key-pair.pem aws ec2 describe-key-pairs --key-names my-key-pair The private key is returned exactly once at creation. AWS does not store it. If you lose it, you generate a new one and replace it everywhere it was used. I've seen this cause real problems in production environments where the key wasn't backed up properly. Always run chmod 400 my-key-pair.pem after saving it. SSH will refuse to use a key file with open permissions. It won't tell you that's the reason straight away. What Day 1 Taught Me That 8 Years Didn't Nothing here was technically new to

You add a sixth Lambda trigger to your OrderEvents table, deploy it, and within 20 minutes your SLA dashboard goes red. Latency on order writes jumps from 4ms to 40ms. The function itself is fine. The table is fine. The problem is that five other Lambdas are already hitting the same partition key on every write, and you just made it six. DynamoDB's internal partition throttling doesn't care that each function looks clean in isolation. This is an N+1 trigger problem, and your AI coding assistant cannot catch it. Not because it lacks intelligence, but because the fact that five Lambdas already target that table lives in your AWS account and your full codebase — not in the file your assistant has open. Infrawise · npm Why the LLM Can't See the Pattern When you ask Claude to write a new order processing Lambda, it reads the file you have open and generates code that looks correct — because in the context of that one file, it is correct. It doesn't know about ProcessRefundsLambda , NotifyFulfillmentLambda , SyncInventoryLambda , UpdateAnalyticsLambda , and AuditTrailLambda , all of which you wrote in previous sprints and which all write to the Orders table. This is a category of failure that model quality doesn't fix. A better model produces a more fluent explanation for why your latency spiked. The fact that five functions converge on the same table is a lookup, not a prediction. The source of truth is a combination of your code (which functions exist) and your infrastructure (what they access). Infrawise draws that boundary explicitly. It extracts the answer from your code using AST parsing and from your infrastructure using API calls, then hands that graph to the model as structured context — it never generates the answer. How Infrawise Traces Trigger Chains to the Same Table When Infrawise scans your repository, it uses ts-morph to walk every CallExpression in every source file. It's not searching for the string "DynamoDB" — it matches call structure against a known

Introduction In the previous articles, we explored AWS networking concepts like: VPC Subnets Internet Gateway Security Groups Route 53 Now, let's move to one of the most popular AWS services: Amazon S3 (Simple Storage Service) Amazon S3 is one of the easiest AWS services to learn and one of the most widely used services in real-world applications. Almost every application stores some kind of data: Images Videos Documents Log files Backups Static websites Amazon S3 helps us store and retrieve these files securely from anywhere in the world. In this article, we will understand: What Amazon S3 is Buckets and Objects Benefits of S3 Storage Classes Versioning Basic security concepts Static website hosting overview Why Do We Need Storage? Imagine you are running an online photo-sharing application. Users upload: Profile pictures Photos Videos Where should these files be stored? Keeping them directly inside application servers is not a good idea because: Storage is limited. Scaling becomes difficult. Replacing servers may cause data loss. This is where Amazon S3 helps. What is Amazon S3? Amazon S3 stands for: Simple Storage Service It is a cloud-based object storage service provided by AWS. S3 allows us to: Store data Retrieve data Manage data from anywhere using the internet. Amazon S3 is designed to be: Highly available Durable Scalable Secure Cost-effective Real-World Example Think of Amazon S3 as a digital warehouse. Suppose you own an e-commerce company. Inside your warehouse, you store: Product images Invoices Customer documents Videos Similarly, Amazon S3 stores digital files safely in the cloud. Buckets and Objects Amazon S3 stores data using two concepts: Bucket A bucket is a container used to store files. Think of a bucket like a folder. Examples: company-documents customer-images application-logs Bucket names must be globally unique. Object Anything stored inside a bucket is called an Object . Examples: invoice.pdf profile.jpg backup.zip video.mp4 Objects can co

AWS recently introduced Amazon Cognito multi-region replication, which automatically replicates user identities and user pool configurations from a primary region to a secondary one. This enables applications to continue authenticating users from a replica region during outages, without requiring custom replication and failover mechanisms. By Renato Losio

Google Open Knowledge Format: Why Enterprise Agents Need a Knowledge Layer, Not Just More Tools Most enterprise AI conversations still start in the wrong place. They start with the model. Which model should we use? Which framework should we adopt? Which vendor has the best agent platform? Which tools should we connect next? These are fair questions. But in real enterprise architecture, they are not the hardest questions. The harder question is this: Can our AI systems actually understand how our business works? That is why Google Cloud’s article on Open Knowledge Format caught my attention. The article talks about a simple but important idea: representing knowledge in a way that humans can read and machines can use. In OKF, that means markdown for the content and structured metadata for context. At first glance, that may sound too simple. But that simplicity is the point. Enterprises do not need another place where knowledge goes to die. We already have enough portals, catalogs, wikis, dashboards, folders, and internal tools. What we need is a practical way to package knowledge so it can be reviewed, versioned, governed, searched, and reused by both people and AI agents. That is where this idea becomes very relevant for agentic AI. The Real Enterprise AI Problem Most organizations already have the knowledge their AI agents need. They have it in databases, dashboards, tickets, architecture notes, runbooks, Confluence pages, data catalogs, code comments, incident reports, old project documents, and the heads of experienced employees. The issue is not that knowledge does not exist. The issue is that it is fragmented. Some of it is outdated. Some of it is duplicated. Some of it is tribal. Some of it is locked inside tools. Some of it is written for humans but not structured enough for AI systems to use reliably. This becomes a serious problem when we move from AI assistants to AI agents. An assistant can give a helpful answer. An agent does more. It plans, selects tools

AWS just launched AWS Blocks, an open-source TypeScript framework that gives you backend capabilities...

Certifications help when they match a role and are backed by proof — not as a scoreboard. The problem Beginners are told certifications are the key to IT, so they buy the most popular one, pass it, and are surprised when interviews still go badly. A certificate proves you can pass an exam; it does not, on its own, prove you can do the job. Why this matters now Certifications remain useful signals, and official providers like CompTIA, Microsoft, AWS, Cisco and Google keep their exam objectives public and current. But as AI makes it easier to grind practice questions, employers lean harder on whether you can actually apply the knowledge. The value of a certificate is increasingly in what you can demonstrate alongside it. There is also a cost reality. Exams, courses and retakes add up in money and time, and career changers usually have limited amounts of both. Spending three months and a chunk of savings on a certificate that no target role actually asks for is one of the most common and most avoidable mistakes in an IT transition — which is exactly why the order you choose them in matters. The practical framework Use certifications as targeted evidence, not as a scoreboard. Three rules: Match objectives to a job. Open the certification's published objectives next to a real job description. Overlap means it is relevant; no overlap means it is a hobby. Prove the same skills in practice. For each major objective, build one small artefact that shows you can do it, not just recall it. Stop at enough. One well-chosen, well-demonstrated certification beats three unrelated ones. Sequence them to roles, not to availability. Which one first? Let the target role decide, not the brand with the loudest marketing. As a rough guide: a vendor-neutral foundation (such as CompTIA A+ for general IT support, or Network+/Security+ as you specialise) suits broad support roles; a cloud-fundamentals exam (Microsoft Azure or AWS) suits cloud-leaning roles; Cisco-flavoured paths suit networkin

A new FTC lawsuit reveals how sophisticated subscription app operators can allegedly use shell companies and payment infrastructure to stay active on app stores despite mounting consumer complaints.

IaC tools built for single-team deployments fail structurally at 200 accounts because the failure modes are architectural, not configurational. Why 200 Accounts Is Where IaC Tools Break IaC tools built for single-team deployments fail structurally at 200 accounts because the failure modes are architectural, not configurational. Scale Threshold State Management Provider Auth Overhead Execution Time Impact ~10 accounts One backend bucket, one workspace; quirks are routable Not a meaningful bottleneck Sequential plan/apply is manageable ~50 accounts Sequential execution still viable; blast radius contained Per-account latency exists but tolerable Below threshold where parallelism is required 200+ accounts 200 separate plan operations per shared-module refactor 3-sec per-account auth × 200 = 10 min added per plan cycle Sequential Terraform applies measured at 4.1 hours end-to-end A 10-account environment forgives sloppy state management. One backend bucket, one workspace convention, one pipeline. Engineers learn the tool's quirks and route around them. At 200 accounts, those same quirks compound. Why the threshold is 200 State lock contention, cross-account provider authentication chains, and module resolution latency stack on top of each other. The result is not slower deploys. It is non-deterministic deploys, which is operationally worse. The specific threshold matters. Below roughly 50 accounts, most teams run plan and apply sequentially without parallelism because the blast radius of a runaway apply is contained. Above 200 accounts, sequential execution becomes untenable. We measured a 200-account org where sequential Terraform applies across all accounts took 4.1 hours end-to-end. That latency made emergency remediation impossible inside a standard incident window. Three compounding failure modes State file proliferation. Each account carries its own state file, and each state file is a consistency boundary. At 200 accounts, a single refactor touching a shared modu

On 14 April, the Trump administration quietly acknowledged the widespread use of AI to automate government processes. The office of management and budget (OMB) disclosed a staggering 3,611 active or planned use cases for AI across the federal government. The list has ballooned by 70% from the one published in the final year of the Biden administration, and includes many disturbing-seeming plans to hand over sensitive governmental functions to AI. Scanning this list, many readers may find many causes for alarm. It represents a transfer of decision processes from human to machine on a massive scale over matters of individual freedom, public health and well-being, nuclear reactor safety and more...

An AI agent has two kinds of memory: conversation (semantic) and context (exact reference). Keep them separate with Strands and AgentCore.

The Justice department says the Pentagon needs xAI to keep using its unpermitted gas turbines.

Coinbase has published a detailed postmortem of its May 7, 2026, outage, revealing how a localized cooling failure inside an AWS data center escalated into a multi-hour disruption that halted nearly all trading activity across the cryptocurrency exchange By Craig Risi

My AWS Bedrock Experiment Cost Me $8.43 in Just One Day What I learned about AWS Bedrock pricing the hard way, and why budget alerts saved me Why I Even Tried Claude Code on Bedrock I have been using Claude Code for a while now, connected to Anthropic directly. It works well. But two things were bothering me. First, the usage limits. Claude Code on Anthropic's native setup has 5hours session limit and a weekly usage cap. Once you hit it, you have to wait. If you are in the middle of something or just want to experiment freely, that gets frustrating fast. Second, billing. I already manage everything on AWS. I'm very familiar with it, the invoices go to one place, and I understand how to track and control costs there. Adding a separate Anthropic subscription meant one more billing account, one more credit card charge, one more thing to track. I just wanted everything under one roof. So I thought, why not try Claude Code connected to Amazon Bedrock? Same tool, runs on AWS, billed through AWS. Seemed like a clean solution to both problems. What happened next is why I am writing this post. The Two Ways to Run Claude Code Most people do not realise Claude Code can be configured to run in two different ways. Option 1: Claude Code via Anthropic directly You connect Claude Code to Anthropic's API or use it under your Claude subscription. Billing goes through Anthropic. If you are on a subscription plan, you pay a flat monthly fee and the usage limits apply to how much you can do within that. Option 2: Claude Code via Amazon Bedrock You connect Claude Code to AWS Bedrock as the backend. Same Claude models, but now AWS is your provider. Billing goes through your AWS account. No Anthropic subscription needed. From the outside, it looks and feels the same. But the billing model underneath is completely different, and that is where things get interesting. What Happened When I Tried It I set up Claude Code to use Bedrock and gave it a prompt. A fairly detailed one, nothing unusual