Llama 4 vs Gemma 4: The Open-Source LLM Race Just Got Real
Meta dropped Llama 4 Scout, Maverick, and Behemoth. Google fired back with Gemma 4. As a Technical Lead, here's what these releases actually mean for your teams and projects.
#architecture
49 posts
The LLM Cost War: Qwen3.6-Plus, Gemini Flash-Lite, and the Dawn of Commodity AI
Alibaba just released its third proprietary model in days. Google's Gemini Flash-Lite costs $0.25 per million tokens. NVIDIA's Nemotron runs 2.2x faster than GPT-OSS-120B. The LLM cost war has arrived — here's what it means for architects choosing AI infrastructure in 2026.
English Lesson — Wednesday Morning: System Architecture
Daily English practice for tech professionals. Morning session covering system architecture vocabulary with pronunciation guide, exercises, and real-world examples.
Agent2Agent Protocol: Building the Internet of AI Agents
The A2A protocol under the Linux Foundation is quietly becoming the HTTP of the agentic era. Here's what it means for enterprise architects, why it matters more than another model release, and how to think about it from a systems design perspective.
Tech Lead English: How to Lead Architecture Debates Without Losing the Room
Practical English phrases for Vietnamese tech leads navigating technical disagreements, design discussions, and architecture decision meetings with international teams.
MCP at 10,000 Servers: How a Protocol Became the Agent Integration Standard
The Model Context Protocol crossed 10,000 published servers under the Linux Foundation's Agentic AI Foundation. As someone who's integrated dozens of AI systems, here's why this number matters more than any benchmark.
The AI Cost Collapse: How to Architect Smart at Under $1/M Tokens
GPT-4 level AI cost $30/M tokens in 2023. Today it's under $1. Here's the technical architecture that lets you capture 90%+ of that savings without sacrificing quality.
Build a Full-Stack Startup for $20/Month: The 2026 Free-Tier Stack
A comprehensive guide to the modern free-tier tech stack that lets you build, deploy, and scale a startup for roughly $20/month. No servers. No DevOps team. No funding required. Just an idea and WiFi.
AI Agents in Production 2026: The Shift from Copilot to Autopilot
90% of developers now use AI at work. But the real shift in March 2026 is agents moving from suggestion-mode to autonomous execution. Here's what that actually looks like in production systems and what breaks when you go too far too fast.
English Lesson — Wednesday Morning: System Architecture
Daily English practice for tech professionals. Morning session covering System Architecture vocabulary — microservices, scalability, fault tolerance, load balancing, and cloud design patterns — with pronunciation guide, exercises, and real-world examples.
English Lesson — Wednesday Noon: Architecture Vocabulary
Daily English practice for tech professionals. Noon session — vocabulary deep dive with pronunciation, exercises, and real-world examples.
What Production AI Agents Actually Look Like in 2026 — Not the Demo, the Reality
Gartner says 40% of enterprise apps will embed AI agents this year. But 40% of agentic projects will be scrapped by 2027. Here's what separates the teams that ship production agents from those that get stuck in pilots forever.
Tech Lead English: Facilitating Technical Design Discussions
Practical English phrases and dialogue templates for Vietnamese Tech Leads running architecture reviews, proposing solutions, and handling technical disagreements in international teams.
Claude Opus 4.6 Agent Teams: Multi-Agent Development Is Here
Anthropic's Agent Teams feature in Claude Opus 4.6 lets multiple Claude Code instances work in parallel on the same codebase. Here's the architectural model, real-world performance data, and what actually changes for teams building production software.
Business English for Tech Professionals: Architecture Proposals, Design Reviews & Technical Disagreements
The exact language patterns senior engineers use to propose technical solutions, run architecture review meetings, push back on bad ideas without damaging relationships, and write ADRs that actually get read and followed.
AI-Driven Software Architecture: A Hands-On Guide for Engineering Teams (2026)
How AI is reshaping software architecture from the inside — ML-powered pattern selection, LLM orchestration, AI gateways, event-driven agents, and a full team implementation roadmap with diagrams and production-ready code.
When All Frontier AI Models Are Equal: A Technical Lead's Guide to Choosing in 2026
GPT-5.4, Gemini 3.1 Pro, and Claude 4.6 are now neck-and-neck on benchmarks. When the models are equal, everything else becomes the differentiator. Here's how to choose.
Umbraco AI Migration Playbook: The Marketing OS Framework — Scaling Across Multiple Sites
When you're managing 10, 20, or 50 Umbraco sites, individual project economics don't work. The Marketing OS framework: shared NuGet packages, shared document type libraries, AI-accelerated delivery, and how to reduce per-site migration cost by 50–70%.
When AI Writes Beautiful Code That Doesn't Fit: The Architecture Trap
AI can generate impressive code that completely ignores your architecture. How to provide architectural context, enforce patterns, and know when to override AI suggestions.
Tech Coffee Break #11: Event-Driven, CQRS, Saga — Buzz or Useful?
Architecture buzzwords demolished and rebuilt. Two tech leads explain when event-driven architecture, CQRS, and the Saga pattern are genuinely useful — and when they're just resume padding. Pizza delivery analogies included.
The 40% That Nobody Wants to Do: Why Planning Before Prompting Changes Everything
Most developers skip straight to 'generate code.' The teams that get real value from AI spend 40% of their time planning before writing a single prompt.
What If You Don't Want Next.js? Five Alternative Frontends for Headless Umbraco 17
Not every team wants React. Here are five production-ready alternatives for building marketing websites with headless Umbraco 17 — from Astro and Nuxt to SvelteKit, .NET Razor, and even plain HTML.
Shipping the Template: Multi-Tenant Onboarding, Cost Savings, and the Honest Retrospective
Turning MarketingOS into a reusable template: new client onboarding in under an hour, multi-tenant content management, cost analysis showing 70% reduction per site, lessons learned, and what I'd do differently.
Tech Coffee Break #7: SQL or NoSQL? The Answer Is Always 'It Depends'
PostgreSQL, MongoDB, Redis, DynamoDB — when do you use what? Two tech leads break it down with filing cabinet analogies, real use cases, and zero religious wars.
Tech Coffee Break #6: Cool Demo, But Will It Work Monday Morning?
Putting AI into production is nothing like building a demo. Two tech leads discuss costs, hallucinations, latency, guard rails, and what actually breaks when real users hit your AI features.
The Voice AI Interview Playbook: Cost Optimization — From $0.14/min to $0.03/min Without Sacrificing Quality
The real cost of AI voice interviews, broken down per minute. Managed vs self-hosted economics, the three tipping points, and how to get from $3.45 per interview to under $1.00.
The Voice AI Interview Playbook: Scaling to Thousands — Architecture for Concurrent Voice Sessions
From 10 concurrent interviews to 10,000. LiveKit SFU mesh, stateless agent workers, Kubernetes auto-scaling, regional deployment, and the infrastructure patterns that handle hiring season surges.
Tech Coffee Break #2: REST, GraphQL, gRPC — Which One Do I Pick?
Two tech leads break down API design styles using restaurant analogies. Learn when to use REST, GraphQL, or gRPC — explained in casual English perfect for listening practice.
Building KidSpark: Tech Stack Selection — Flutter, React Native, or Native?
The framework debate almost split the team. Flutter, React Native, or going fully native? Here's our decision matrix and what we learned comparing all three.
Tech Coffee Break #1: So... Why Did Everyone Split Their Apps?
A casual conversation about microservices vs monoliths. Two tech leads explain when to split, when to stay, and why most teams get it wrong — in plain English you can listen to and learn from.
Building a Marketing Website Template with Umbraco 17 & Next.js: Why This Architecture and How to Set It Up
Why headless Umbraco 17 with Next.js is the sweet spot for reusable marketing websites, the architecture decisions behind MarketingOS, and setting up both projects with Clean Architecture on .NET 10.
Production Voice AI for Research at Scale: The Architecture Nobody Warns You About
Why research interviews need server-side voice agents, the three-tier architecture, room metadata as configuration transport, and the 100-500ms propagation latency nobody tells you about.
Angular 21 Project Setup: Clean Architecture on the Frontend
Setting up an Angular 21 ecommerce project from scratch. Nx monorepo, feature-based folder structure, ESLint flat config, Vitest, and auto-generated Kiota TypeScript API client from .NET 10.
Angular Ecommerce Playbook: The Tech Lead's First Week with Angular 21 and .NET 10
A Technical Lead's honest assessment of Angular 21 (released Nov 2025), .NET 10 LTS, and GitHub Copilot for an Ecommerce project. Architecture decisions, ADR templates, and what nobody tells you on day one.
Tech Lead Playbook: Angular 21 + .NET 10 Ecommerce — Strengths, Weaknesses, and Risk Register
The Tech Lead's honest retrospective on Angular 21 + .NET 10 for an ecommerce project. What this stack does well, where it struggles, the risk register, and practical advice for teams starting this journey.
Nx Module Boundaries — The #1 Architecture Rule for Large Angular Codebases
Post A — How to enforce Nx module boundary rules in Angular 21 to prevent spaghetti imports, protect domain separation, and keep teams independently productive in a monorepo.
Production-Ready Clean Architecture: Deployment, Monitoring, and the Lessons I'd Share With My Past Self
Taking Kids Learn to production with Docker, CI/CD, OpenTelemetry observability, performance optimization, Native AOT considerations, and an honest retrospective on what worked and what was over-engineered.
The AI Solution Architect: System Design, ADRs & Technology Selection in the AI Era
How AI transforms the Solution Architect role: AI-assisted architecture diagramming, ADR generation, trade-off analysis, technology selection rationale, and the architectural taste that only experience provides.
Testing Clean Architecture: From Unit Tests to Architecture Enforcement
Testing strategy per layer for Kids Learn. Domain unit tests without mocks, Application tests with NSubstitute, integration tests with Testcontainers, and NetArchTest for enforcing the Dependency Rule.
Vertical Slices Inside Clean Architecture: The Best of Both Worlds
Why pure Clean Architecture scatters features across projects, how Vertical Slice Architecture solves this, and the hybrid approach we use in Kids Learn.
EF Core 10, Minimal APIs, and the Outer Layers Nobody Gets Right
Implementing Infrastructure with EF Core 10 (pgvector, JSON columns), AI service integrations, Minimal APIs with Route Groups, authentication, and wiring it all together in Program.cs.
The Voice AI Interview Playbook: Cascaded vs. Speech-to-Speech — Choosing Your Pipeline Architecture
The cascaded STT→LLM→TTS pipeline gives you control. Speech-to-speech models give you speed. Here's how to choose — and why the best systems use both.
CQRS, Wolverine vs MediatR, and the Application Layer That Keeps Your Sanity
Command/Query separation for Kids Learn, pipeline behaviors, the MediatR licensing debate, Wolverine as the modern alternative, and the Repository Pattern in 2026.
The Voice AI Interview Playbook: Why Real-Time Voice Changes Everything
The landscape of real-time voice AI has shifted. Gemini Live, OpenAI Realtime, Bedrock Nova Sonic, and Grok make sub-500ms AI conversations possible. Here's the reference architecture for building a production voice interview platform.
Building a Domain Layer That Actually Has Behavior (Not Just Properties)
Rich domain models for Kids Learn with C# 14. Entities with invariants, value objects, domain events, aggregate roots, and architecture tests to enforce the rules.
Clean Architecture in .NET 10: Why I Stopped Copy-Pasting Templates and Started Understanding the Rules
What Clean Architecture actually means in .NET 10, the Dependency Rule explained with real code, C# 14 features that matter, and setting up the Kids Learn solution structure.
From Idea to Production: Building a SaaS Product with Claude, Gemini, and Agentic AI
How I designed, analyzed, implemented, and tested Kids Learn — an AI-powered educational SaaS platform — using Claude as my development partner, Gemini for AI features, Next.js, PostgreSQL, and pgvector. A complete walkthrough from napkin sketch to production.
I Built This Site in a Weekend with Astro (And You Should Too)
After trying Next.js, Gatsby, Hugo, and plain HTML for personal sites, I finally found the framework that fits. Here's why Astro won.
Why We Stopped Fighting the Monolith and Started Strangling It
The story of migrating a 2M+ line retail platform to microservices. What the strangler pattern actually looks like when you're in the middle of it.
Stay in the loop
Get notified when I publish new posts on AI, .NET, cloud architecture and more.