Agentic AI Series | Alexandre Agius

AI ENGINEERING

26 September 2026 · 11 MIN READ

AI-DLC in a Team: the Agent Is No Longer the Bottleneck

In January I used AI-DLC alone, one developer and one agent in an IDE. This month I deployed AIDLC Collaborative, the open-source sample that runs the same method for a whole team: intents, human gates, parallel construction lanes, agents in isolated AgentCore sessions, and a platform that owns git. Two intents with the same 48 minutes of agent work took 81 and 284 minutes end to end. Here is what the team version changes, what it costs to stand up, the failure that painted 14 empty stages green, and what I have not verified yet.

Read → ⁂ #AI-DLC

AI ENGINEERING

26 September 2026 · 11 MIN READ

Kiro Trusts One File. Here Is How I Stopped Editing It by Hand

Kiro's enterprise MCP registry is one JSON file behind one URL: whatever is in it, developers see; whatever is not, never starts. That makes the file a control point — and a hand-edited control point is a liability. I rebuilt mine as a generated artifact: AWS Agent Registry as the approved catalog, AgentCore Gateway as the only remote MCP endpoint, and a small publisher that turns approvals into the file Kiro reads. Here are the five decisions, the six things the docs did not tell me, and what I still have not verified.

Read → †⁂ #Kiro

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

AI ENGINEERING

30 July 2026 · 9 MIN READ

Multi-Agent Spec Writing: Specialist Agents, Conflict Detection, and Human Escalation on AgentCore

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.

Read → ⁂ #AI Agents

AI ENGINEERING

20 July 2026 · 10 MIN READ

From Hackathon to Cloud Pipeline: Inspecting Physical Parts with a Humanoid and AgentCore

A two-day hackathon build where a humanoid walks an inspection route, captures imagery, and an agent on Bedrock checks each assembly against its bill of materials. What the cloud pipeline looked like, and what a hackathon proves versus what it doesn't.

Read → ⁂ #AI

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

AI ENGINEERING

19 June 2026 · 11 MIN READ

AgentCore Harness: Governing 500 Agents at Scale

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.

Read → †⁂ #AgentCore

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

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

AI ENGINEERING

22 April 2026 · 6 MIN READ

Agentic Data Governance — Building a Multi-Platform Access Broker with Bedrock Agents

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.

Read → ⁂ #Agentic AI

AI ENGINEERING

21 April 2026 · 5 MIN READ

From RPA Bots to AI Agents — A 5-Criterion Scoring Framework for Enterprise Migration

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.

Read → ⁂ #Agentic AI

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

02 March 2026 · 14 MIN READ

The RISEN Framework: Writing System Prompts That Actually Work for AI Agents

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.

Read → ⁂ #AI

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

24 February 2026 · 9 MIN READ

Getting Hands-On with Mistral AI: From API to Self-Hosted in One Afternoon

A practical walkthrough of two paths to working with Mistral — the managed API for fast prototyping and self-hosted deployment for full control — with real code covering prompting, model selection, function calling, RAG, and INT8 quantization.

Read → ∴⁂ #AI

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

AI ENGINEERING

14 January 2026 · 5 MIN READ

Browser Automation Agents - Amazon Bedrock AgentCore

Enterprise workflows often require interacting with web applications that lack APIs. Traditional automation scripts are brittle and break when UIs change.

Read → ⁂ #AWS

Explore more series

3 DOSSIERS

AI & LLM Fundamentals

Deep dives into artificial intelligence, large language models, transformers, embeddings, and the core concepts powering modern AI systems.

18 ARTICLES

Cloud Security

Best practices and deep dives into cloud security — from zero trust architectures to WAF configurations and penetration testing.

23 ARTICLES

AWS Architecture

Patterns, services, and architectural decisions for building on AWS — including Bedrock, SageMaker, Transfer Family, and more.

20 ARTICLES

All series Full journal