Who is Fernando F. Azevedo?

Fernando F. Azevedo is a Senior Solutions Architect at Banco Itaú with 16+ years of experience across AWS, event-driven architecture, DevSecOps, Data Mesh, AI and financial systems.

What technical topics does Fernando work with?

Fernando works with AWS, Kubernetes, Kafka, Data Mesh, Amazon Bedrock, RAG, DevSecOps, observability, financial systems and architecture communication using C4, ADRs and trade-off analysis.

Is Fernando available for professional conversations?

Fernando is currently building at Banco Itaú and is open to thoughtful conversations about architecture, cloud, AI, engineering leadership, community, podcasts and technical collaboration.

Insights

Architecture field notes

Architecture, cloud and applied AI blog

Deep analysis on solution architecture, AWS, AI, security, data and financial technology through a critical-systems lens.

Tracks

Solution Architecture3 articles AWS & Cloud6 articles AI & Agents14 articles Security & Resilience8 articles Data Platforms7 articles Financial Systems4 articles

Browse guided learning paths

New York suspends new data centers above 50 MW

Governor Kathy Hochul signed an order pausing new 50 MW+ data centers for up to a year while the state runs an environmental study. It targets AI's pressure on the grid, water use and cost-shifting to the public — and signals a new regulatory risk for anyone designing cloud and AI workloads.

Jul 20, 2026 7 minintermediate

Read full analysis

Technical picks

Deep technical reading

AI & AgentsField Notes

The IDE Became the Exception: How I Shifted to Building Loops Instead of Code

After 16 years building financial-grade systems on AWS, I realized my job changed: I no longer design code line by line, I design loops — triggers, topologies, verifiers, and stop-rules. The IDE still exists on my workbench, but less and less. This post is the honest record of that transition.

loop-engineeringai-agentsaws-bedrock

Jun 29, 2026 5 minintermediate

AI & AgentsDeep Dive

Amazon Bedrock AgentCore Harness: From Idea to Production-Grade Agent

AgentCore Harness reached GA in June 2026 as a managed abstraction that collapses the LLM agent control plane into two API calls. In this article, I analyze how the harness works internally, where it fails, and what architects of financial-grade systems need to understand before putting it into production.

bedrockagentcoreagentic-ai

Jun 24, 2026 9 minadvanced

AWS & CloudTechnology Review

AWS Lambda MicroVMs: technical review of a new serverless primitive

AWS Lambda MicroVMs fills a genuine gap between ephemeral functions and heavy VMs, delivering hypervisor-level isolation with near-instant resume latency and state preserved for up to 8 hours. As an architect operating financial-grade multi-tenant environments, I see genuine potential here — and equally real pitfalls that must be addressed before any production adoption.

lambdamicrovmsfirecracker

Jun 23, 2026 10 minadvanced

Latest articles

AI & AgentsTechnology Review

Amazon Bedrock AgentCore: Continuous Agent Optimization in Production

Amazon Bedrock AgentCore introduces a continuous improvement loop that turns production traces into actionable diagnostics, data-grounded recommendations, and statistical validation via A/B testing. For architects of financial systems and high-stakes platforms, this represents AWS's first serious attempt to close the gap between agent observability and reliable production operation.

bedrockagentcoreagentic-aiobservabilitymlops

Jun 23, 2026 11 minadvanced

Bedrock Managed Knowledge Base: Anatomy of a Managed RAG Pipeline

Amazon Bedrock Managed Knowledge Base abstracts the entire RAG stack — connectors, parsing, embeddings, re-ranking, and agentic retrieval — into a single managed primitive. In this article, I disassemble each layer, expose the failure modes the documentation doesn't mention, and analyze the real trade-offs for engineers designing financial-grade AI systems on AWS.

bedrockragknowledge-baseagentic-aienterprise-ai

Jun 23, 2026 9 minexpert

AI & AgentsComparison

InvokeGuardrailChecks vs Classic Guardrails: Which to Use in AI Agents?

AWS released the InvokeGuardrailChecks API in Amazon Bedrock Guardrails — a resourceless API that lets you apply individual safeguards at any point in an agentic loop without creating or versioning guardrail resources. In this article, I run a direct head-to-head between this approach and classic resource-based Guardrails, evaluating latency, governance, cost, and fitness for financial-grade mission-critical systems.

bedrockguardrailsagentic-aisecurityfinancial-grade

Jun 22, 2026 8 minadvanced

EC2 G7 & NVIDIA Blackwell: GPU Inference Architecture for Production

EC2 G7 instances, accelerated by NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs, represent a generational leap that goes well beyond benchmark numbers. In this analysis, I examine the real GPU-to-GPU communication mechanisms, failure patterns in multi-node clusters, and the architectural decisions that separate a functional inference deployment from a financial-grade fault-tolerant system.

ec2-g7nvidia-blackwellgpu-inferenceefagpudirect-rdma

Jun 18, 2026 9 minexpert

AWS & CloudComparison

ECS Auto Scaling: High-Resolution Metrics vs. Traditional Scaling Approaches

The launch of high-resolution (20-second) metrics for Amazon ECS reshapes the auto scaling calculus for latency-sensitive financial workloads. This article compares the four primary scaling approaches — target tracking with high resolution, step scaling, scheduled scaling, and predictive — with concrete trade-offs, real numbers, and a decision matrix for production environments.

ECSAuto ScalingCloudWatchFargateFinancialGrade

Jun 18, 2026 9 minadvanced

Security & Resilience

Read

Topics

Well-Architected

Security & ResilienceComparison

AI Agents for Security and DevOps: Productivity or Risk?

AWS launched frontier agents for security testing and cloud operations, opening a real debate about how far AI autonomy can go in regulated environments. This article compares four deployment patterns — fully autonomous agent, semi-autonomous with human approval, assisted (copilot), and deterministic pipeline — using concrete criteria of risk, cost, latency, and compliance.

bedrock-agentssecurity-automationdevopsgovernancezero-trust

Jun 18, 2026 8 minexpert