Topic index / 32 entries
Field notes, architecture decisions, and practical guides filed under this recurring subject.
← All topicsCLOUD
08 September 2026 · 3 MIN READ
80% of organizations have adopted AI — only 10% govern it. AWS just published the AI Security Framework: the right controls, at the right layers, at the right phases. An 85-second explainer plus the architect's takeaway: day-1 controls are configuration changes, not architecture changes.
CLOUD
07 September 2026 · 2 MIN READ
76 seconds on the AWS news that actually changes your architecture this week: Claude Fable 5.1 on Bedrock, Amazon Quick GA, Bedrock Knowledge Bases 3LO connectors for SharePoint/Confluence, EC2 AMI instance-type enforcement — plus one industry signal on agentic commerce.
AI ENGINEERING
02 September 2026 · 5 MIN READ
I wanted a detection app my kids could use without a single camera frame leaving the device. The answer: RF-DETR quantized to int8, ONNX Runtime Web on threaded WASM, and a static Amplify site.
WEEKLY DIGEST
19 August 2026 · 7 MIN READ
Two months of AWS news in one editorial pass: GPT-5.6 lands on Bedrock and gets 80% cheaper seventeen days later, AgentCore ships the full production stack for agents (persistent compute, temporal governance, native payments), AI primitives melt into DynamoDB and Lambda, and a July 30 maintenance wave quietly retires the first-generation AI portfolio. With practitioner takes and what I'm watching for la rentrée.
AI
07 August 2026 · 7 MIN READ
My pipeline generates a playable HTML5 game every day with Bedrock. An audit found 6 of 7 published games broken — while every one of them passed structural validation. Here is how I rebuilt the quality gate around real usage: hit-tested playtests, a progress-signal check, prompt contracts, and a fail-closed publish loop that rejected three broken versions before shipping a good one.
CLOUD
06 August 2026 · 8 MIN READ
AWS just cut GPT-5.6 Luna prices by 80% and Terra by 20% on Bedrock, matching OpenAI's first-party cut on the same day. The interesting part is not the discount — it's the asymmetry, and what it changes in your model-routing math. With worked examples.
AI ENGINEERING
30 July 2026 · 9 MIN READ
Four domain-specialist agents on Bedrock AgentCore draft one integrated specification, catch a cross-domain conflict between their own outputs, and hand it to a human to resolve. A concrete look at what multi-agent actually means when the agents have to agree.
AI ENGINEERING
23 July 2026 · 3 MIN READ
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.
CLOUD
23 July 2026 · 5 MIN READ
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.
AI ENGINEERING
23 July 2026 · 6 MIN READ
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.
CLOUD
20 July 2026 · 10 MIN READ
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.
CLOUD
20 July 2026 · 9 MIN READ
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.
AI ENGINEERING
12 July 2026 · 12 MIN READ
From zero-percent RL success to reliable grasping via imitation learning — all in a physics sim on a MacBook, orchestrated by an LLM.
AI ENGINEERING
19 June 2026 · 11 MIN READ
AgentCore Harness just went GA. Here's what it solves, what it doesn't, and when you should adopt it instead of building your own agent runtime governance layer.
AI ENGINEERING
09 May 2026 · 13 MIN READ
I woke up to 204 pull requests from a single autonomous agent running overnight. 12 hours, ~$900 in Bedrock tokens, 509 failed builds, zero features shipped. Prompt-only safeguards all failed. Here's the 3-layer fix — hard kill switch, atomic circuit breakers, drift observability — that now prevents runaway agents.
AI ENGINEERING
22 April 2026 · 6 MIN READ
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.
AI ENGINEERING
21 April 2026 · 5 MIN READ
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.
AI
20 April 2026 · 8 MIN READ
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.
AI ENGINEERING
20 April 2026 · 10 MIN READ
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.
CLOUD
05 April 2026 · 6 MIN READ
Weekly roundup of AWS announcements: AI Scholars program, Agent Plugin for serverless, Aurora Express setup, Lambda upgrades, Polly streaming, and more.
AI
20 March 2026 · 8 MIN READ
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%.
CLOUD
16 March 2026 · 10 MIN READ
How Amazon Connect's native AI stack replaces fragmented CCaaS platforms with a unified, pay-per-use contact center backbone for global enterprises.
AI
10 March 2026 · 14 MIN READ
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.
AI
10 March 2026 · 12 MIN READ
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.
AI
04 March 2026 · 19 MIN READ
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.
AI
02 March 2026 · 14 MIN READ
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.
CLOUD
22 February 2026 · 7 MIN READ
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.
CLOUD
22 February 2026 · 14 MIN READ
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.
AI
22 February 2026 · 11 MIN READ
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.
AI
09 February 2026 · 22 MIN READ
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
06 February 2026 · 8 MIN READ
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.
AI ENGINEERING
14 January 2026 · 5 MIN READ
Enterprise workflows often require interacting with web applications that lack APIs. Traditional automation scripts are brittle and break when UIs change.