The Engineering Notebook — page 15 of 32
Notes on building with AI, agents & the modern stack.
Deep dives on AI/ML, RAG systems, agent engineering, and senior-engineer architecture decisions — a new post every week.
Developer Tools Free vs Paid Vibe Coding Tools in 2026: What You Actually Get (and What You're Paying For)
A tool-by-tool breakdown of free tier limits vs paid plans for Cursor, Claude Code, Bolt, Windsurf, Lovable, and v0 — with specific token counts, feature gates, and the real capability gaps.
AI and Machine Learning Building an AI Agent With OpenAI + LangChain: What the freeCodeCamp Course Teaches and What It Misses [2026]
The freeCodeCamp AI agent course is pulling 15,000+ views/day. Here are the 3 production gaps it leaves wide open — and how to close them before your agent burns $108/hour.
Developer Tools AI Coding Workflow 2026: What a YC Founder's Stack Taught Me About the Hard Parts [Guide]
AI didn't make coding easier — it eliminated the easy parts. Here's how I rebuilt my entire dev workflow around Claude Code, Cursor, and the brutal reality that architecture is now the whole job.
Technology Hermes Agent Desktop Free With Local LLMs: The Claude Code Alternative Nobody's Billing You For [2026]
Hermes Agent runs a full coding agent on your local machine with zero API costs. Here's which models actually work, the hardware you need, and how to set it up.
AI and Machine Learning NVIDIA RTX Spark: What the Backlash Gets Wrong About AI on Your Desktop [2026]
RTX Spark launched to massive controversy — privacy fears, Apple Silicon comparisons, and marketing skepticism. Here's what actually matters for developers running local models.
AI and Machine Learning Gemma 4 12B vs GPT-4o Mini vs Claude Haiku: Is Google's Local LLM Good Enough to Replace API Calls? [2026]
I ran Gemma's 12B model locally via Ollama and compared it against GPT-4o Mini and Claude Haiku on real dev tasks — here's when the free local model actually beats paid APIs.
AI and Machine Learning MCP vs OpenAI Function Calling 2026: Which Tool Protocol Wins?
MCP wins for multi-model, cross-vendor agent ecosystems; OpenAI function calling wins for teams already deep in the OpenAI stack. Your choice depends on how vendor-locked you're willing to be.
Developer Tools tRPC vs GraphQL 2026: Which API Layer Should You Actually Use?
tRPC wins for full-stack TypeScript monorepos where speed of iteration matters most; GraphQL wins for multi-client, multi-team APIs that need flexible querying. Pick based on your client diversity, not just your language preference.
Cloud and DevOps ClickHouse vs PostgreSQL for Analytics in 2026: Which DB Wins?
ClickHouse dominates analytical workloads with blazing columnar speed; PostgreSQL wins when you need OLTP reliability, rich SQL, and a mature ecosystem. Your choice depends almost entirely on your query patterns.
Frontend and Mobile Tailwind CSS vs CSS Modules 2026: Which Wins for Your Stack?
Tailwind CSS wins for rapid UI development, design systems, and teams that want co-located styles; CSS Modules wins for strict encapsulation, legacy codebases, and teams that prefer semantic, maintainable class names. Your framework choice and team size tip the scales.
Cloud and DevOps Cloudflare Workers vs Vercel Functions 2026: Which Edge Platform Wins?
Cloudflare Workers wins for raw edge performance, global scale, and cost efficiency at volume; Vercel Functions wins for Next.js teams who need frictionless DX and tight framework integration. Your stack decides the winner.
Cloud and DevOps Fly.io vs Railway in 2026: Which PaaS Actually Wins?
Railway wins for rapid prototyping and team-friendly simplicity; Fly.io wins for global edge performance and production-grade control. If you're choosing a modern PaaS in 2026, the right answer depends almost entirely on where you are in your product lifecycle.