Posts tagged "GenAI" | Alexandre Agius

CLOUD

23 September 2026 · 5 MIN READ

AWS This Week: CloudWatch Omni, GPT-6 Sol & Luna and Claude Opus 5.5 on Bedrock (Video)

88 seconds on the AWS news that actually changes your AI platform this week: Amazon CloudWatch Omni is generally available (observability organised around teams and applications, with an evaluation workflow for agents), OpenAI's GPT-6 Sol and Luna reach GA on Amazon Bedrock, Claude Opus 5.5 lands on AWS — plus one industry signal: frontier model prices fell twice in one day.

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

AI ENGINEERING

16 September 2026 · 9 MIN READ

Five Agents, One Football Team: Per-Role Model Selection and Deterministic Guardrails on AgentCore

I entered an agent football tournament: five LLM-driven players on Bedrock AgentCore, one command per game tick, every tick latency-sensitive. Per-role Nova model selection, memory switched off, and deterministic rules applied after the LLM made the team work — and then command fingerprinting in CloudWatch proved my perfectly healthy runtimes had been playing for the wrong team all along.

Read → ⁂ #GenAI

CLOUD

08 September 2026 · 3 MIN READ

Deep Dive: The AWS AI Security Framework in 85 Seconds (Video)

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.

Read → † #AWS

CLOUD

07 September 2026 · 2 MIN READ

AWS This Week: 4 Launches That Matter for Your Architecture (Video)

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.

Read → ❖ #AWS

CLOUD

05 September 2026 · 1 MIN READ

AWS This Week: 4 Launches That Matter for Your Architecture (Video)

68 seconds on the AWS news that actually changes your architecture this week: Lambda SnapStart for container images, AgentCore-generated architecture diagrams, Amazon Linux 2027 preview, CloudFront flat-rate pricing API — plus one industry signal on offensive AI.

Read → ❖ #AWS

07 August 2026 · 7 MIN READ

Validate the Issue, Not the Structure: a Self-Correcting Pipeline for LLM-Generated Games

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.

Read → #GenAI

CLOUD

06 August 2026 · 8 MIN READ

Bedrock Cuts GPT-5.6 Prices by up to 80%: What the Luna/Terra/Sol Asymmetry Tells You

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.

Read → #AWS

CLOUD

20 July 2026 · 10 MIN READ

Attributing Bedrock Costs per User and per Project: 4 Mechanisms That Actually Work

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.

Read → #AWS

CLOUD

10 July 2026 · 9 MIN READ

AWS Transform + GenAI for VM Migration: The Assisted Data-Center Exit

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.

Read → #AWS

10 March 2026 · 14 MIN READ

Building a RAG System That Actually Works: Chunking, Vector Engines, and Testing

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.

Read → ∴⁂ #AWS

10 March 2026 · 12 MIN READ

Vector Search vs Semantic Search: They're Not the Same Thing

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.

Read → ⁂ #AWS

02 March 2026 · 8 MIN READ

Inside AWS Security Agent: How Multi-Agent Systems Automate Penetration Testing

A deep dive into the multi-agent architecture behind AWS Security Agent's automated penetration testing — from specialized agent swarms to assertion-based validation.

Read → †⁂ #AWS

09 February 2026 · 22 MIN READ

RAG on AWS: Which Vector Store Is Right for You?

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.

Read → ⁂ #AWS

All topics Full journal