Posts tagged "Architecture"

CLOUD

25 September 2026 · 6 MIN READ

AWS This Week: EventBridge's New Event Bus, Network Security Manager and Cross-Continent DynamoDB (Video)

80 seconds on the AWS news that changes how platform teams build this week: Amazon EventBridge relaunches the custom event bus (one bus for the whole organisation, ordered delivery, per-GB pricing), AWS Network Security Manager is generally available, DynamoDB multi-Region strong consistency now crosses continents, Kinesis Data Streams picks the partition key for you — plus one industry signal: Seller Central opens to outside AI agents.

Read → †❖ #AWS

AI ENGINEERING

22 September 2026 · 9 MIN READ

One 'AI Gateway', Two Different Jobs: the LLM Gateway and the Tool Gateway

Every agentic architecture conversation I have eventually collides with the phrase 'AI gateway' — and half the time the two people using it are talking about two different products. One proxies model traffic; the other fronts tools. Confusing them produces bad verdicts, broken migrations, and gateways justified by the wrong criterion. Here is how I untangle the two roles, the per-model API compatibility trap, and the one question that decides whether an extra gateway earns its place.

Read → ⁂ #GenAI

CLOUD

05 September 2026 · 4 MIN READ

Lambda SnapStart Now Covers Container Images: The Last Cold-Start Excuse Is Gone

AWS extended Lambda SnapStart to container image functions — up to 10 GB, sub-second resume, nearly all commercial Regions. Here's what it unlocks for ML inference and heavy runtimes, the snapshot discipline that still applies, and how it changes the SnapStart vs provisioned concurrency vs Fargate math.

Read → ❖ #AWS

AI ENGINEERING

30 July 2026 · 10 MIN READ

Logical Agents as Data, Not Infrastructure: The Multi-Tenant 'Let Customers Build Agents' Decision

When your SaaS lets customers create their own agents, the first architecture fork decides everything: is an agent a row in a table, or a piece of infrastructure? Here is why the answer is almost always the row, and the shared-runtime pattern that makes it hold.

Read → #AWS

CLOUD

20 July 2026 · 9 MIN READ

Loom + FAST: Wiring an Enterprise Agent Control Plane to a Customer-Facing App on AgentCore

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.

Read → ⁂ #AWS

CLOUD

30 May 2026 · 10 MIN READ

Amazon Leo for Enterprise: What a LEO Satellite Network Changes for Cloud Architecture

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.

Read → ❖ #AWS

AI ENGINEERING

16 May 2026 · 10 MIN READ

The Agent Memory Problem: Why 5+ Solutions Exist and None Won

Mem0, Letta, Zep, graph-RAG, Neptune Memory, HiveMemory, Obsidian steering files -- the agent memory space is fragmenting faster than it's converging. Here's a landscape analysis of why no single solution wins, the four types of memory agents actually need, and a decision framework for choosing your architecture.

Read → ⁂ #AI Agents

AI ENGINEERING

16 May 2026 · 9 MIN READ

MCP Gateway as Policy Enforcement Point: RBAC for Your Agent's Tool Access

Your AI agent has access to tools that perform real actions -- approving expenses, querying databases, modifying infrastructure. Prompt-based guardrails don't survive adversarial inputs. Here's how AgentCore Gateway + Cedar policies create a deterministic enforcement layer that operates independently of the agent's reasoning.

Read → † #AI Agents

AI ENGINEERING

14 May 2026 · 9 MIN READ

AWS Agent Toolkit GA: How I Gave an Agent 15,000 AWS APIs Without Losing Sleep

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.

Read → †⁂ #AI Agents

CLOUD

17 March 2026 · 10 MIN READ

Your ZTNA Strategy Has a Blind Spot — External Users Need a Different Approach

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.

Read → † #AWS

CLOUD

16 March 2026 · 10 MIN READ

Why Amazon Connect Is an AI Platform That Happens to Handle Phone Calls

How Amazon Connect's native AI stack replaces fragmented CCaaS platforms with a unified, pay-per-use contact center backbone for global enterprises.

Read → #AWS

CLOUD

16 March 2026 · 9 MIN READ

Your CSPM Won't Save You — Why Cloud Security Is a Governance Problem

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.

Read → † #AWS

04 March 2026 · 19 MIN READ

OpenClaw vs NanoBot vs PicoClaw vs TinyClaw: Four Approaches to Self-Hosted AI Assistants

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.

Read → † #AI

SECURITY

27 February 2026 · 10 MIN READ

Your Security Team Wants to Privatize Your App — Here's What They Actually Need

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.

Read → † #AWS

26 February 2026 · 17 MIN READ

LLM Architecture Explained Simply: 10 Questions From Prompt to Token

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.

Read → ∴⁂ #AI

CLOUD

26 February 2026 · 11 MIN READ

MPLS vs SD-WAN vs CloudWAN: Enterprise Networking Explained Simply

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.

Read → ❖ #AWS

23 February 2026 · 15 MIN READ

Transformer Anatomy: Attention + FFN Demystified

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).

Read → ∴ #AI

CLOUD

13 February 2026 · 10 MIN READ

Replacing Legacy SFTP with AWS Transfer Family in a Multi-Account Landing Zone

How to architect a secure, multi-tenant SFTP service across AWS accounts using Transfer Family, NLB, Transit Gateway, and per-partner S3 isolation.

Read → †❖ #AWS

All topics Full journal