Implementation Notes
What shipped, what it cost, and what broke. Lessons from real IBM, AI, and infrastructure deployments.
Building production MCP servers and clients with Python. Covers the JSON-RPC 2.0 wire protocol, transport layers (stdio, SSE, Streamable HTTP), filesystem tool implementation with path traversal protection, and connecting Claude to your custom tools.
A real migration story from Next.js 15.1 with Tailwind v3.4 to Next.js 16 with Tailwind v4. Covers the CSS-first config system, OKLCH color conversion, Turbopack landmines, and every class name that changed.
Running quantized LLMs behind a FastAPI proxy with Ollama and vLLM backends. Covers model quantization tradeoffs, GGUF vs GPTQ vs AWQ, streaming responses, request queuing, Docker Compose deployment, and production monitoring.
Compiling Rust to WebAssembly for real browser performance wins. Includes image filter benchmarks (grayscale, box blur), SIMD optimization, JS-Wasm boundary analysis, bundle size strategies, and Next.js integration.
A three-tier token architecture (primitive, semantic, component) with CSS custom properties, Style Dictionary transforms, Tailwind v4 integration, and dark mode that's a token swap instead of a stylesheet rewrite.
A deep dive into LTI 1.3 — the OIDC-based protocol that connects learning tools to Canvas, Moodle, and Blackboard. Covers the three-step launch flow, JWT anatomy, ltijs implementation, NRPS roster access, and AGS grade passback.
Production TypeScript patterns: const type parameters, satisfies operator, template literal types for API routes, branded types for domain safety, discriminated unions, and the builder pattern with full type inference.
Hardening Linux servers running GPU inference and training workloads. Covers SSH lockdown, Docker rootless mode, NVIDIA driver security, systemd sandboxing, audit logging, and network segmentation for AI infrastructure.
Building production multi-agent systems from scratch. Covers ReAct, plan-and-execute, supervisor, and pipeline patterns with full Python implementations. Includes inter-agent communication, human-in-the-loop, memory systems, failure modes, and a real EdTech production architecture.
A practical mental model for React Server Components. Covers the two-runtime architecture, serialization boundary rules, composition patterns, streaming with Suspense, caching layers, and common mistakes that break production apps.
Hands-on comparison of Pinecone, Qdrant, Weaviate, pgvector, and Chroma for production AI. Covers embedding fundamentals, indexing algorithms (HNSW, IVF, PQ), chunking strategies, reranking, and when each database fits.
What Tailwind doesn't cover: cascade layers for specificity control, CSS Modules for complex components, vanilla-extract for type-safe theming, and the architectural patterns that make them all work together in production.